Merge branch 'perf/urgent' into perf/core, before applying dependent patches
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Makefile b/Makefile
index 92a7078..9349d89 100644
--- a/Makefile
+++ b/Makefile
@@ -215,7 +215,6 @@
export srctree objtree VPATH
-
# SUBARCH tells the usermode build what the underlying arch is. That is set
# first, and if a usermode build is happening, the "ARCH=um" on the command
# line overrides the setting of ARCH below. If a native build is happening,
@@ -1497,11 +1496,11 @@
# Clear a bunch of variables before executing the submake
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/ $*
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/ $*
# Single targets
# ---------------------------------------------------------------------------
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index dd319e5..356bc7b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -921,6 +921,9 @@
case 69: /* Haswell Celeron */
ret = hsw_uncore_pci_init();
break;
+ case 61: /* Broadwell */
+ ret = bdw_uncore_pci_init();
+ break;
default:
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index f789ec9..ebab4ba 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -327,6 +327,7 @@
int snb_uncore_pci_init(void);
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 4562e9e..b005a78 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -7,6 +7,7 @@
#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -486,6 +487,14 @@
{ /* end: all zeroes */ },
};
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -501,6 +510,11 @@
.id_table = hsw_uncore_pci_ids,
};
+static struct pci_driver bdw_uncore_pci_driver = {
+ .name = "bdw_uncore",
+ .id_table = bdw_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -514,6 +528,7 @@
IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
+ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
{ /* end marker */ }
};
@@ -561,6 +576,11 @@
return imc_uncore_pci_init();
}
+int bdw_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
/* end of Sandy Bridge uncore support */
/* Nehalem uncore support */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d8a82a8..248f782 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -794,11 +794,33 @@
extern struct static_key_deferred perf_sched_events;
+static __always_inline bool
+perf_sw_migrate_enabled(void)
+{
+ if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
+ return true;
+ return false;
+}
+
+static inline void perf_event_task_migrate(struct task_struct *task)
+{
+ if (perf_sw_migrate_enabled())
+ task->sched_migrated = 1;
+}
+
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
+
+ if (perf_sw_migrate_enabled() && task->sched_migrated) {
+ struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+ perf_fetch_caller_regs(regs);
+ ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+ task->sched_migrated = 0;
+ }
}
static inline void perf_event_task_sched_out(struct task_struct *prev,
@@ -921,6 +943,8 @@
static inline void *
perf_get_aux(struct perf_output_handle *handle) { return NULL; }
static inline void
+perf_event_task_migrate(struct task_struct *task) { }
+static inline void
perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task) { }
static inline void
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e61..2c5e6c3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1356,9 +1356,6 @@
#endif
struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
-#endif
/* per-thread vma caching */
u32 vmacache_seqnum;
struct vm_area_struct *vmacache[VMACACHE_SIZE];
@@ -1381,10 +1378,14 @@
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
+ unsigned sched_migrated:1;
#ifdef CONFIG_MEMCG_KMEM
unsigned memcg_kmem_skip_account:1;
#endif
+#ifdef CONFIG_COMPAT_BRK
+ unsigned brk_randomized:1;
+#endif
unsigned long atomic_flags; /* Flags needing atomic access. */
diff --git a/init/Kconfig b/init/Kconfig
index dc24dec..81050e4 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1637,7 +1637,7 @@
config DEBUG_PERF_USE_VMALLOC
default n
bool "Debug: use vmalloc to back perf mmap() buffers"
- depends on PERF_EVENTS && DEBUG_KERNEL
+ depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
select PERF_USE_VMALLOC
help
Use vmalloc memory to back perf mmap() buffers.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1236732..db9b10a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1049,7 +1049,7 @@
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
- perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+ perf_event_task_migrate(p);
}
__set_task_cpu(p, new_cpu);
diff --git a/tools/Makefile b/tools/Makefile
index 9a617ad..b351027 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -1,3 +1,8 @@
+# Some of the tools (perf) use same make variables
+# as in kernel build.
+export srctree=
+export objtree=
+
include scripts/Makefile.include
help:
@@ -47,11 +52,16 @@
liblockdep: FORCE
$(call descend,lib/lockdep)
-libapikfs: FORCE
+libapi: FORCE
$(call descend,lib/api)
-perf: libapikfs FORCE
- $(call descend,$@)
+# The perf build does not follow the descend function setup,
+# invoking it via it's own make rule.
+PERF_O = $(if $(O),$(O)/tools/perf,)
+
+perf: FORCE
+ $(Q)mkdir -p $(PERF_O) .
+ $(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir=
selftests: FORCE
$(call descend,testing/$@)
@@ -97,10 +107,10 @@
liblockdep_clean:
$(call descend,lib/lockdep,clean)
-libapikfs_clean:
+libapi_clean:
$(call descend,lib/api,clean)
-perf_clean: libapikfs_clean
+perf_clean:
$(call descend,$(@:_clean=),clean)
selftests_clean:
diff --git a/tools/arch/alpha/include/asm/barrier.h b/tools/arch/alpha/include/asm/barrier.h
new file mode 100644
index 0000000..95df19c
--- /dev/null
+++ b/tools/arch/alpha/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+#define __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+
+#define mb() __asm__ __volatile__("mb": : :"memory")
+#define rmb() __asm__ __volatile__("mb": : :"memory")
+#define wmb() __asm__ __volatile__("wmb": : :"memory")
+
+#endif /* __TOOLS_LINUX_ASM_ALPHA_BARRIER_H */
diff --git a/tools/arch/arm/include/asm/barrier.h b/tools/arch/arm/include/asm/barrier.h
new file mode 100644
index 0000000..005c618
--- /dev/null
+++ b/tools/arch/arm/include/asm/barrier.h
@@ -0,0 +1,12 @@
+#ifndef _TOOLS_LINUX_ASM_ARM_BARRIER_H
+#define _TOOLS_LINUX_ASM_ARM_BARRIER_H
+
+/*
+ * Use the __kuser_memory_barrier helper in the CPU helper page. See
+ * arch/arm/kernel/entry-armv.S in the kernel source for details.
+ */
+#define mb() ((void(*)(void))0xffff0fa0)()
+#define wmb() ((void(*)(void))0xffff0fa0)()
+#define rmb() ((void(*)(void))0xffff0fa0)()
+
+#endif /* _TOOLS_LINUX_ASM_ARM_BARRIER_H */
diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
new file mode 100644
index 0000000..a0483c8
--- /dev/null
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -0,0 +1,16 @@
+#ifndef _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+#define _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+
+/*
+ * From tools/perf/perf-sys.h, last modified in:
+ * f428ebd184c82a7914b2aa7e9f868918aaf7ea78 perf tools: Fix AAAAARGH64 memory barriers
+ *
+ * XXX: arch/arm64/include/asm/barrier.h in the kernel sources use dsb, is this
+ * a case like for arm32 where we do things differently in userspace?
+ */
+
+#define mb() asm volatile("dmb ish" ::: "memory")
+#define wmb() asm volatile("dmb ishst" ::: "memory")
+#define rmb() asm volatile("dmb ishld" ::: "memory")
+
+#endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
new file mode 100644
index 0000000..e4422b4
--- /dev/null
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -0,0 +1,48 @@
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * Memory barrier definitions. This is based on information published
+ * in the Processor Abstraction Layer and the System Abstraction Layer
+ * manual.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ * David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _TOOLS_LINUX_ASM_IA64_BARRIER_H
+#define _TOOLS_LINUX_ASM_IA64_BARRIER_H
+
+#include <linux/compiler.h>
+
+/*
+ * Macros to force memory ordering. In these descriptions, "previous"
+ * and "subsequent" refer to program order; "visible" means that all
+ * architecturally visible effects of a memory access have occurred
+ * (at a minimum, this means the memory has been read or written).
+ *
+ * wmb(): Guarantees that all preceding stores to memory-
+ * like regions are visible before any subsequent
+ * stores and that all following stores will be
+ * visible only after all previous stores.
+ * rmb(): Like wmb(), but for reads.
+ * mb(): wmb()/rmb() combo, i.e., all previous memory
+ * accesses are visible before all subsequent
+ * accesses and vice versa. This is also known as
+ * a "fence."
+ *
+ * Note: "mb()" and its variants cannot be used as a fence to order
+ * accesses to memory mapped I/O registers. For that, mf.a needs to
+ * be used. However, we don't want to always use mf.a because (a)
+ * it's (presumably) much slower than mf and (b) mf.a is supported for
+ * sequential memory pages only.
+ */
+
+/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
+#define ia64_mf() asm volatile ("mf" ::: "memory")
+
+#define mb() ia64_mf()
+#define rmb() mb()
+#define wmb() mb()
+
+#endif /* _TOOLS_LINUX_ASM_IA64_BARRIER_H */
diff --git a/tools/arch/mips/include/asm/barrier.h b/tools/arch/mips/include/asm/barrier.h
new file mode 100644
index 0000000..80f96f7
--- /dev/null
+++ b/tools/arch/mips/include/asm/barrier.h
@@ -0,0 +1,20 @@
+#ifndef _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+#define _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in c1e028ef40b8d6943b767028ba17d4f2ba020edb, more work needed to make it
+ * more closely follow the Linux kernel arch/mips/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+#define mb() asm volatile( \
+ ".set mips2\n\t" \
+ "sync\n\t" \
+ ".set mips0" \
+ : /* no output */ \
+ : /* no input */ \
+ : "memory")
+#define wmb() mb()
+#define rmb() mb()
+
+#endif /* _TOOLS_LINUX_ASM_MIPS_BARRIER_H */
diff --git a/tools/arch/powerpc/include/asm/barrier.h b/tools/arch/powerpc/include/asm/barrier.h
new file mode 100644
index 0000000..b23aee8
--- /dev/null
+++ b/tools/arch/powerpc/include/asm/barrier.h
@@ -0,0 +1,29 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+#define _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory). The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ */
+#define mb() __asm__ __volatile__ ("sync" : : : "memory")
+#define rmb() __asm__ __volatile__ ("sync" : : : "memory")
+#define wmb() __asm__ __volatile__ ("sync" : : : "memory")
+
+#endif /* _TOOLS_LINUX_ASM_POWERPC_BARRIER_H */
diff --git a/tools/arch/s390/include/asm/barrier.h b/tools/arch/s390/include/asm/barrier.h
new file mode 100644
index 0000000..f851412
--- /dev/null
+++ b/tools/arch/s390/include/asm/barrier.h
@@ -0,0 +1,30 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __TOOLS_LINUX_ASM_BARRIER_H
+#define __TOOLS_LINUX_ASM_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+/* Fast-BCR without checkpoint synchronization */
+#define __ASM_BARRIER "bcr 14,0\n"
+#else
+#define __ASM_BARRIER "bcr 15,0\n"
+#endif
+
+#define mb() do { asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
+
+#define rmb() mb()
+#define wmb() mb()
+
+#endif /* __TOOLS_LIB_ASM_BARRIER_H */
diff --git a/tools/arch/sh/include/asm/barrier.h b/tools/arch/sh/include/asm/barrier.h
new file mode 100644
index 0000000..c18fd75
--- /dev/null
+++ b/tools/arch/sh/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __TOOLS_LINUX_ASM_SH_BARRIER_H
+#define __TOOLS_LINUX_ASM_SH_BARRIER_H
+
+/*
+ * A brief note on ctrl_barrier(), the control register write barrier.
+ *
+ * Legacy SH cores typically require a sequence of 8 nops after
+ * modification of a control register in order for the changes to take
+ * effect. On newer cores (like the sh4a and sh5) this is accomplished
+ * with icbi.
+ *
+ * Also note that on sh4a in the icbi case we can forego a synco for the
+ * write barrier, as it's not necessary for control registers.
+ *
+ * Historically we have only done this type of barrier for the MMUCR, but
+ * it's also necessary for the CCR, so we make it generic here instead.
+ */
+#if defined(__SH4A__) || defined(__SH5__)
+#define mb() __asm__ __volatile__ ("synco": : :"memory")
+#define rmb() mb()
+#define wmb() mb()
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif /* __TOOLS_LINUX_ASM_SH_BARRIER_H */
diff --git a/tools/arch/sparc/include/asm/barrier.h b/tools/arch/sparc/include/asm/barrier.h
new file mode 100644
index 0000000..8c017b3
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#define ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#if defined(__sparc__) && defined(__arch64__)
+#include "barrier_64.h"
+#else
+#include "barrier_32.h"
+#endif
+#endif
diff --git a/tools/arch/sparc/include/asm/barrier_32.h b/tools/arch/sparc/include/asm/barrier_32.h
new file mode 100644
index 0000000..c5eadd0
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier_32.h
@@ -0,0 +1,6 @@
+#ifndef __TOOLS_PERF_SPARC_BARRIER_H
+#define __TOOLS_PERF_SPARC_BARRIER_H
+
+#include <asm-generic/barrier.h>
+
+#endif /* !(__TOOLS_PERF_SPARC_BARRIER_H) */
diff --git a/tools/arch/sparc/include/asm/barrier_64.h b/tools/arch/sparc/include/asm/barrier_64.h
new file mode 100644
index 0000000..9a7d732
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier_64.h
@@ -0,0 +1,42 @@
+#ifndef __TOOLS_LINUX_SPARC64_BARRIER_H
+#define __TOOLS_LINUX_SPARC64_BARRIER_H
+
+/* Copied from the kernel sources to tools/:
+ *
+ * These are here in an effort to more fully work around Spitfire Errata
+ * #51. Essentially, if a memory barrier occurs soon after a mispredicted
+ * branch, the chip can stop executing instructions until a trap occurs.
+ * Therefore, if interrupts are disabled, the chip can hang forever.
+ *
+ * It used to be believed that the memory barrier had to be right in the
+ * delay slot, but a case has been traced recently wherein the memory barrier
+ * was one instruction after the branch delay slot and the chip still hung.
+ * The offending sequence was the following in sym_wakeup_done() of the
+ * sym53c8xx_2 driver:
+ *
+ * call sym_ccb_from_dsa, 0
+ * movge %icc, 0, %l0
+ * brz,pn %o0, .LL1303
+ * mov %o0, %l2
+ * membar #LoadLoad
+ *
+ * The branch has to be mispredicted for the bug to occur. Therefore, we put
+ * the memory barrier explicitly into a "branch always, predicted taken"
+ * delay slot to avoid the problem case.
+ */
+#define membar_safe(type) \
+do { __asm__ __volatile__("ba,pt %%xcc, 1f\n\t" \
+ " membar " type "\n" \
+ "1:\n" \
+ : : : "memory"); \
+} while (0)
+
+/* The kernel always executes in TSO memory model these days,
+ * and furthermore most sparc64 chips implement more stringent
+ * memory ordering than required by the specifications.
+ */
+#define mb() membar_safe("#StoreLoad")
+#define rmb() __asm__ __volatile__("":::"memory")
+#define wmb() __asm__ __volatile__("":::"memory")
+
+#endif /* !(__TOOLS_LINUX_SPARC64_BARRIER_H) */
diff --git a/tools/arch/tile/include/asm/barrier.h b/tools/arch/tile/include/asm/barrier.h
new file mode 100644
index 0000000..7d3692c
--- /dev/null
+++ b/tools/arch/tile/include/asm/barrier.h
@@ -0,0 +1,15 @@
+#ifndef _TOOLS_LINUX_ASM_TILE_BARRIER_H
+#define _TOOLS_LINUX_ASM_TILE_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in 620830b6954913647b7c7f68920cf48eddf6ad92, more work needed to make it
+ * more closely follow the Linux kernel arch/tile/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+
+#define mb() asm volatile ("mf" ::: "memory")
+#define wmb() mb()
+#define rmb() mb()
+
+#endif /* _TOOLS_LINUX_ASM_TILE_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
new file mode 100644
index 0000000..059e33e
--- /dev/null
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -0,0 +1,65 @@
+#ifndef _TOOLS_LINUX_ASM_X86_ATOMIC_H
+#define _TOOLS_LINUX_ASM_X86_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "rmwcc.h"
+
+#define LOCK_PREFIX "\n\tlock; "
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+ return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+ asm volatile(LOCK_PREFIX "incl %0"
+ : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+ GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+}
+
+#endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
new file mode 100644
index 0000000..f366d8e
--- /dev/null
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -0,0 +1,28 @@
+#ifndef _TOOLS_LINUX_ASM_X86_BARRIER_H
+#define _TOOLS_LINUX_ASM_X86_BARRIER_H
+
+/*
+ * Copied from the Linux kernel sources, and also moving code
+ * out from tools/perf/perf-sys.h so as to make it be located
+ * in a place similar as in the kernel sources.
+ *
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#if defined(__i386__)
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#elif defined(__x86_64__)
+#define mb() asm volatile("mfence":::"memory")
+#define rmb() asm volatile("lfence":::"memory")
+#define wmb() asm volatile("sfence" ::: "memory")
+#endif
+
+#endif /* _TOOLS_LINUX_ASM_X86_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
new file mode 100644
index 0000000..a6669bc
--- /dev/null
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -0,0 +1,41 @@
+#ifndef _TOOLS_LINUX_ASM_X86_RMWcc
+#define _TOOLS_LINUX_ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...) \
+do { \
+ asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \
+ : : "m" (var), ## __VA_ARGS__ \
+ : "memory" : cc_label); \
+ return 0; \
+cc_label: \
+ return 1; \
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+ __GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
+ __GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...) \
+do { \
+ char c; \
+ asm volatile (fullop "; set" cc " %1" \
+ : "+m" (var), "=qm" (c) \
+ : __VA_ARGS__ : "memory"); \
+ return c != 0; \
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+ __GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
+ __GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _TOOLS_LINUX_ASM_X86_RMWcc */
diff --git a/tools/arch/xtensa/include/asm/barrier.h b/tools/arch/xtensa/include/asm/barrier.h
new file mode 100644
index 0000000..583800b
--- /dev/null
+++ b/tools/arch/xtensa/include/asm/barrier.h
@@ -0,0 +1,18 @@
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2012 Tensilica Inc.
+ */
+
+#ifndef _TOOLS_LINUX_XTENSA_SYSTEM_H
+#define _TOOLS_LINUX_XTENSA_SYSTEM_H
+
+#define mb() ({ __asm__ __volatile__("memw" : : : "memory"); })
+#define rmb() barrier()
+#define wmb() mb()
+
+#endif /* _TOOLS_LINUX_XTENSA_SYSTEM_H */
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3a0b0ca..2975632 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@
# the rule that uses them - an example for that is the 'bionic'
# feature check. ]
#
-FEATURE_TESTS = \
+FEATURE_TESTS ?= \
backtrace \
dwarf \
fortify-source \
@@ -53,7 +53,7 @@
zlib \
lzma
-FEATURE_DISPLAY = \
+FEATURE_DISPLAY ?= \
dwarf \
glibc \
gtk2 \
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
new file mode 100644
index 0000000..2ba78c9
--- /dev/null
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -0,0 +1,63 @@
+#ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
+#define __TOOLS_ASM_GENERIC_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ *
+ * Excerpts obtained from the Linux kernel sources.
+ */
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+ return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+ __sync_add_and_fetch(&v->counter, 1);
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+ return __sync_sub_and_fetch(&v->counter, 1) == 0;
+}
+
+#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/asm-generic/barrier.h b/tools/include/asm-generic/barrier.h
new file mode 100644
index 0000000..47b9339
--- /dev/null
+++ b/tools/include/asm-generic/barrier.h
@@ -0,0 +1,44 @@
+/*
+ * Copied from the kernel sources to tools/perf/:
+ *
+ * Generic barrier definitions, originally based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+#define __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb() barrier()
+#endif
+
+#ifndef rmb
+#define rmb() mb()
+#endif
+
+#ifndef wmb
+#define wmb() mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __TOOLS_LINUX_ASM_GENERIC_BARRIER_H */
diff --git a/tools/include/asm/atomic.h b/tools/include/asm/atomic.h
new file mode 100644
index 0000000..70794f5
--- /dev/null
+++ b/tools/include/asm/atomic.h
@@ -0,0 +1,10 @@
+#ifndef __TOOLS_LINUX_ASM_ATOMIC_H
+#define __TOOLS_LINUX_ASM_ATOMIC_H
+
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/atomic.h"
+#else
+#include <asm-generic/atomic-gcc.h>
+#endif
+
+#endif /* __TOOLS_LINUX_ASM_ATOMIC_H */
diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h
new file mode 100644
index 0000000..ac66ac5
--- /dev/null
+++ b/tools/include/asm/barrier.h
@@ -0,0 +1,27 @@
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/barrier.h"
+#elif defined(__arm__)
+#include "../../arch/arm/include/asm/barrier.h"
+#elif defined(__aarch64__)
+#include "../../arch/arm64/include/asm/barrier.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/asm/barrier.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/asm/barrier.h"
+#elif defined(__sh__)
+#include "../../arch/sh/include/asm/barrier.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/asm/barrier.h"
+#elif defined(__tile__)
+#include "../../arch/tile/include/asm/barrier.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/asm/barrier.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/asm/barrier.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/asm/barrier.h"
+#elif defined(__xtensa__)
+#include "../../arch/xtensa/include/asm/barrier.h"
+#else
+#include <asm-generic/barrier.h>
+#endif
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
new file mode 100644
index 0000000..4e3d3d1
--- /dev/null
+++ b/tools/include/linux/atomic.h
@@ -0,0 +1,6 @@
+#ifndef __TOOLS_LINUX_ATOMIC_H
+#define __TOOLS_LINUX_ATOMIC_H
+
+#include <asm/atomic.h>
+
+#endif /* __TOOLS_LINUX_ATOMIC_H */
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 88461f0..f0e7267 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,6 +1,10 @@
#ifndef _TOOLS_LINUX_COMPILER_H_
#define _TOOLS_LINUX_COMPILER_H_
+/* Optimization barrier */
+/* The "volatile" is due to gcc bugs */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
#ifndef __always_inline
# define __always_inline inline __attribute__((always_inline))
#endif
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index b5cf25e..8ebf627 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -60,6 +60,14 @@
typedef __u64 __bitwise __le64;
typedef __u64 __bitwise __be64;
+typedef struct {
+ int counter;
+} atomic_t;
+
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
struct list_head {
struct list_head *next, *prev;
};
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index d410da3..8464039 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -34,9 +34,15 @@
DESTDIR ?=
DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+ libdir_relative = lib64
+else
+ libdir_relative = lib
+endif
+
prefix ?= /usr/local
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+libdir = $(prefix)/$(libdir_relative)
man_dir = $(prefix)/share/man
man_dir_SQ = '$(subst ','\'',$(man_dir))'
@@ -58,7 +64,7 @@
override plugin_dir = $(HOME)/.traceevent/plugins
set_plugin_dir := 0
else
-override plugin_dir = $(prefix)/lib/traceevent/plugins
+override plugin_dir = $(libdir)/traceevent/plugins
endif
endif
@@ -85,11 +91,11 @@
#$(info Determined 'srctree' to be $(srctree))
endif
-export prefix bindir src obj
+export prefix libdir src obj
# Shell quotes
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
LIB_FILE = libtraceevent.a libtraceevent.so
@@ -240,7 +246,7 @@
install_lib: all_cmd install_plugins
$(call QUIET_INSTALL, $(LIB_FILE)) \
- $(call do_install,$(LIB_FILE),$(bindir_SQ))
+ $(call do_install,$(LIB_FILE),$(libdir_SQ))
install_plugins: $(PLUGINS)
$(call QUIET_INSTALL, trace_plugins) \
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 29f94f6..cc25f05 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1387,7 +1387,7 @@
do_warning_event(event, "%s: no type found", __func__);
goto fail;
}
- field->name = last_token;
+ field->name = field->alias = last_token;
if (test_type(type, EVENT_OP))
goto fail;
@@ -1469,7 +1469,7 @@
size_dynamic = type_size(field->name);
free_token(field->name);
strcat(field->type, brackets);
- field->name = token;
+ field->name = field->alias = token;
type = read_token(&token);
} else {
char *new_type;
@@ -6444,6 +6444,8 @@
void pevent_free_format_field(struct format_field *field)
{
free(field->type);
+ if (field->alias != field->name)
+ free(field->alias);
free(field->name);
free(field);
}
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 86a5839..063b197 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -191,6 +191,7 @@
struct event_format *event;
char *type;
char *name;
+ char *alias;
int offset;
int size;
unsigned int arraylen;
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index 4592d84..ec57d0c 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -4,6 +4,19 @@
#include <endian.h>
#include "event-parse.h"
+/*
+ * From glibc endian.h, for older systems where it is not present, e.g.: RHEL5,
+ * Fedora6.
+ */
+#ifndef le16toh
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+# define le16toh(x) (x)
+# else
+# define le16toh(x) __bswap_16 (x)
+# endif
+#endif
+
+
static unsigned long long
process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
{
diff --git a/tools/perf/Documentation/callchain-overhead-calculation.txt b/tools/perf/Documentation/callchain-overhead-calculation.txt
new file mode 100644
index 0000000..1a75792
--- /dev/null
+++ b/tools/perf/Documentation/callchain-overhead-calculation.txt
@@ -0,0 +1,108 @@
+Overhead calculation
+--------------------
+The overhead can be shown in two columns as 'Children' and 'Self' when
+perf collects callchains. The 'self' overhead is simply calculated by
+adding all period values of the entry - usually a function (symbol).
+This is the value that perf shows traditionally and sum of all the
+'self' overhead values should be 100%.
+
+The 'children' overhead is calculated by adding all period values of
+the child functions so that it can show the total overhead of the
+higher level functions even if they don't directly execute much.
+'Children' here means functions that are called from another (parent)
+function.
+
+It might be confusing that the sum of all the 'children' overhead
+values exceeds 100% since each of them is already an accumulation of
+'self' overhead of its child functions. But with this enabled, users
+can find which function has the most overhead even if samples are
+spread over the children.
+
+Consider the following example; there are three functions like below.
+
+-----------------------
+void foo(void) {
+ /* do something */
+}
+
+void bar(void) {
+ /* do something */
+ foo();
+}
+
+int main(void) {
+ bar()
+ return 0;
+}
+-----------------------
+
+In this case 'foo' is a child of 'bar', and 'bar' is an immediate
+child of 'main' so 'foo' also is a child of 'main'. In other words,
+'main' is a parent of 'foo' and 'bar', and 'bar' is a parent of 'foo'.
+
+Suppose all samples are recorded in 'foo' and 'bar' only. When it's
+recorded with callchains the output will show something like below
+in the usual (self-overhead-only) output of perf report:
+
+----------------------------------
+Overhead Symbol
+........ .....................
+ 60.00% foo
+ |
+ --- foo
+ bar
+ main
+ __libc_start_main
+
+ 40.00% bar
+ |
+ --- bar
+ main
+ __libc_start_main
+----------------------------------
+
+When the --children option is enabled, the 'self' overhead values of
+child functions (i.e. 'foo' and 'bar') are added to the parents to
+calculate the 'children' overhead. In this case the report could be
+displayed as:
+
+-------------------------------------------
+Children Self Symbol
+........ ........ ....................
+ 100.00% 0.00% __libc_start_main
+ |
+ --- __libc_start_main
+
+ 100.00% 0.00% main
+ |
+ --- main
+ __libc_start_main
+
+ 100.00% 40.00% bar
+ |
+ --- bar
+ main
+ __libc_start_main
+
+ 60.00% 60.00% foo
+ |
+ --- foo
+ bar
+ main
+ __libc_start_main
+-------------------------------------------
+
+In the above output, the 'self' overhead of 'foo' (60%) was add to the
+'children' overhead of 'bar', 'main' and '\_\_libc_start_main'.
+Likewise, the 'self' overhead of 'bar' (40%) was added to the
+'children' overhead of 'main' and '\_\_libc_start_main'.
+
+So '\_\_libc_start_main' and 'main' are shown first since they have
+same (100%) 'children' overhead (even though they have zero 'self'
+overhead) and they are the parents of 'foo' and 'bar'.
+
+Since v3.16 the 'children' overhead is shown by default and the output
+is sorted by its values. The 'children' overhead is disabled by
+specifying --no-children option on the command line or by adding
+'report.children = false' or 'top.children = false' in the perf config
+file.
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index f6480cb..bf3d064 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -210,6 +210,9 @@
*wake*::
Suite for evaluating wake calls.
+*wake-parallel*::
+Suite for evaluating parallel wake calls.
+
*requeue*::
Suite for evaluating requeue calls.
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index dc7442c..b876ae3 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -44,6 +44,33 @@
--kallsyms=<file>::
kallsyms pathname
+--itrace::
+ Decode Instruction Tracing data, replacing it with synthesized events.
+ Options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ x synthesize transactions events
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+ The default is all events i.e. the same as --itrace=ibxe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 23219c6..ff0f433 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -37,7 +37,11 @@
-s <key[,key2...]>::
--sort=<key[,key2...]>::
- Sort the output (default: frag,hit,bytes)
+ Sort the output (default: 'frag,hit,bytes' for slab and 'bytes,hit'
+ for page). Available sort keys are 'ptr, callsite, bytes, hit,
+ pingpong, frag' for slab and 'page, callsite, bytes, hit, order,
+ migtype, gfp' for page. This option should be preceded by one of the
+ mode selection options - i.e. --slab, --page, --alloc and/or --caller.
-l <num>::
--line=<num>::
@@ -52,6 +56,11 @@
--page::
Analyze page allocator events
+--live::
+ Show live page stat. The perf kmem shows total allocation stat by
+ default, but this option shows live (currently allocated) pages
+ instead. (This option works with --page option only)
+
SEE ALSO
--------
linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 239609c..3a8a9ba 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -14,11 +14,13 @@
or
'perf probe' [options] --del='[GROUP:]EVENT' [...]
or
-'perf probe' --list
+'perf probe' --list[=[GROUP:]EVENT]
or
'perf probe' [options] --line='LINE'
or
'perf probe' [options] --vars='PROBEPOINT'
+or
+'perf probe' [options] --funcs
DESCRIPTION
-----------
@@ -64,8 +66,8 @@
classes(e.g. [a-z], [!A-Z]).
-l::
---list::
- List up current probe events.
+--list[=[GROUP:]EVENT]::
+ List up current probe events. This can also accept filtering patterns of event names.
-L::
--line=::
@@ -81,10 +83,15 @@
(Only for --vars) Show external defined variables in addition to local
variables.
+--no-inlines::
+ (Only for --add) Search only for non-inlined functions. The functions
+ which do not have instances are ignored.
+
-F::
---funcs::
+--funcs[=FILTER]::
Show available functions in given module or kernel. With -x/--exec,
can also list functions in a user space executable / shared library.
+ This also can accept a FILTER rule argument.
--filter=FILTER::
(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
@@ -148,7 +155,7 @@
[NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
-'$vars' special argument is also available for NAME, it is expanded to the local variables which can access at given probe point.
+'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 4847a79..280533e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -108,6 +108,8 @@
Number of mmap data pages (must be a power of two) or size
specification with appended unit character - B/K/M/G. The
size is rounded up to have nearest pages power of two value.
+ Also, by adding a comma, the number of mmap pages for AUX
+ area tracing can be specified.
--group::
Put all events in a single event group. This precedes the --event
@@ -145,7 +147,8 @@
-s::
--stat::
- Per thread counts.
+ Record per-thread event counts. Use it with 'perf report -T' to see
+ the values.
-d::
--data::
@@ -257,6 +260,13 @@
CLOCK_MONOTONIC_RAW are supported, some events might also allow
CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
+-S::
+--snapshot::
+Select AUX area tracing Snapshot Mode. This option is valid only with an
+AUX area tracing event. Optionally the number of bytes to capture per
+snapshot can be specified. In Snapshot Mode, trace data is captured only when
+signal SIGUSR2 is received.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 4879cf6..c33b69f 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -34,7 +34,8 @@
-T::
--threads::
- Show per-thread event counters
+ Show per-thread event counters. The input data file should be recorded
+ with -s option.
-c::
--comms=::
Only consider symbols in these comms. CSV that understands
@@ -193,6 +194,7 @@
Accumulate callchain of children to parent entry so that then can
show up in the output. The output will have a new "Children" column
and will be sorted on the data. It requires callchains are recorded.
+ See the `overhead calculation' section for more details.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
@@ -323,6 +325,37 @@
--header-only::
Show only perf.data header (forces --stdio).
+--itrace::
+ Options for decoding instruction tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ x synthesize transactions events
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+ The default is all events i.e. the same as --itrace=ibxe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
+
+include::callchain-overhead-calculation.txt[]
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 7944575..c82df57 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,8 @@
-f::
--fields::
Comma separated list of fields to print. Options are:
- comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
+ comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
+ srcline, period, flags.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace
@@ -165,6 +166,12 @@
At this point usage is displayed, and perf-script exits.
+ The flags field is synthesized and may have a value when Instruction
+ Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+ call, return, conditional, system, asynchronous, interrupt,
+ transaction abort, trace begin, trace end, and in transaction,
+ respectively.
+
Finally, a user may not set fields to none for all event types.
i.e., -f "" is not allowed.
@@ -221,6 +228,34 @@
--header-only
Show only perf.data header.
+--itrace::
+ Options for decoding instruction tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ x synthesize transactions events
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+ The default is all events i.e. the same as --itrace=ibxe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 3265b10..9e5b07eb 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -168,7 +168,7 @@
Accumulate callchain of children to parent entry so that then can
show up in the output. The output will have a new "Children" column
and will be sorted on the data. It requires -g/--call-graph option
- enabled.
+ enabled. See the `overhead calculation' section for more details.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
@@ -234,6 +234,7 @@
Pressing any unmapped key displays a menu, and prompts for input.
+include::callchain-overhead-calculation.txt[]
SEE ALSO
--------
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index ba03fd5..1db9c8b 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,7 @@
-e::
--expr::
- List of events to show, currently only syscall names.
+ List of syscalls to show, currently only syscall names.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 11ccbb2..a83cf75 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,12 +1,30 @@
tools/perf
+tools/arch/alpha/include/asm/barrier.h
+tools/arch/arm/include/asm/barrier.h
+tools/arch/ia64/include/asm/barrier.h
+tools/arch/mips/include/asm/barrier.h
+tools/arch/powerpc/include/asm/barrier.h
+tools/arch/s390/include/asm/barrier.h
+tools/arch/sh/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier_32.h
+tools/arch/sparc/include/asm/barrier_64.h
+tools/arch/tile/include/asm/barrier.h
+tools/arch/x86/include/asm/barrier.h
+tools/arch/xtensa/include/asm/barrier.h
tools/scripts
tools/build
+tools/arch/x86/include/asm/atomic.h
+tools/arch/x86/include/asm/rmwcc.h
tools/lib/traceevent
tools/lib/api
tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h
tools/lib/util/find_next_bit.c
+tools/include/asm/atomic.h
+tools/include/asm/barrier.h
tools/include/asm/bug.h
+tools/include/asm-generic/barrier.h
tools/include/asm-generic/bitops/arch_hweight.h
tools/include/asm-generic/bitops/atomic.h
tools/include/asm-generic/bitops/const_hweight.h
@@ -17,6 +35,7 @@
tools/include/asm-generic/bitops/fls.h
tools/include/asm-generic/bitops/hweight.h
tools/include/asm-generic/bitops.h
+tools/include/linux/atomic.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h
tools/include/linux/export.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c43a205..03409cc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -73,6 +73,8 @@
# for CTF data format.
#
# Define NO_LZMA if you do not want to support compressed (xz) kernel modules
+#
+# Define NO_AUXTRACE if you do not want AUX area tracing support
ifeq ($(srctree),)
srctree := $(patsubst %/,%,$(dir $(shell pwd)))
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 0af6e9b..7b8b0d1 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,4 +1,5 @@
libperf-y += header.o
+libperf-y += sym-handling.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
new file mode 100644
index 0000000..bbc1a50
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -0,0 +1,82 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+ return ehdr.e_type == ET_EXEC ||
+ ehdr.e_type == ET_REL ||
+ ehdr.e_type == ET_DYN;
+}
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+void arch__elf_sym_adjust(GElf_Sym *sym)
+{
+ sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#endif
+#endif
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+int arch__choose_best_symbol(struct symbol *syma,
+ struct symbol *symb __maybe_unused)
+{
+ char *sym = syma->name;
+
+ /* Skip over any initial dot */
+ if (*sym == '.')
+ sym++;
+
+ /* Avoid "SyS" kernel syscall aliases */
+ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
+ return SYMBOL_B;
+ if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10))
+ return SYMBOL_B;
+
+ return SYMBOL_A;
+}
+
+/* Allow matching against dot variants */
+int arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+ /* Skip over initial dot */
+ if (*namea == '.')
+ namea++;
+ if (*nameb == '.')
+ nameb++;
+
+ return strcmp(namea, nameb);
+}
+#endif
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+bool arch__prefers_symtab(void)
+{
+ return true;
+}
+
+#define PPC64LE_LEP_OFFSET 8
+
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+ struct probe_trace_event *tev, struct map *map)
+{
+ /*
+ * ppc64 ABIv2 local entry point is currently always 2 instructions
+ * (8 bytes) after the global entry point.
+ */
+ if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+ tev->point.address += PPC64LE_LEP_OFFSET;
+ tev->point.offset += PPC64LE_LEP_OFFSET;
+ }
+}
+#endif
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 5ce9802..c3ab760 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -3,6 +3,7 @@
perf-y += mem-memcpy.o
perf-y += futex-hash.o
perf-y += futex-wake.o
+perf-y += futex-wake-parallel.o
perf-y += futex-requeue.o
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 3c4dd44..70b2f71 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -33,6 +33,8 @@
extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake_parallel(int argc, const char **argv,
+ const char *prefix);
extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
#define BENCH_FORMAT_DEFAULT_STR "default"
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
new file mode 100644
index 0000000..6d8c9fa
--- /dev/null
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -0,0 +1,294 @@
+/*
+ * Copyright (C) 2015 Davidlohr Bueso.
+ *
+ * Block a bunch of threads and let parallel waker threads wakeup an
+ * equal amount of them. The program output reflects the avg latency
+ * for each individual thread to service its share of work. Ultimately
+ * it can be used to measure futex_wake() changes.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+struct thread_data {
+ pthread_t worker;
+ unsigned int nwoken;
+ struct timeval runtime;
+};
+
+static unsigned int nwakes = 1;
+
+/* all threads will block on the same futex -- hash bucket chaos ;) */
+static u_int32_t futex = 0;
+
+static pthread_t *blocked_worker;
+static bool done = false, silent = false, fshared = false;
+static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting;
+static int futex_flag = 0;
+
+static const struct option options[] = {
+ OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
+ OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"),
+ OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
+ OPT_END()
+};
+
+static const char * const bench_futex_wake_parallel_usage[] = {
+ "perf bench futex wake-parallel <options>",
+ NULL
+};
+
+static void *waking_workerfn(void *arg)
+{
+ struct thread_data *waker = (struct thread_data *) arg;
+ struct timeval start, end;
+
+ gettimeofday(&start, NULL);
+
+ waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
+ if (waker->nwoken != nwakes)
+ warnx("couldn't wakeup all tasks (%d/%d)",
+ waker->nwoken, nwakes);
+
+ gettimeofday(&end, NULL);
+ timersub(&end, &start, &waker->runtime);
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
+{
+ unsigned int i;
+
+ pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
+
+ /* create and block all threads */
+ for (i = 0; i < nwaking_threads; i++) {
+ /*
+ * Thread creation order will impact per-thread latency
+ * as it will affect the order to acquire the hb spinlock.
+ * For now let the scheduler decide.
+ */
+ if (pthread_create(&td[i].worker, &thread_attr,
+ waking_workerfn, (void *)&td[i]))
+ err(EXIT_FAILURE, "pthread_create");
+ }
+
+ for (i = 0; i < nwaking_threads; i++)
+ if (pthread_join(td[i].worker, NULL))
+ err(EXIT_FAILURE, "pthread_join");
+}
+
+static void *blocked_workerfn(void *arg __maybe_unused)
+{
+ pthread_mutex_lock(&thread_lock);
+ threads_starting--;
+ if (!threads_starting)
+ pthread_cond_signal(&thread_parent);
+ pthread_cond_wait(&thread_worker, &thread_lock);
+ pthread_mutex_unlock(&thread_lock);
+
+ while (1) { /* handle spurious wakeups */
+ if (futex_wait(&futex, 0, NULL, futex_flag) != EINTR)
+ break;
+ }
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+{
+ cpu_set_t cpu;
+ unsigned int i;
+
+ threads_starting = nblocked_threads;
+
+ /* create and block all threads */
+ for (i = 0; i < nblocked_threads; i++) {
+ CPU_ZERO(&cpu);
+ CPU_SET(i % ncpus, &cpu);
+
+ if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+ err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+ if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+ err(EXIT_FAILURE, "pthread_create");
+ }
+}
+
+static void print_run(struct thread_data *waking_worker, unsigned int run_num)
+{
+ unsigned int i, wakeup_avg;
+ double waketime_avg, waketime_stddev;
+ struct stats __waketime_stats, __wakeup_stats;
+
+ init_stats(&__wakeup_stats);
+ init_stats(&__waketime_stats);
+
+ for (i = 0; i < nwaking_threads; i++) {
+ update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
+ update_stats(&__wakeup_stats, waking_worker[i].nwoken);
+ }
+
+ waketime_avg = avg_stats(&__waketime_stats);
+ waketime_stddev = stddev_stats(&__waketime_stats);
+ wakeup_avg = avg_stats(&__wakeup_stats);
+
+ printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
+ "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
+ nblocked_threads, waketime_avg/1e3,
+ rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void print_summary(void)
+{
+ unsigned int wakeup_avg;
+ double waketime_avg, waketime_stddev;
+
+ waketime_avg = avg_stats(&waketime_stats);
+ waketime_stddev = stddev_stats(&waketime_stats);
+ wakeup_avg = avg_stats(&wakeup_stats);
+
+ printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
+ wakeup_avg,
+ nblocked_threads,
+ waketime_avg/1e3,
+ rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+
+static void do_run_stats(struct thread_data *waking_worker)
+{
+ unsigned int i;
+
+ for (i = 0; i < nwaking_threads; i++) {
+ update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
+ update_stats(&wakeup_stats, waking_worker[i].nwoken);
+ }
+
+}
+
+static void toggle_done(int sig __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *uc __maybe_unused)
+{
+ done = true;
+}
+
+int bench_futex_wake_parallel(int argc, const char **argv,
+ const char *prefix __maybe_unused)
+{
+ int ret = 0;
+ unsigned int i, j;
+ struct sigaction act;
+ pthread_attr_t thread_attr;
+ struct thread_data *waking_worker;
+
+ argc = parse_options(argc, argv, options,
+ bench_futex_wake_parallel_usage, 0);
+ if (argc) {
+ usage_with_options(bench_futex_wake_parallel_usage, options);
+ exit(EXIT_FAILURE);
+ }
+
+ sigfillset(&act.sa_mask);
+ act.sa_sigaction = toggle_done;
+ sigaction(SIGINT, &act, NULL);
+
+ ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ if (!nblocked_threads)
+ nblocked_threads = ncpus;
+
+ /* some sanity checks */
+ if (nwaking_threads > nblocked_threads || !nwaking_threads)
+ nwaking_threads = nblocked_threads;
+
+ if (nblocked_threads % nwaking_threads)
+ errx(EXIT_FAILURE, "Must be perfectly divisible");
+ /*
+ * Each thread will wakeup nwakes tasks in
+ * a single futex_wait call.
+ */
+ nwakes = nblocked_threads/nwaking_threads;
+
+ blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+ if (!blocked_worker)
+ err(EXIT_FAILURE, "calloc");
+
+ if (!fshared)
+ futex_flag = FUTEX_PRIVATE_FLAG;
+
+ printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
+ "futex %p), %d threads waking up %d at a time.\n\n",
+ getpid(), nblocked_threads, fshared ? "shared":"private",
+ &futex, nwaking_threads, nwakes);
+
+ init_stats(&wakeup_stats);
+ init_stats(&waketime_stats);
+
+ pthread_attr_init(&thread_attr);
+ pthread_mutex_init(&thread_lock, NULL);
+ pthread_cond_init(&thread_parent, NULL);
+ pthread_cond_init(&thread_worker, NULL);
+
+ for (j = 0; j < bench_repeat && !done; j++) {
+ waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+ if (!waking_worker)
+ err(EXIT_FAILURE, "calloc");
+
+ /* create, launch & block all threads */
+ block_threads(blocked_worker, thread_attr);
+
+ /* make sure all threads are already blocked */
+ pthread_mutex_lock(&thread_lock);
+ while (threads_starting)
+ pthread_cond_wait(&thread_parent, &thread_lock);
+ pthread_cond_broadcast(&thread_worker);
+ pthread_mutex_unlock(&thread_lock);
+
+ usleep(100000);
+
+ /* Ok, all threads are patiently blocked, start waking folks up */
+ wakeup_threads(waking_worker, thread_attr);
+
+ for (i = 0; i < nblocked_threads; i++) {
+ ret = pthread_join(blocked_worker[i], NULL);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_join");
+ }
+
+ do_run_stats(waking_worker);
+ if (!silent)
+ print_run(waking_worker, j);
+
+ free(waking_worker);
+ }
+
+ /* cleanup & report results */
+ pthread_cond_destroy(&thread_parent);
+ pthread_cond_destroy(&thread_worker);
+ pthread_mutex_destroy(&thread_lock);
+ pthread_attr_destroy(&thread_attr);
+
+ print_summary();
+
+ free(blocked_worker);
+ return ret;
+}
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 929f762..e5e41d3 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -60,7 +60,12 @@
pthread_cond_wait(&thread_worker, &thread_lock);
pthread_mutex_unlock(&thread_lock);
- futex_wait(&futex1, 0, NULL, futex_flag);
+ while (1) {
+ if (futex_wait(&futex1, 0, NULL, futex_flag) != EINTR)
+ break;
+ }
+
+ pthread_exit(NULL);
return NULL;
}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index ba5efa47..870b7e6 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -8,6 +8,7 @@
#include "../builtin.h"
#include "../util/util.h"
#include "../util/parse-options.h"
+#include "../util/cloexec.h"
#include "bench.h"
@@ -23,6 +24,7 @@
#include <pthread.h>
#include <sys/mman.h>
#include <sys/time.h>
+#include <sys/resource.h>
#include <sys/wait.h>
#include <sys/prctl.h>
#include <sys/types.h>
@@ -51,6 +53,9 @@
unsigned int loops_done;
u64 val;
u64 runtime_ns;
+ u64 system_time_ns;
+ u64 user_time_ns;
+ double speed_gbs;
pthread_mutex_t *process_lock;
};
@@ -1042,6 +1047,7 @@
u64 bytes_done;
long work_done;
u32 l;
+ struct rusage rusage;
bind_to_cpumask(td->bind_cpumask);
bind_to_memnode(td->bind_node);
@@ -1194,6 +1200,13 @@
timersub(&stop, &start0, &diff);
td->runtime_ns = diff.tv_sec * 1000000000ULL;
td->runtime_ns += diff.tv_usec * 1000ULL;
+ td->speed_gbs = bytes_done / (td->runtime_ns / 1e9) / 1e9;
+
+ getrusage(RUSAGE_THREAD, &rusage);
+ td->system_time_ns = rusage.ru_stime.tv_sec * 1000000000ULL;
+ td->system_time_ns += rusage.ru_stime.tv_usec * 1000ULL;
+ td->user_time_ns = rusage.ru_utime.tv_sec * 1000000000ULL;
+ td->user_time_ns += rusage.ru_utime.tv_usec * 1000ULL;
free_data(thread_data, g->p.bytes_thread);
@@ -1420,7 +1433,7 @@
double runtime_sec_min;
int wait_stat;
double bytes;
- int i, t;
+ int i, t, p;
if (init())
return -1;
@@ -1556,6 +1569,24 @@
print_res(name, bytes / runtime_sec_max / 1e9,
"GB/sec,", "total-speed", "GB/sec total speed");
+ if (g->p.show_details >= 2) {
+ char tname[32];
+ struct thread_data *td;
+ for (p = 0; p < g->p.nr_proc; p++) {
+ for (t = 0; t < g->p.nr_threads; t++) {
+ memset(tname, 0, 32);
+ td = g->threads + p*g->p.nr_threads + t;
+ snprintf(tname, 32, "process%d:thread%d", p, t);
+ print_res(tname, td->speed_gbs,
+ "GB/sec", "thread-speed", "GB/sec/thread speed");
+ print_res(tname, td->system_time_ns / 1e9,
+ "secs", "thread-system-time", "system CPU time/thread");
+ print_res(tname, td->user_time_ns / 1e9,
+ "secs", "thread-user-time", "user CPU time/thread");
+ }
+ }
+ }
+
free(pids);
deinit();
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 71bf745..b57a027 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -84,6 +84,7 @@
{
struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
struct addr_location al;
+ int ret = 0;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
@@ -92,15 +93,16 @@
}
if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
- return 0;
+ goto out_put;
if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
pr_warning("problem incrementing symbol count, "
"skipping event\n");
- return -1;
+ ret = -1;
}
-
- return 0;
+out_put:
+ addr_location__put(&al);
+ return ret;
}
static int hist_entry__tty_annotate(struct hist_entry *he,
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b9a56fa..b5314e4 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -58,6 +58,7 @@
static struct bench futex_benchmarks[] = {
{ "hash", "Benchmark for futex hash table", bench_futex_hash },
{ "wake", "Benchmark for futex wake calls", bench_futex_wake },
+ { "wake-parallel", "Benchmark for parallel futex wake calls", bench_futex_wake_parallel },
{ "requeue", "Benchmark for futex requeue calls", bench_futex_requeue },
{ "all", "Test all futex benchmarks", NULL },
{ NULL, NULL, NULL }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index feb420f..9fe93c8 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -69,6 +69,15 @@
session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
if (session == NULL)
return -1;
+
+ /*
+ * We take all buildids when the file contains AUX area tracing data
+ * because we do not decode the trace because it would take too long.
+ */
+ if (!perf_data_file__is_pipe(&file) &&
+ perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ with_hits = false;
+
/*
* in pipe-mode, the only way to get the buildids is to parse
* the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index df6307b..daaa7dc 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -328,6 +328,7 @@
{
struct addr_location al;
struct hists *hists = evsel__hists(evsel);
+ int ret = -1;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
@@ -338,7 +339,7 @@
if (hists__add_entry(hists, &al, sample->period,
sample->weight, sample->transaction)) {
pr_warning("problem incrementing symbol period, skipping event\n");
- return -1;
+ goto out_put;
}
/*
@@ -350,8 +351,10 @@
hists->stats.total_period += sample->period;
if (!al.filtered)
hists->stats.total_non_filtered_period += sample->period;
-
- return 0;
+ ret = 0;
+out_put:
+ addr_location__put(&al);
+ return ret;
}
static struct perf_tool tool = {
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40a33d7..52ec66b 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,6 +16,7 @@
#include "util/debug.h"
#include "util/build-id.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include "util/parse-options.h"
@@ -26,10 +27,12 @@
struct perf_session *session;
bool build_ids;
bool sched_stat;
+ bool have_auxtrace;
const char *input_name;
struct perf_data_file output;
u64 bytes_written;
struct list_head samples;
+ struct itrace_synth_opts itrace_synth_opts;
};
struct event_entry {
@@ -38,14 +41,11 @@
union perf_event event[0];
};
-static int perf_event__repipe_synth(struct perf_tool *tool,
- union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
{
- struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
ssize_t size;
- size = perf_data_file__write(&inject->output, event,
- event->header.size);
+ size = perf_data_file__write(&inject->output, buf, sz);
if (size < 0)
return -errno;
@@ -53,6 +53,15 @@
return 0;
}
+static int perf_event__repipe_synth(struct perf_tool *tool,
+ union perf_event *event)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+
+ return output_bytes(inject, event, event->header.size);
+}
+
static int perf_event__repipe_oe_synth(struct perf_tool *tool,
union perf_event *event,
struct ordered_events *oe __maybe_unused)
@@ -86,6 +95,79 @@
return perf_event__repipe_synth(tool, event);
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+ int ret;
+
+ inject->have_auxtrace = true;
+
+ if (!inject->output.is_pipe) {
+ off_t offset;
+
+ offset = lseek(inject->output.fd, 0, SEEK_CUR);
+ if (offset == -1)
+ return -errno;
+ ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
+ event, offset);
+ if (ret < 0)
+ return ret;
+ }
+
+ if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+ ret = output_bytes(inject, event, event->header.size);
+ if (ret < 0)
+ return ret;
+ ret = copy_bytes(inject, perf_data_file__fd(session->file),
+ event->auxtrace.size);
+ } else {
+ ret = output_bytes(inject, event,
+ event->header.size + event->auxtrace.size);
+ }
+ if (ret < 0)
+ return ret;
+
+ return event->auxtrace.size;
+}
+
+#else
+
+static s64
+perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+#endif
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -155,6 +237,32 @@
return err;
}
+static int perf_event__repipe_comm(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_comm(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
+static int perf_event__repipe_exit(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_exit(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_tracing_data(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session)
@@ -167,6 +275,18 @@
return err;
}
+static int perf_event__repipe_id_index(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ int err;
+
+ perf_event__repipe_synth(tool, event);
+ err = perf_event__process_id_index(tool, event, session);
+
+ return err;
+}
+
static int dso__read_build_id(struct dso *dso)
{
if (dso->has_build_id)
@@ -245,6 +365,7 @@
}
}
+ thread__put(thread);
repipe:
perf_event__repipe(tool, event, sample, machine);
return 0;
@@ -351,16 +472,20 @@
struct perf_session *session = inject->session;
struct perf_data_file *file_out = &inject->output;
int fd = perf_data_file__fd(file_out);
+ u64 output_data_offset;
signal(SIGINT, sig_handler);
- if (inject->build_ids || inject->sched_stat) {
+ if (inject->build_ids || inject->sched_stat ||
+ inject->itrace_synth_opts.set) {
inject->tool.mmap = perf_event__repipe_mmap;
inject->tool.mmap2 = perf_event__repipe_mmap2;
inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
+ output_data_offset = session->header.data_offset;
+
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
} else if (inject->sched_stat) {
@@ -379,17 +504,43 @@
else if (!strncmp(name, "sched:sched_stat_", 17))
evsel->handler = perf_inject__sched_stat;
}
+ } else if (inject->itrace_synth_opts.set) {
+ session->itrace_synth_opts = &inject->itrace_synth_opts;
+ inject->itrace_synth_opts.inject = true;
+ inject->tool.comm = perf_event__repipe_comm;
+ inject->tool.exit = perf_event__repipe_exit;
+ inject->tool.id_index = perf_event__repipe_id_index;
+ inject->tool.auxtrace_info = perf_event__process_auxtrace_info;
+ inject->tool.auxtrace = perf_event__process_auxtrace;
+ inject->tool.ordered_events = true;
+ inject->tool.ordering_requires_timestamps = true;
+ /* Allow space in the header for new attributes */
+ output_data_offset = 4096;
}
+ if (!inject->itrace_synth_opts.set)
+ auxtrace_index__free(&session->auxtrace_index);
+
if (!file_out->is_pipe)
- lseek(fd, session->header.data_offset, SEEK_SET);
+ lseek(fd, output_data_offset, SEEK_SET);
ret = perf_session__process_events(session);
if (!file_out->is_pipe) {
- if (inject->build_ids)
+ if (inject->build_ids) {
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
+ if (inject->have_auxtrace)
+ dsos__hit_all(session);
+ }
+ /*
+ * The AUX areas have been removed and replaced with
+ * synthesized hardware events, so clear the feature flag.
+ */
+ if (inject->itrace_synth_opts.set)
+ perf_header__clear_feat(&session->header,
+ HEADER_AUXTRACE);
+ session->header.data_offset = output_data_offset;
session->header.data_size = inject->bytes_written;
perf_session__write_header(session, session->evlist, fd, true);
}
@@ -408,11 +559,16 @@
.fork = perf_event__repipe,
.exit = perf_event__repipe,
.lost = perf_event__repipe,
+ .aux = perf_event__repipe,
+ .itrace_start = perf_event__repipe,
.read = perf_event__repipe_sample,
.throttle = perf_event__repipe,
.unthrottle = perf_event__repipe,
.attr = perf_event__repipe_attr,
.tracing_data = perf_event__repipe_op2_synth,
+ .auxtrace_info = perf_event__repipe_op2_synth,
+ .auxtrace = perf_event__repipe_auxtrace,
+ .auxtrace_error = perf_event__repipe_op2_synth,
.finished_round = perf_event__repipe_oe_synth,
.build_id = perf_event__repipe_op2_synth,
.id_index = perf_event__repipe_op2_synth,
@@ -444,6 +600,9 @@
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
"kallsyms pathname"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
+ NULL, "opts", "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const inject_usage[] = {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 1634186..254614b 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -10,6 +10,7 @@
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/callchain.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
@@ -21,14 +22,19 @@
#include <linux/rbtree.h>
#include <linux/string.h>
#include <locale.h>
+#include <regex.h>
static int kmem_slab;
static int kmem_page;
static long kmem_page_size;
+static enum {
+ KMEM_SLAB,
+ KMEM_PAGE,
+} kmem_default = KMEM_SLAB; /* for backward compatibility */
struct alloc_stat;
-typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
+typedef int (*sort_fn_t)(void *, void *);
static int alloc_flag;
static int caller_flag;
@@ -179,8 +185,8 @@
return ret;
}
-static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
-static int callsite_cmp(struct alloc_stat *, struct alloc_stat *);
+static int ptr_cmp(void *, void *);
+static int slab_callsite_cmp(void *, void *);
static struct alloc_stat *search_alloc_stat(unsigned long ptr,
unsigned long call_site,
@@ -221,7 +227,8 @@
s_alloc->pingpong++;
s_caller = search_alloc_stat(0, s_alloc->call_site,
- &root_caller_stat, callsite_cmp);
+ &root_caller_stat,
+ slab_callsite_cmp);
if (!s_caller)
return -1;
s_caller->pingpong++;
@@ -241,6 +248,8 @@
static unsigned long nr_page_nomatch;
static bool use_pfn;
+static bool live_page;
+static struct perf_session *kmem_session;
#define MAX_MIGRATE_TYPES 6
#define MAX_PAGE_ORDER 11
@@ -250,6 +259,7 @@
struct page_stat {
struct rb_node node;
u64 page;
+ u64 callsite;
int order;
unsigned gfp_flags;
unsigned migrate_type;
@@ -259,13 +269,158 @@
int nr_free;
};
-static struct rb_root page_tree;
+static struct rb_root page_live_tree;
static struct rb_root page_alloc_tree;
static struct rb_root page_alloc_sorted;
+static struct rb_root page_caller_tree;
+static struct rb_root page_caller_sorted;
-static struct page_stat *search_page(unsigned long page, bool create)
+struct alloc_func {
+ u64 start;
+ u64 end;
+ char *name;
+};
+
+static int nr_alloc_funcs;
+static struct alloc_func *alloc_func_list;
+
+static int funcmp(const void *a, const void *b)
{
- struct rb_node **node = &page_tree.rb_node;
+ const struct alloc_func *fa = a;
+ const struct alloc_func *fb = b;
+
+ if (fa->start > fb->start)
+ return 1;
+ else
+ return -1;
+}
+
+static int callcmp(const void *a, const void *b)
+{
+ const struct alloc_func *fa = a;
+ const struct alloc_func *fb = b;
+
+ if (fb->start <= fa->start && fa->end < fb->end)
+ return 0;
+
+ if (fa->start > fb->start)
+ return 1;
+ else
+ return -1;
+}
+
+static int build_alloc_func_list(void)
+{
+ int ret;
+ struct map *kernel_map;
+ struct symbol *sym;
+ struct rb_node *node;
+ struct alloc_func *func;
+ struct machine *machine = &kmem_session->machines.host;
+ regex_t alloc_func_regex;
+ const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+ ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
+ if (ret) {
+ char err[BUFSIZ];
+
+ regerror(ret, &alloc_func_regex, err, sizeof(err));
+ pr_err("Invalid regex: %s\n%s", pattern, err);
+ return -EINVAL;
+ }
+
+ kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
+ if (map__load(kernel_map, NULL) < 0) {
+ pr_err("cannot load kernel map\n");
+ return -ENOENT;
+ }
+
+ map__for_each_symbol(kernel_map, sym, node) {
+ if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+ continue;
+
+ func = realloc(alloc_func_list,
+ (nr_alloc_funcs + 1) * sizeof(*func));
+ if (func == NULL)
+ return -ENOMEM;
+
+ pr_debug("alloc func: %s\n", sym->name);
+ func[nr_alloc_funcs].start = sym->start;
+ func[nr_alloc_funcs].end = sym->end;
+ func[nr_alloc_funcs].name = sym->name;
+
+ alloc_func_list = func;
+ nr_alloc_funcs++;
+ }
+
+ qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+ regfree(&alloc_func_regex);
+ return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */
+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+ struct addr_location al;
+ struct machine *machine = &kmem_session->machines.host;
+ struct callchain_cursor_node *node;
+
+ if (alloc_func_list == NULL) {
+ if (build_alloc_func_list() < 0)
+ goto out;
+ }
+
+ al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+ sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+ callchain_cursor_commit(&callchain_cursor);
+ while (true) {
+ struct alloc_func key, *caller;
+ u64 addr;
+
+ node = callchain_cursor_current(&callchain_cursor);
+ if (node == NULL)
+ break;
+
+ key.start = key.end = node->ip;
+ caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+ sizeof(key), callcmp);
+ if (!caller) {
+ /* found */
+ if (node->map)
+ addr = map__unmap_ip(node->map, node->ip);
+ else
+ addr = node->ip;
+
+ return addr;
+ } else
+ pr_debug3("skipping alloc function: %s\n", caller->name);
+
+ callchain_cursor_advance(&callchain_cursor);
+ }
+
+out:
+ pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+ return sample->ip;
+}
+
+struct sort_dimension {
+ const char name[20];
+ sort_fn_t cmp;
+ struct list_head list;
+};
+
+static LIST_HEAD(page_alloc_sort_input);
+static LIST_HEAD(page_caller_sort_input);
+
+static struct page_stat *
+__page_stat__findnew_page(struct page_stat *pstat, bool create)
+{
+ struct rb_node **node = &page_live_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
@@ -275,7 +430,7 @@
parent = *node;
data = rb_entry(*node, struct page_stat, node);
- cmp = data->page - page;
+ cmp = data->page - pstat->page;
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
@@ -289,49 +444,48 @@
data = zalloc(sizeof(*data));
if (data != NULL) {
- data->page = page;
+ data->page = pstat->page;
+ data->order = pstat->order;
+ data->gfp_flags = pstat->gfp_flags;
+ data->migrate_type = pstat->migrate_type;
rb_link_node(&data->node, parent, node);
- rb_insert_color(&data->node, &page_tree);
+ rb_insert_color(&data->node, &page_live_tree);
}
return data;
}
-static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
+static struct page_stat *page_stat__find_page(struct page_stat *pstat)
{
- if (a->page > b->page)
- return -1;
- if (a->page < b->page)
- return 1;
- if (a->order > b->order)
- return -1;
- if (a->order < b->order)
- return 1;
- if (a->migrate_type > b->migrate_type)
- return -1;
- if (a->migrate_type < b->migrate_type)
- return 1;
- if (a->gfp_flags > b->gfp_flags)
- return -1;
- if (a->gfp_flags < b->gfp_flags)
- return 1;
- return 0;
+ return __page_stat__findnew_page(pstat, false);
}
-static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
+static struct page_stat *page_stat__findnew_page(struct page_stat *pstat)
+{
+ return __page_stat__findnew_page(pstat, true);
+}
+
+static struct page_stat *
+__page_stat__findnew_alloc(struct page_stat *pstat, bool create)
{
struct rb_node **node = &page_alloc_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
+ struct sort_dimension *sort;
while (*node) {
- s64 cmp;
+ int cmp = 0;
parent = *node;
data = rb_entry(*node, struct page_stat, node);
- cmp = page_stat_cmp(data, pstat);
+ list_for_each_entry(sort, &page_alloc_sort_input, list) {
+ cmp = sort->cmp(pstat, data);
+ if (cmp)
+ break;
+ }
+
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
@@ -357,6 +511,71 @@
return data;
}
+static struct page_stat *page_stat__find_alloc(struct page_stat *pstat)
+{
+ return __page_stat__findnew_alloc(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_alloc(struct page_stat *pstat)
+{
+ return __page_stat__findnew_alloc(pstat, true);
+}
+
+static struct page_stat *
+__page_stat__findnew_caller(struct page_stat *pstat, bool create)
+{
+ struct rb_node **node = &page_caller_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct page_stat *data;
+ struct sort_dimension *sort;
+
+ while (*node) {
+ int cmp = 0;
+
+ parent = *node;
+ data = rb_entry(*node, struct page_stat, node);
+
+ list_for_each_entry(sort, &page_caller_sort_input, list) {
+ cmp = sort->cmp(pstat, data);
+ if (cmp)
+ break;
+ }
+
+ if (cmp < 0)
+ node = &parent->rb_left;
+ else if (cmp > 0)
+ node = &parent->rb_right;
+ else
+ return data;
+ }
+
+ if (!create)
+ return NULL;
+
+ data = zalloc(sizeof(*data));
+ if (data != NULL) {
+ data->callsite = pstat->callsite;
+ data->order = pstat->order;
+ data->gfp_flags = pstat->gfp_flags;
+ data->migrate_type = pstat->migrate_type;
+
+ rb_link_node(&data->node, parent, node);
+ rb_insert_color(&data->node, &page_caller_tree);
+ }
+
+ return data;
+}
+
+static struct page_stat *page_stat__find_caller(struct page_stat *pstat)
+{
+ return __page_stat__findnew_caller(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_caller(struct page_stat *pstat)
+{
+ return __page_stat__findnew_caller(pstat, true);
+}
+
static bool valid_page(u64 pfn_or_page)
{
if (use_pfn && pfn_or_page == -1UL)
@@ -366,6 +585,176 @@
return true;
}
+struct gfp_flag {
+ unsigned int flags;
+ char *compact_str;
+ char *human_readable;
+};
+
+static struct gfp_flag *gfps;
+static int nr_gfps;
+
+static int gfpcmp(const void *a, const void *b)
+{
+ const struct gfp_flag *fa = a;
+ const struct gfp_flag *fb = b;
+
+ return fa->flags - fb->flags;
+}
+
+/* see include/trace/events/gfpflags.h */
+static const struct {
+ const char *original;
+ const char *compact;
+} gfp_compact_table[] = {
+ { "GFP_TRANSHUGE", "THP" },
+ { "GFP_HIGHUSER_MOVABLE", "HUM" },
+ { "GFP_HIGHUSER", "HU" },
+ { "GFP_USER", "U" },
+ { "GFP_TEMPORARY", "TMP" },
+ { "GFP_KERNEL", "K" },
+ { "GFP_NOFS", "NF" },
+ { "GFP_ATOMIC", "A" },
+ { "GFP_NOIO", "NI" },
+ { "GFP_HIGH", "H" },
+ { "GFP_WAIT", "W" },
+ { "GFP_IO", "I" },
+ { "GFP_COLD", "CO" },
+ { "GFP_NOWARN", "NWR" },
+ { "GFP_REPEAT", "R" },
+ { "GFP_NOFAIL", "NF" },
+ { "GFP_NORETRY", "NR" },
+ { "GFP_COMP", "C" },
+ { "GFP_ZERO", "Z" },
+ { "GFP_NOMEMALLOC", "NMA" },
+ { "GFP_MEMALLOC", "MA" },
+ { "GFP_HARDWALL", "HW" },
+ { "GFP_THISNODE", "TN" },
+ { "GFP_RECLAIMABLE", "RC" },
+ { "GFP_MOVABLE", "M" },
+ { "GFP_NOTRACK", "NT" },
+ { "GFP_NO_KSWAPD", "NK" },
+ { "GFP_OTHER_NODE", "ON" },
+ { "GFP_NOWAIT", "NW" },
+};
+
+static size_t max_gfp_len;
+
+static char *compact_gfp_flags(char *gfp_flags)
+{
+ char *orig_flags = strdup(gfp_flags);
+ char *new_flags = NULL;
+ char *str, *pos;
+ size_t len = 0;
+
+ if (orig_flags == NULL)
+ return NULL;
+
+ str = strtok_r(orig_flags, "|", &pos);
+ while (str) {
+ size_t i;
+ char *new;
+ const char *cpt;
+
+ for (i = 0; i < ARRAY_SIZE(gfp_compact_table); i++) {
+ if (strcmp(gfp_compact_table[i].original, str))
+ continue;
+
+ cpt = gfp_compact_table[i].compact;
+ new = realloc(new_flags, len + strlen(cpt) + 2);
+ if (new == NULL) {
+ free(new_flags);
+ return NULL;
+ }
+
+ new_flags = new;
+
+ if (!len) {
+ strcpy(new_flags, cpt);
+ } else {
+ strcat(new_flags, "|");
+ strcat(new_flags, cpt);
+ len++;
+ }
+
+ len += strlen(cpt);
+ }
+
+ str = strtok_r(NULL, "|", &pos);
+ }
+
+ if (max_gfp_len < len)
+ max_gfp_len = len;
+
+ free(orig_flags);
+ return new_flags;
+}
+
+static char *compact_gfp_string(unsigned long gfp_flags)
+{
+ struct gfp_flag key = {
+ .flags = gfp_flags,
+ };
+ struct gfp_flag *gfp;
+
+ gfp = bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+ if (gfp)
+ return gfp->compact_str;
+
+ return NULL;
+}
+
+static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
+ unsigned int gfp_flags)
+{
+ struct pevent_record record = {
+ .cpu = sample->cpu,
+ .data = sample->raw_data,
+ .size = sample->raw_size,
+ };
+ struct trace_seq seq;
+ char *str, *pos = NULL;
+
+ if (nr_gfps) {
+ struct gfp_flag key = {
+ .flags = gfp_flags,
+ };
+
+ if (bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp))
+ return 0;
+ }
+
+ trace_seq_init(&seq);
+ pevent_event_info(&seq, evsel->tp_format, &record);
+
+ str = strtok_r(seq.buffer, " ", &pos);
+ while (str) {
+ if (!strncmp(str, "gfp_flags=", 10)) {
+ struct gfp_flag *new;
+
+ new = realloc(gfps, (nr_gfps + 1) * sizeof(*gfps));
+ if (new == NULL)
+ return -ENOMEM;
+
+ gfps = new;
+ new += nr_gfps++;
+
+ new->flags = gfp_flags;
+ new->human_readable = strdup(str + 10);
+ new->compact_str = compact_gfp_flags(str + 10);
+ if (!new->human_readable || !new->compact_str)
+ return -ENOMEM;
+
+ qsort(gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+ }
+
+ str = strtok_r(NULL, " ", &pos);
+ }
+
+ trace_seq_destroy(&seq);
+ return 0;
+}
+
static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
struct perf_sample *sample)
{
@@ -375,6 +764,7 @@
unsigned int migrate_type = perf_evsel__intval(evsel, sample,
"migratetype");
u64 bytes = kmem_page_size << order;
+ u64 callsite;
struct page_stat *pstat;
struct page_stat this = {
.order = order,
@@ -397,20 +787,36 @@
return 0;
}
+ if (parse_gfp_flags(evsel, sample, gfp_flags) < 0)
+ return -1;
+
+ callsite = find_callsite(evsel, sample);
+
/*
* This is to find the current page (with correct gfp flags and
* migrate type) at free event.
*/
- pstat = search_page(page, true);
+ this.page = page;
+ pstat = page_stat__findnew_page(&this);
if (pstat == NULL)
return -ENOMEM;
- pstat->order = order;
- pstat->gfp_flags = gfp_flags;
- pstat->migrate_type = migrate_type;
+ pstat->nr_alloc++;
+ pstat->alloc_bytes += bytes;
+ pstat->callsite = callsite;
- this.page = page;
- pstat = search_page_alloc_stat(&this, true);
+ if (!live_page) {
+ pstat = page_stat__findnew_alloc(&this);
+ if (pstat == NULL)
+ return -ENOMEM;
+
+ pstat->nr_alloc++;
+ pstat->alloc_bytes += bytes;
+ pstat->callsite = callsite;
+ }
+
+ this.callsite = callsite;
+ pstat = page_stat__findnew_caller(&this);
if (pstat == NULL)
return -ENOMEM;
@@ -441,7 +847,8 @@
nr_page_frees++;
total_page_free_bytes += bytes;
- pstat = search_page(page, false);
+ this.page = page;
+ pstat = page_stat__find_page(&this);
if (pstat == NULL) {
pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
page, order);
@@ -452,20 +859,41 @@
return 0;
}
- this.page = page;
this.gfp_flags = pstat->gfp_flags;
this.migrate_type = pstat->migrate_type;
+ this.callsite = pstat->callsite;
- rb_erase(&pstat->node, &page_tree);
+ rb_erase(&pstat->node, &page_live_tree);
free(pstat);
- pstat = search_page_alloc_stat(&this, false);
+ if (live_page) {
+ order_stats[this.order][this.migrate_type]--;
+ } else {
+ pstat = page_stat__find_alloc(&this);
+ if (pstat == NULL)
+ return -ENOMEM;
+
+ pstat->nr_free++;
+ pstat->free_bytes += bytes;
+ }
+
+ pstat = page_stat__find_caller(&this);
if (pstat == NULL)
return -ENOENT;
pstat->nr_free++;
pstat->free_bytes += bytes;
+ if (live_page) {
+ pstat->nr_alloc--;
+ pstat->alloc_bytes -= bytes;
+
+ if (pstat->nr_alloc == 0) {
+ rb_erase(&pstat->node, &page_caller_tree);
+ free(pstat);
+ }
+ }
+
return 0;
}
@@ -478,6 +906,7 @@
struct perf_evsel *evsel,
struct machine *machine)
{
+ int err = 0;
struct thread *thread = machine__findnew_thread(machine, sample->pid,
sample->tid);
@@ -491,10 +920,12 @@
if (evsel->handler != NULL) {
tracepoint_handler f = evsel->handler;
- return f(evsel, sample);
+ err = f(evsel, sample);
}
- return 0;
+ thread__put(thread);
+
+ return err;
}
static struct perf_tool perf_kmem = {
@@ -576,41 +1007,111 @@
"UNKNOWN",
};
-static void __print_page_result(struct rb_root *root,
- struct perf_session *session __maybe_unused,
- int n_lines)
+static void __print_page_alloc_result(struct perf_session *session, int n_lines)
{
- struct rb_node *next = rb_first(root);
+ struct rb_node *next = rb_first(&page_alloc_sorted);
+ struct machine *machine = &session->machines.host;
const char *format;
+ int gfp_len = max(strlen("GFP flags"), max_gfp_len);
- printf("\n%.80s\n", graph_dotted_line);
- printf(" %-16s | Total alloc (KB) | Hits | Order | Mig.type | GFP flags\n",
- use_pfn ? "PFN" : "Page");
- printf("%.80s\n", graph_dotted_line);
+ printf("\n%.105s\n", graph_dotted_line);
+ printf(" %-16s | %5s alloc (KB) | Hits | Order | Mig.type | %-*s | Callsite\n",
+ use_pfn ? "PFN" : "Page", live_page ? "Live" : "Total",
+ gfp_len, "GFP flags");
+ printf("%.105s\n", graph_dotted_line);
if (use_pfn)
- format = " %16llu | %'16llu | %'9d | %5d | %8s | %08lx\n";
+ format = " %16llu | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
else
- format = " %016llx | %'16llu | %'9d | %5d | %8s | %08lx\n";
+ format = " %016llx | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
while (next && n_lines--) {
struct page_stat *data;
+ struct symbol *sym;
+ struct map *map;
+ char buf[32];
+ char *caller = buf;
data = rb_entry(next, struct page_stat, node);
+ sym = machine__find_kernel_function(machine, data->callsite,
+ &map, NULL);
+ if (sym && sym->name)
+ caller = sym->name;
+ else
+ scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
printf(format, (unsigned long long)data->page,
(unsigned long long)data->alloc_bytes / 1024,
data->nr_alloc, data->order,
migrate_type_str[data->migrate_type],
- (unsigned long)data->gfp_flags);
+ gfp_len, compact_gfp_string(data->gfp_flags), caller);
next = rb_next(next);
}
- if (n_lines == -1)
- printf(" ... | ... | ... | ... | ... | ... \n");
+ if (n_lines == -1) {
+ printf(" ... | ... | ... | ... | ... | %-*s | ...\n",
+ gfp_len, "...");
+ }
- printf("%.80s\n", graph_dotted_line);
+ printf("%.105s\n", graph_dotted_line);
+}
+
+static void __print_page_caller_result(struct perf_session *session, int n_lines)
+{
+ struct rb_node *next = rb_first(&page_caller_sorted);
+ struct machine *machine = &session->machines.host;
+ int gfp_len = max(strlen("GFP flags"), max_gfp_len);
+
+ printf("\n%.105s\n", graph_dotted_line);
+ printf(" %5s alloc (KB) | Hits | Order | Mig.type | %-*s | Callsite\n",
+ live_page ? "Live" : "Total", gfp_len, "GFP flags");
+ printf("%.105s\n", graph_dotted_line);
+
+ while (next && n_lines--) {
+ struct page_stat *data;
+ struct symbol *sym;
+ struct map *map;
+ char buf[32];
+ char *caller = buf;
+
+ data = rb_entry(next, struct page_stat, node);
+ sym = machine__find_kernel_function(machine, data->callsite,
+ &map, NULL);
+ if (sym && sym->name)
+ caller = sym->name;
+ else
+ scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
+
+ printf(" %'16llu | %'9d | %5d | %8s | %-*s | %s\n",
+ (unsigned long long)data->alloc_bytes / 1024,
+ data->nr_alloc, data->order,
+ migrate_type_str[data->migrate_type],
+ gfp_len, compact_gfp_string(data->gfp_flags), caller);
+
+ next = rb_next(next);
+ }
+
+ if (n_lines == -1) {
+ printf(" ... | ... | ... | ... | %-*s | ...\n",
+ gfp_len, "...");
+ }
+
+ printf("%.105s\n", graph_dotted_line);
+}
+
+static void print_gfp_flags(void)
+{
+ int i;
+
+ printf("#\n");
+ printf("# GFP flags\n");
+ printf("# ---------\n");
+ for (i = 0; i < nr_gfps; i++) {
+ printf("# %08x: %*s: %s\n", gfps[i].flags,
+ (int) max_gfp_len, gfps[i].compact_str,
+ gfps[i].human_readable);
+ }
}
static void print_slab_summary(void)
@@ -682,8 +1183,12 @@
static void print_page_result(struct perf_session *session)
{
+ if (caller_flag || alloc_flag)
+ print_gfp_flags();
+ if (caller_flag)
+ __print_page_caller_result(session, caller_lines);
if (alloc_flag)
- __print_page_result(&page_alloc_sorted, session, alloc_lines);
+ __print_page_alloc_result(session, alloc_lines);
print_page_summary();
}
@@ -695,14 +1200,10 @@
print_page_result(session);
}
-struct sort_dimension {
- const char name[20];
- sort_fn_t cmp;
- struct list_head list;
-};
-
-static LIST_HEAD(caller_sort);
-static LIST_HEAD(alloc_sort);
+static LIST_HEAD(slab_caller_sort);
+static LIST_HEAD(slab_alloc_sort);
+static LIST_HEAD(page_caller_sort);
+static LIST_HEAD(page_alloc_sort);
static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
struct list_head *sort_list)
@@ -751,10 +1252,12 @@
}
}
-static void sort_page_insert(struct rb_root *root, struct page_stat *data)
+static void sort_page_insert(struct rb_root *root, struct page_stat *data,
+ struct list_head *sort_list)
{
struct rb_node **new = &root->rb_node;
struct rb_node *parent = NULL;
+ struct sort_dimension *sort;
while (*new) {
struct page_stat *this;
@@ -763,8 +1266,11 @@
this = rb_entry(*new, struct page_stat, node);
parent = *new;
- /* TODO: support more sort key */
- cmp = data->alloc_bytes - this->alloc_bytes;
+ list_for_each_entry(sort, sort_list, list) {
+ cmp = sort->cmp(data, this);
+ if (cmp)
+ break;
+ }
if (cmp > 0)
new = &parent->rb_left;
@@ -776,7 +1282,8 @@
rb_insert_color(&data->node, root);
}
-static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
+static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted,
+ struct list_head *sort_list)
{
struct rb_node *node;
struct page_stat *data;
@@ -788,7 +1295,7 @@
rb_erase(node, root);
data = rb_entry(node, struct page_stat, node);
- sort_page_insert(root_sorted, data);
+ sort_page_insert(root_sorted, data, sort_list);
}
}
@@ -796,12 +1303,20 @@
{
if (kmem_slab) {
__sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
- &alloc_sort);
+ &slab_alloc_sort);
__sort_slab_result(&root_caller_stat, &root_caller_sorted,
- &caller_sort);
+ &slab_caller_sort);
}
if (kmem_page) {
- __sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+ if (live_page)
+ __sort_page_result(&page_live_tree, &page_alloc_sorted,
+ &page_alloc_sort);
+ else
+ __sort_page_result(&page_alloc_tree, &page_alloc_sorted,
+ &page_alloc_sort);
+
+ __sort_page_result(&page_caller_tree, &page_caller_sorted,
+ &page_caller_sort);
}
}
@@ -850,8 +1365,12 @@
return err;
}
-static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
+/* slab sort keys */
+static int ptr_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->ptr < r->ptr)
return -1;
else if (l->ptr > r->ptr)
@@ -864,8 +1383,11 @@
.cmp = ptr_cmp,
};
-static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int slab_callsite_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->call_site < r->call_site)
return -1;
else if (l->call_site > r->call_site)
@@ -875,11 +1397,14 @@
static struct sort_dimension callsite_sort_dimension = {
.name = "callsite",
- .cmp = callsite_cmp,
+ .cmp = slab_callsite_cmp,
};
-static int hit_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int hit_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->hit < r->hit)
return -1;
else if (l->hit > r->hit)
@@ -892,8 +1417,11 @@
.cmp = hit_cmp,
};
-static int bytes_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int bytes_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->bytes_alloc < r->bytes_alloc)
return -1;
else if (l->bytes_alloc > r->bytes_alloc)
@@ -906,9 +1434,11 @@
.cmp = bytes_cmp,
};
-static int frag_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int frag_cmp(void *a, void *b)
{
double x, y;
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
x = fragmentation(l->bytes_req, l->bytes_alloc);
y = fragmentation(r->bytes_req, r->bytes_alloc);
@@ -925,8 +1455,11 @@
.cmp = frag_cmp,
};
-static int pingpong_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int pingpong_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->pingpong < r->pingpong)
return -1;
else if (l->pingpong > r->pingpong)
@@ -939,7 +1472,135 @@
.cmp = pingpong_cmp,
};
-static struct sort_dimension *avail_sorts[] = {
+/* page sort keys */
+static int page_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->page < r->page)
+ return -1;
+ else if (l->page > r->page)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_sort_dimension = {
+ .name = "page",
+ .cmp = page_cmp,
+};
+
+static int page_callsite_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->callsite < r->callsite)
+ return -1;
+ else if (l->callsite > r->callsite)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_callsite_sort_dimension = {
+ .name = "callsite",
+ .cmp = page_callsite_cmp,
+};
+
+static int page_hit_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->nr_alloc < r->nr_alloc)
+ return -1;
+ else if (l->nr_alloc > r->nr_alloc)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_hit_sort_dimension = {
+ .name = "hit",
+ .cmp = page_hit_cmp,
+};
+
+static int page_bytes_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->alloc_bytes < r->alloc_bytes)
+ return -1;
+ else if (l->alloc_bytes > r->alloc_bytes)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_bytes_sort_dimension = {
+ .name = "bytes",
+ .cmp = page_bytes_cmp,
+};
+
+static int page_order_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->order < r->order)
+ return -1;
+ else if (l->order > r->order)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_order_sort_dimension = {
+ .name = "order",
+ .cmp = page_order_cmp,
+};
+
+static int migrate_type_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ /* for internal use to find free'd page */
+ if (l->migrate_type == -1U)
+ return 0;
+
+ if (l->migrate_type < r->migrate_type)
+ return -1;
+ else if (l->migrate_type > r->migrate_type)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension migrate_type_sort_dimension = {
+ .name = "migtype",
+ .cmp = migrate_type_cmp,
+};
+
+static int gfp_flags_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ /* for internal use to find free'd page */
+ if (l->gfp_flags == -1U)
+ return 0;
+
+ if (l->gfp_flags < r->gfp_flags)
+ return -1;
+ else if (l->gfp_flags > r->gfp_flags)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension gfp_flags_sort_dimension = {
+ .name = "gfp",
+ .cmp = gfp_flags_cmp,
+};
+
+static struct sort_dimension *slab_sorts[] = {
&ptr_sort_dimension,
&callsite_sort_dimension,
&hit_sort_dimension,
@@ -948,16 +1609,24 @@
&pingpong_sort_dimension,
};
-#define NUM_AVAIL_SORTS ((int)ARRAY_SIZE(avail_sorts))
+static struct sort_dimension *page_sorts[] = {
+ &page_sort_dimension,
+ &page_callsite_sort_dimension,
+ &page_hit_sort_dimension,
+ &page_bytes_sort_dimension,
+ &page_order_sort_dimension,
+ &migrate_type_sort_dimension,
+ &gfp_flags_sort_dimension,
+};
-static int sort_dimension__add(const char *tok, struct list_head *list)
+static int slab_sort_dimension__add(const char *tok, struct list_head *list)
{
struct sort_dimension *sort;
int i;
- for (i = 0; i < NUM_AVAIL_SORTS; i++) {
- if (!strcmp(avail_sorts[i]->name, tok)) {
- sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
+ for (i = 0; i < (int)ARRAY_SIZE(slab_sorts); i++) {
+ if (!strcmp(slab_sorts[i]->name, tok)) {
+ sort = memdup(slab_sorts[i], sizeof(*slab_sorts[i]));
if (!sort) {
pr_err("%s: memdup failed\n", __func__);
return -1;
@@ -970,7 +1639,27 @@
return -1;
}
-static int setup_sorting(struct list_head *sort_list, const char *arg)
+static int page_sort_dimension__add(const char *tok, struct list_head *list)
+{
+ struct sort_dimension *sort;
+ int i;
+
+ for (i = 0; i < (int)ARRAY_SIZE(page_sorts); i++) {
+ if (!strcmp(page_sorts[i]->name, tok)) {
+ sort = memdup(page_sorts[i], sizeof(*page_sorts[i]));
+ if (!sort) {
+ pr_err("%s: memdup failed\n", __func__);
+ return -1;
+ }
+ list_add_tail(&sort->list, list);
+ return 0;
+ }
+ }
+
+ return -1;
+}
+
+static int setup_slab_sorting(struct list_head *sort_list, const char *arg)
{
char *tok;
char *str = strdup(arg);
@@ -985,8 +1674,34 @@
tok = strsep(&pos, ",");
if (!tok)
break;
- if (sort_dimension__add(tok, sort_list) < 0) {
- error("Unknown --sort key: '%s'", tok);
+ if (slab_sort_dimension__add(tok, sort_list) < 0) {
+ error("Unknown slab --sort key: '%s'", tok);
+ free(str);
+ return -1;
+ }
+ }
+
+ free(str);
+ return 0;
+}
+
+static int setup_page_sorting(struct list_head *sort_list, const char *arg)
+{
+ char *tok;
+ char *str = strdup(arg);
+ char *pos = str;
+
+ if (!str) {
+ pr_err("%s: strdup failed\n", __func__);
+ return -1;
+ }
+
+ while (true) {
+ tok = strsep(&pos, ",");
+ if (!tok)
+ break;
+ if (page_sort_dimension__add(tok, sort_list) < 0) {
+ error("Unknown page --sort key: '%s'", tok);
free(str);
return -1;
}
@@ -1002,10 +1717,18 @@
if (!arg)
return -1;
- if (caller_flag > alloc_flag)
- return setup_sorting(&caller_sort, arg);
- else
- return setup_sorting(&alloc_sort, arg);
+ if (kmem_page > kmem_slab ||
+ (kmem_page == 0 && kmem_slab == 0 && kmem_default == KMEM_PAGE)) {
+ if (caller_flag > alloc_flag)
+ return setup_page_sorting(&page_caller_sort, arg);
+ else
+ return setup_page_sorting(&page_alloc_sort, arg);
+ } else {
+ if (caller_flag > alloc_flag)
+ return setup_slab_sorting(&slab_caller_sort, arg);
+ else
+ return setup_slab_sorting(&slab_alloc_sort, arg);
+ }
return 0;
}
@@ -1084,7 +1807,7 @@
if (kmem_slab)
rec_argc += ARRAY_SIZE(slab_events);
if (kmem_page)
- rec_argc += ARRAY_SIZE(page_events);
+ rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -1099,6 +1822,8 @@
rec_argv[i] = strdup(slab_events[j]);
}
if (kmem_page) {
+ rec_argv[i++] = strdup("-g");
+
for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
rec_argv[i] = strdup(page_events[j]);
}
@@ -1109,9 +1834,26 @@
return cmd_record(i, rec_argv, NULL);
}
+static int kmem_config(const char *var, const char *value, void *cb)
+{
+ if (!strcmp(var, "kmem.default")) {
+ if (!strcmp(value, "slab"))
+ kmem_default = KMEM_SLAB;
+ else if (!strcmp(value, "page"))
+ kmem_default = KMEM_PAGE;
+ else
+ pr_err("invalid default value ('slab' or 'page' required): %s\n",
+ value);
+ return 0;
+ }
+
+ return perf_default_config(var, value, cb);
+}
+
int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
{
- const char * const default_sort_order = "frag,hit,bytes";
+ const char * const default_slab_sort = "frag,hit,bytes";
+ const char * const default_page_sort = "bytes,hit";
struct perf_data_file file = {
.mode = PERF_DATA_MODE_READ,
};
@@ -1124,8 +1866,8 @@
OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
"show per-allocation statistics", parse_alloc_opt),
OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
- "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
- parse_sort_opt),
+ "sort by keys: ptr, callsite, bytes, hit, pingpong, frag, "
+ "page, order, migtype, gfp", parse_sort_opt),
OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
@@ -1133,6 +1875,7 @@
parse_slab_opt),
OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
parse_page_opt),
+ OPT_BOOLEAN(0, "live", &live_page, "Show live page stat"),
OPT_END()
};
const char *const kmem_subcommands[] = { "record", "stat", NULL };
@@ -1142,15 +1885,21 @@
};
struct perf_session *session;
int ret = -1;
+ const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n";
+ perf_config(kmem_config, NULL);
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
if (!argc)
usage_with_options(kmem_usage, kmem_options);
- if (kmem_slab == 0 && kmem_page == 0)
- kmem_slab = 1; /* for backward compatibility */
+ if (kmem_slab == 0 && kmem_page == 0) {
+ if (kmem_default == KMEM_SLAB)
+ kmem_slab = 1;
+ else
+ kmem_page = 1;
+ }
if (!strncmp(argv[0], "rec", 3)) {
symbol__init(NULL);
@@ -1159,19 +1908,30 @@
file.path = input_name;
- session = perf_session__new(&file, false, &perf_kmem);
+ kmem_session = session = perf_session__new(&file, false, &perf_kmem);
if (session == NULL)
return -1;
- if (kmem_page) {
- struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+ if (kmem_slab) {
+ if (!perf_evlist__find_tracepoint_by_name(session->evlist,
+ "kmem:kmalloc")) {
+ pr_err(errmsg, "slab", "slab");
+ return -1;
+ }
+ }
- if (evsel == NULL || evsel->tp_format == NULL) {
- pr_err("invalid event found.. aborting\n");
+ if (kmem_page) {
+ struct perf_evsel *evsel;
+
+ evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+ "kmem:mm_page_alloc");
+ if (evsel == NULL) {
+ pr_err(errmsg, "page", "page");
return -1;
}
kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+ symbol_conf.use_callchain = true;
}
symbol__init(&session->header.env);
@@ -1182,11 +1942,21 @@
if (cpu__setup_cpunode_map())
goto out_delete;
- if (list_empty(&caller_sort))
- setup_sorting(&caller_sort, default_sort_order);
- if (list_empty(&alloc_sort))
- setup_sorting(&alloc_sort, default_sort_order);
+ if (list_empty(&slab_caller_sort))
+ setup_slab_sorting(&slab_caller_sort, default_slab_sort);
+ if (list_empty(&slab_alloc_sort))
+ setup_slab_sorting(&slab_alloc_sort, default_slab_sort);
+ if (list_empty(&page_caller_sort))
+ setup_page_sorting(&page_caller_sort, default_page_sort);
+ if (list_empty(&page_alloc_sort))
+ setup_page_sorting(&page_alloc_sort, default_page_sort);
+ if (kmem_page) {
+ setup_page_sorting(&page_alloc_sort_input,
+ "page,order,migtype,gfp");
+ setup_page_sorting(&page_caller_sort_input,
+ "callsite,order,migtype,gfp");
+ }
ret = __cmd_kmem(session);
} else
usage_with_options(kmem_usage, kmem_options);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 1f9338f..15fecd3 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -651,6 +651,7 @@
struct perf_evsel *evsel,
struct machine *machine)
{
+ int err = 0;
struct thread *thread;
struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
tool);
@@ -666,9 +667,10 @@
}
if (!handle_kvm_event(kvm, thread, evsel, sample))
- return -1;
+ err = -1;
- return 0;
+ thread__put(thread);
+ return err;
}
static int cpu_isa_config(struct perf_kvm_stat *kvm)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index d49c2ab..de16aae 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -769,6 +769,7 @@
t = perf_session__findnew(session, st->tid);
pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
node = rb_next(node);
+ thread__put(t);
};
}
@@ -810,6 +811,7 @@
struct perf_evsel *evsel,
struct machine *machine)
{
+ int err = 0;
struct thread *thread = machine__findnew_thread(machine, sample->pid,
sample->tid);
@@ -821,10 +823,12 @@
if (evsel->handler != NULL) {
tracepoint_handler f = evsel->handler;
- return f(evsel, sample);
+ err = f(evsel, sample);
}
- return 0;
+ thread__put(thread);
+
+ return err;
}
static void sort_result(void)
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 675216e..da2ec06 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -74,7 +74,7 @@
}
if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
- return 0;
+ goto out_put;
if (al.map != NULL)
al.map->dso->hit = 1;
@@ -103,7 +103,8 @@
symbol_conf.field_sep,
al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
al.sym ? al.sym->name : "???");
-
+out_put:
+ addr_location__put(&al);
return 0;
}
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f7b1af6..1272559 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -44,25 +44,19 @@
#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
#define DEFAULT_FUNC_FILTER "!_*"
+#define DEFAULT_LIST_FILTER "*:*"
/* Session management structure */
static struct {
+ int command; /* Command short_name */
bool list_events;
- bool force_add;
- bool show_lines;
- bool show_vars;
- bool show_ext_vars;
- bool show_funcs;
- bool mod_events;
bool uprobes;
bool quiet;
bool target_used;
int nevents;
struct perf_probe_event events[MAX_PROBES];
- struct strlist *dellist;
struct line_range line_range;
char *target;
- int max_probe_points;
struct strfilter *filter;
} params;
@@ -93,6 +87,28 @@
return ret;
}
+static int params_add_filter(const char *str)
+{
+ const char *err = NULL;
+ int ret = 0;
+
+ pr_debug2("Add filter: %s\n", str);
+ if (!params.filter) {
+ params.filter = strfilter__new(str, &err);
+ if (!params.filter)
+ ret = err ? -EINVAL : -ENOMEM;
+ } else
+ ret = strfilter__or(params.filter, str, &err);
+
+ if (ret == -EINVAL) {
+ pr_err("Filter parse error at %td.\n", err - str + 1);
+ pr_err("Source: \"%s\"\n", str);
+ pr_err(" %*c\n", (int)(err - str + 1), '^');
+ }
+
+ return ret;
+}
+
static int set_target(const char *ptr)
{
int found = 0;
@@ -152,34 +168,11 @@
len += sprintf(&buf[len], "%s ", argv[i]);
}
- params.mod_events = true;
ret = parse_probe_event(buf);
free(buf);
return ret;
}
-static int opt_add_probe_event(const struct option *opt __maybe_unused,
- const char *str, int unset __maybe_unused)
-{
- if (str) {
- params.mod_events = true;
- return parse_probe_event(str);
- } else
- return 0;
-}
-
-static int opt_del_probe_event(const struct option *opt __maybe_unused,
- const char *str, int unset __maybe_unused)
-{
- if (str) {
- params.mod_events = true;
- if (!params.dellist)
- params.dellist = strlist__new(true, NULL);
- strlist__add(params.dellist, str);
- }
- return 0;
-}
-
static int opt_set_target(const struct option *opt, const char *str,
int unset __maybe_unused)
{
@@ -217,8 +210,10 @@
return ret;
}
+/* Command option callbacks */
+
#ifdef HAVE_DWARF_SUPPORT
-static int opt_show_lines(const struct option *opt __maybe_unused,
+static int opt_show_lines(const struct option *opt,
const char *str, int unset __maybe_unused)
{
int ret = 0;
@@ -226,19 +221,19 @@
if (!str)
return 0;
- if (params.show_lines) {
+ if (params.command == 'L') {
pr_warning("Warning: more than one --line options are"
" detected. Only the first one is valid.\n");
return 0;
}
- params.show_lines = true;
+ params.command = opt->short_name;
ret = parse_line_range_desc(str, ¶ms.line_range);
return ret;
}
-static int opt_show_vars(const struct option *opt __maybe_unused,
+static int opt_show_vars(const struct option *opt,
const char *str, int unset __maybe_unused)
{
struct perf_probe_event *pev = ¶ms.events[params.nevents];
@@ -252,29 +247,39 @@
pr_err(" Error: '--vars' doesn't accept arguments.\n");
return -EINVAL;
}
- params.show_vars = true;
+ params.command = opt->short_name;
return ret;
}
#endif
+static int opt_add_probe_event(const struct option *opt,
+ const char *str, int unset __maybe_unused)
+{
+ if (str) {
+ params.command = opt->short_name;
+ return parse_probe_event(str);
+ }
+
+ return 0;
+}
+
+static int opt_set_filter_with_command(const struct option *opt,
+ const char *str, int unset)
+{
+ if (!unset)
+ params.command = opt->short_name;
+
+ if (str)
+ return params_add_filter(str);
+
+ return 0;
+}
static int opt_set_filter(const struct option *opt __maybe_unused,
const char *str, int unset __maybe_unused)
{
- const char *err;
-
- if (str) {
- pr_debug2("Set filter: %s\n", str);
- if (params.filter)
- strfilter__delete(params.filter);
- params.filter = strfilter__new(str, &err);
- if (!params.filter) {
- pr_err("Filter parse error at %td.\n", err - str + 1);
- pr_err("Source: \"%s\"\n", str);
- pr_err(" %*c\n", (int)(err - str + 1), '^');
- return -EINVAL;
- }
- }
+ if (str)
+ return params_add_filter(str);
return 0;
}
@@ -290,8 +295,6 @@
for (i = 0; i < params.nevents; i++)
clear_perf_probe_event(params.events + i);
- if (params.dellist)
- strlist__delete(params.dellist);
line_range__clear(¶ms.line_range);
free(params.target);
if (params.filter)
@@ -316,22 +319,24 @@
"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
"perf probe [<options>] --del '[GROUP:]EVENT' ...",
- "perf probe --list",
+ "perf probe --list [GROUP:]EVENT ...",
#ifdef HAVE_DWARF_SUPPORT
"perf probe [<options>] --line 'LINEDESC'",
"perf probe [<options>] --vars 'PROBEPOINT'",
#endif
+ "perf probe [<options>] --funcs",
NULL
-};
+ };
struct option options[] = {
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show parsed arguments, etc)"),
OPT_BOOLEAN('q', "quiet", ¶ms.quiet,
"be quiet (do not show any mesages)"),
- OPT_BOOLEAN('l', "list", ¶ms.list_events,
- "list up current probe events"),
+ OPT_CALLBACK_DEFAULT('l', "list", NULL, "[GROUP:]EVENT",
+ "list up probe events",
+ opt_set_filter_with_command, DEFAULT_LIST_FILTER),
OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
- opt_del_probe_event),
+ opt_set_filter_with_command),
OPT_CALLBACK('a', "add", NULL,
#ifdef HAVE_DWARF_SUPPORT
"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
@@ -356,7 +361,7 @@
"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
#endif
opt_add_probe_event),
- OPT_BOOLEAN('f', "force", ¶ms.force_add, "forcibly add events"
+ OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
" with existing name"),
#ifdef HAVE_DWARF_SUPPORT
OPT_CALLBACK('L', "line", NULL,
@@ -365,8 +370,10 @@
OPT_CALLBACK('V', "vars", NULL,
"FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
"Show accessible variables on PROBEDEF", opt_show_vars),
- OPT_BOOLEAN('\0', "externs", ¶ms.show_ext_vars,
+ OPT_BOOLEAN('\0', "externs", &probe_conf.show_ext_vars,
"Show external variables too (with --vars only)"),
+ OPT_BOOLEAN('\0', "range", &probe_conf.show_location_range,
+ "Show variables location range in scope (with --vars only)"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_STRING('s', "source", &symbol_conf.source_prefix,
@@ -374,12 +381,15 @@
OPT_CALLBACK('m', "module", NULL, "modname|path",
"target module name (for online) or path (for offline)",
opt_set_target),
+ OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
+ "Don't search inlined functions"),
#endif
OPT__DRY_RUN(&probe_event_dry_run),
- OPT_INTEGER('\0', "max-probes", ¶ms.max_probe_points,
+ OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes,
"Set how many probe points can be found for a probe."),
- OPT_BOOLEAN('F', "funcs", ¶ms.show_funcs,
- "Show potential probe-able functions."),
+ OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+ "Show potential probe-able functions.",
+ opt_set_filter_with_command, DEFAULT_FUNC_FILTER),
OPT_CALLBACK('\0', "filter", NULL,
"[!]FILTER", "Set a filter (with --vars/funcs only)\n"
"\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
@@ -402,6 +412,7 @@
set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
#endif
+ set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE);
argc = parse_options(argc, argv, options, probe_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
@@ -410,11 +421,16 @@
pr_warning(" Error: '-' is not supported.\n");
usage_with_options(probe_usage, options);
}
+ if (params.command && params.command != 'a') {
+ pr_warning(" Error: another command except --add is set.\n");
+ usage_with_options(probe_usage, options);
+ }
ret = parse_probe_event_argv(argc, argv);
if (ret < 0) {
pr_err_with_code(" Error: Command Parse Error.", ret);
return ret;
}
+ params.command = 'a';
}
if (params.quiet) {
@@ -425,89 +441,70 @@
verbose = -1;
}
- if (params.max_probe_points == 0)
- params.max_probe_points = MAX_PROBES;
-
- if ((!params.nevents && !params.dellist && !params.list_events &&
- !params.show_lines && !params.show_funcs))
- usage_with_options(probe_usage, options);
+ if (probe_conf.max_probes == 0)
+ probe_conf.max_probes = MAX_PROBES;
/*
* Only consider the user's kernel image path if given.
*/
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
- if (params.list_events) {
+ switch (params.command) {
+ case 'l':
if (params.uprobes) {
pr_warning(" Error: Don't use --list with --exec.\n");
usage_with_options(probe_usage, options);
}
- ret = show_perf_probe_events();
+ ret = show_perf_probe_events(params.filter);
if (ret < 0)
pr_err_with_code(" Error: Failed to show event list.", ret);
return ret;
- }
- if (params.show_funcs) {
- if (!params.filter)
- params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
- NULL);
+ case 'F':
ret = show_available_funcs(params.target, params.filter,
params.uprobes);
- strfilter__delete(params.filter);
- params.filter = NULL;
if (ret < 0)
pr_err_with_code(" Error: Failed to show functions.", ret);
return ret;
- }
-
#ifdef HAVE_DWARF_SUPPORT
- if (params.show_lines) {
+ case 'L':
ret = show_line_range(¶ms.line_range, params.target,
params.uprobes);
if (ret < 0)
pr_err_with_code(" Error: Failed to show lines.", ret);
return ret;
- }
- if (params.show_vars) {
+ case 'V':
if (!params.filter)
params.filter = strfilter__new(DEFAULT_VAR_FILTER,
NULL);
ret = show_available_vars(params.events, params.nevents,
- params.max_probe_points,
- params.target,
- params.filter,
- params.show_ext_vars);
- strfilter__delete(params.filter);
- params.filter = NULL;
+ params.filter);
if (ret < 0)
pr_err_with_code(" Error: Failed to show vars.", ret);
return ret;
- }
#endif
-
- if (params.dellist) {
- ret = del_perf_probe_events(params.dellist);
+ case 'd':
+ ret = del_perf_probe_events(params.filter);
if (ret < 0) {
pr_err_with_code(" Error: Failed to delete events.", ret);
return ret;
}
- }
-
- if (params.nevents) {
+ break;
+ case 'a':
/* Ensure the last given target is used */
if (params.target && !params.target_used) {
pr_warning(" Error: -x/-m must follow the probe definitions.\n");
usage_with_options(probe_usage, options);
}
- ret = add_perf_probe_events(params.events, params.nevents,
- params.max_probe_points,
- params.force_add);
+ ret = add_perf_probe_events(params.events, params.nevents);
if (ret < 0) {
pr_err_with_code(" Error: Failed to add events.", ret);
return ret;
}
+ break;
+ default:
+ usage_with_options(probe_usage, options);
}
return 0;
}
@@ -522,5 +519,5 @@
cleanup_params();
}
- return ret;
+ return ret < 0 ? ret : 0;
}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c3efdfb..5dfe913 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,6 +27,7 @@
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <unistd.h>
#include <sched.h>
@@ -38,6 +39,7 @@
struct record_opts opts;
u64 bytes_written;
struct perf_data_file file;
+ struct auxtrace_record *itr;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
@@ -110,9 +112,12 @@
return rc;
}
-static volatile int done = 0;
+static volatile int done;
static volatile int signr = -1;
-static volatile int child_finished = 0;
+static volatile int child_finished;
+static volatile int auxtrace_snapshot_enabled;
+static volatile int auxtrace_snapshot_err;
+static volatile int auxtrace_record__snapshot_started;
static void sig_handler(int sig)
{
@@ -133,6 +138,133 @@
raise(signr);
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int record__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2)
+{
+ struct record *rec = container_of(tool, struct record, tool);
+ struct perf_data_file *file = &rec->file;
+ size_t padding;
+ u8 pad[8] = {0};
+
+ if (!perf_data_file__is_pipe(file)) {
+ off_t file_offset;
+ int fd = perf_data_file__fd(file);
+ int err;
+
+ file_offset = lseek(fd, 0, SEEK_CUR);
+ if (file_offset == -1)
+ return -1;
+ err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
+ event, file_offset);
+ if (err)
+ return err;
+ }
+
+ /* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
+ padding = (len1 + len2) & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ record__write(rec, event, event->header.size);
+ record__write(rec, data1, len1);
+ if (len2)
+ record__write(rec, data2, len2);
+ record__write(rec, &pad, padding);
+
+ return 0;
+}
+
+static int record__auxtrace_mmap_read(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+ record__process_auxtrace);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
+static int record__auxtrace_mmap_read_snapshot(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+ record__process_auxtrace,
+ rec->opts.auxtrace_snapshot_size);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
+static int record__auxtrace_read_snapshot_all(struct record *rec)
+{
+ int i;
+ int rc = 0;
+
+ for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm =
+ &rec->evlist->mmap[i].auxtrace_mmap;
+
+ if (!mm->base)
+ continue;
+
+ if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
+ }
+out:
+ return rc;
+}
+
+static void record__read_auxtrace_snapshot(struct record *rec)
+{
+ pr_debug("Recording AUX area tracing snapshot\n");
+ if (record__auxtrace_read_snapshot_all(rec) < 0) {
+ auxtrace_snapshot_err = -1;
+ } else {
+ auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
+ if (!auxtrace_snapshot_err)
+ auxtrace_snapshot_enabled = 1;
+ }
+}
+
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+ struct auxtrace_mmap *mm __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
+{
+ return 0;
+}
+
+#endif
+
static int record__open(struct record *rec)
{
char msg[512];
@@ -169,13 +301,16 @@
goto out;
}
- if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+ if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+ opts->auxtrace_mmap_pages,
+ opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
"/proc/sys/kernel/perf_event_mlock_kb,\n"
"or try again with a smaller value of -m/--mmap_pages.\n"
- "(current value: %u)\n", opts->mmap_pages);
+ "(current value: %u,%u)\n",
+ opts->mmap_pages, opts->auxtrace_mmap_pages);
rc = -errno;
} else {
pr_err("failed to mmap with %d (%s)\n", errno,
@@ -270,12 +405,20 @@
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+
if (rec->evlist->mmap[i].base) {
if (record__mmap_read(rec, i) != 0) {
rc = -1;
goto out;
}
}
+
+ if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
+ record__auxtrace_mmap_read(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
}
/*
@@ -305,6 +448,9 @@
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
+ if (!rec->opts.full_auxtrace)
+ perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}
static volatile int workload_exec_errno;
@@ -323,6 +469,8 @@
child_finished = 1;
}
+static void snapshot_sig_handler(int sig);
+
static int __cmd_record(struct record *rec, int argc, const char **argv)
{
int err;
@@ -343,6 +491,10 @@
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
+ if (rec->opts.auxtrace_snapshot_mode)
+ signal(SIGUSR2, snapshot_sig_handler);
+ else
+ signal(SIGUSR2, SIG_IGN);
session = perf_session__new(file, false, tool);
if (session == NULL) {
@@ -421,6 +573,13 @@
}
}
+ if (rec->opts.full_auxtrace) {
+ err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+ session, process_synthesized_event);
+ if (err)
+ goto out_delete_session;
+ }
+
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine);
if (err < 0)
@@ -475,14 +634,27 @@
perf_evlist__enable(rec->evlist);
}
+ auxtrace_snapshot_enabled = 1;
for (;;) {
int hits = rec->samples;
if (record__mmap_read_all(rec) < 0) {
+ auxtrace_snapshot_enabled = 0;
err = -1;
goto out_child;
}
+ if (auxtrace_record__snapshot_started) {
+ auxtrace_record__snapshot_started = 0;
+ if (!auxtrace_snapshot_err)
+ record__read_auxtrace_snapshot(rec);
+ if (auxtrace_snapshot_err) {
+ pr_err("AUX area tracing snapshot failed\n");
+ err = -1;
+ goto out_child;
+ }
+ }
+
if (hits == rec->samples) {
if (done || draining)
break;
@@ -505,10 +677,12 @@
* disable events in this case.
*/
if (done && !disabled && !target__none(&opts->target)) {
+ auxtrace_snapshot_enabled = 0;
perf_evlist__disable(rec->evlist);
disabled = true;
}
}
+ auxtrace_snapshot_enabled = 0;
if (forks && workload_exec_errno) {
char msg[STRERR_BUFSIZE];
@@ -545,15 +719,23 @@
if (!err && !file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
- if (!rec->no_buildid)
+ if (!rec->no_buildid) {
process_buildids(rec);
+ /*
+ * We take all buildids when the file contains
+ * AUX area tracing data because we do not decode the
+ * trace because it would take too long.
+ */
+ if (rec->opts.full_auxtrace)
+ dsos__hit_all(rec->session);
+ }
perf_session__write_header(rec->session, rec->evlist, fd, true);
}
if (!err && !quiet) {
char samples[128];
- if (rec->samples)
+ if (rec->samples && !rec->opts.full_auxtrace)
scnprintf(samples, sizeof(samples),
" (%" PRIu64 " samples)", rec->samples);
else
@@ -795,6 +977,49 @@
return -1;
}
+static int record__parse_mmap_pages(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *s, *p;
+ unsigned int mmap_pages;
+ int ret;
+
+ if (!str)
+ return -EINVAL;
+
+ s = strdup(str);
+ if (!s)
+ return -ENOMEM;
+
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ if (*s) {
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+ if (ret)
+ goto out_free;
+ opts->mmap_pages = mmap_pages;
+ }
+
+ if (!p) {
+ ret = 0;
+ goto out_free;
+ }
+
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+ if (ret)
+ goto out_free;
+
+ opts->auxtrace_mmap_pages = mmap_pages;
+
+out_free:
+ free(s);
+ return ret;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -875,9 +1100,9 @@
&record.opts.no_inherit_set,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
- OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
- "number of mmap data pages",
- perf_evlist__parse_mmap_pages),
+ OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
+ "number of mmap data pages and AUX area tracing mmap pages",
+ record__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
@@ -929,6 +1154,8 @@
OPT_CALLBACK('k', "clockid", &record.opts,
"clockid", "clockid to use for events, see clock_gettime()",
parse_clockid),
+ OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
+ "opts", "AUX area tracing Snapshot Mode", ""),
OPT_END()
};
@@ -936,7 +1163,7 @@
int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
- int err = -ENOMEM;
+ int err;
struct record *rec = &record;
char errbuf[BUFSIZ];
@@ -957,6 +1184,19 @@
usage_with_options(record_usage, record_options);
}
+ if (!rec->itr) {
+ rec->itr = auxtrace_record__init(rec->evlist, &err);
+ if (err)
+ return err;
+ }
+
+ err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+ rec->opts.auxtrace_snapshot_opts);
+ if (err)
+ return err;
+
+ err = -ENOMEM;
+
symbol__init(NULL);
if (symbol_conf.kptr_restrict)
@@ -1002,6 +1242,10 @@
if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
+ err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
+ if (err)
+ goto out_symbol_exit;
+
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out_symbol_exit;
@@ -1011,5 +1255,15 @@
out_symbol_exit:
perf_evlist__delete(rec->evlist);
symbol__exit();
+ auxtrace_record__free(rec->itr);
return err;
}
+
+static void snapshot_sig_handler(int sig __maybe_unused)
+{
+ if (!auxtrace_snapshot_enabled)
+ return;
+ auxtrace_snapshot_enabled = 0;
+ auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
+ auxtrace_record__snapshot_started = 1;
+}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b63aeda..92fca21 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,6 +36,8 @@
#include "util/data.h"
#include "arch/common.h"
+#include "util/auxtrace.h"
+
#include <dlfcn.h>
#include <linux/bitmap.h>
@@ -140,7 +142,7 @@
.hide_unresolved = rep->hide_unresolved,
.add_entry_cb = hist_iter__report_callback,
};
- int ret;
+ int ret = 0;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_debug("problem processing %d event, skipping it.\n",
@@ -149,10 +151,10 @@
}
if (rep->hide_unresolved && al.sym == NULL)
- return 0;
+ goto out_put;
if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
- return 0;
+ goto out_put;
if (sort__mode == SORT_MODE__BRANCH)
iter.ops = &hist_iter_branch;
@@ -170,7 +172,8 @@
rep);
if (ret < 0)
pr_debug("problem adding hist entry, skipping event\n");
-
+out_put:
+ addr_location__put(&al);
return ret;
}
@@ -330,15 +333,14 @@
}
if (sort_order == NULL &&
- parent_pattern == default_parent_pattern) {
+ parent_pattern == default_parent_pattern)
fprintf(stdout, "#\n# (%s)\n#\n", help);
- if (rep->show_threads) {
- bool style = !strcmp(rep->pretty_printing_style, "raw");
- perf_read_values_display(stdout, &rep->show_threads_values,
- style);
- perf_read_values_destroy(&rep->show_threads_values);
- }
+ if (rep->show_threads) {
+ bool style = !strcmp(rep->pretty_printing_style, "raw");
+ perf_read_values_display(stdout, &rep->show_threads_values,
+ style);
+ perf_read_values_destroy(&rep->show_threads_values);
}
return 0;
@@ -585,6 +587,7 @@
int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
struct stat st;
bool has_br_stack = false;
int branch_mode = -1;
@@ -607,6 +610,9 @@
.attr = perf_event__process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -717,6 +723,9 @@
"Don't show entries under that percent", parse_percent_limit),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
"how to display percentage of filtered entries", parse_filter_percentage),
+ OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
struct perf_data_file file = {
@@ -761,6 +770,8 @@
report.queue_size);
}
+ session->itrace_synth_opts = &itrace_synth_opts;
+
report.session = session;
has_br_stack = perf_header__has_feat(&session->header,
@@ -803,8 +814,8 @@
goto error;
}
- /* Force tty output for header output. */
- if (report.header || report.header_only)
+ /* Force tty output for header output and per-thread stat. */
+ if (report.header || report.header_only || report.show_threads)
use_browser = 0;
if (strcmp(input_name, "-") != 0)
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5275bab..79273ec 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -770,7 +770,7 @@
if (child == NULL || parent == NULL) {
pr_debug("thread does not exist on fork event: child %p, parent %p\n",
child, parent);
- return 0;
+ goto out_put;
}
if (verbose) {
@@ -781,6 +781,9 @@
register_pid(sched, parent->tid, thread__comm_str(parent));
register_pid(sched, child->tid, thread__comm_str(child));
+out_put:
+ thread__put(child);
+ thread__put(parent);
return 0;
}
@@ -957,7 +960,7 @@
struct work_atoms *out_events, *in_events;
struct thread *sched_out, *sched_in;
u64 timestamp0, timestamp = sample->time;
- int cpu = sample->cpu;
+ int cpu = sample->cpu, err = -1;
s64 delta;
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
@@ -976,15 +979,17 @@
sched_out = machine__findnew_thread(machine, -1, prev_pid);
sched_in = machine__findnew_thread(machine, -1, next_pid);
+ if (sched_out == NULL || sched_in == NULL)
+ goto out_put;
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
if (!out_events) {
if (thread_atoms_insert(sched, sched_out))
- return -1;
+ goto out_put;
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
if (!out_events) {
pr_err("out-event: Internal tree error");
- return -1;
+ goto out_put;
}
}
if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
@@ -993,22 +998,25 @@
in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
if (!in_events) {
if (thread_atoms_insert(sched, sched_in))
- return -1;
+ goto out_put;
in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
if (!in_events) {
pr_err("in-event: Internal tree error");
- return -1;
+ goto out_put;
}
/*
* Take came in we have not heard about yet,
* add in an initial atom in runnable state:
*/
if (add_sched_out_event(in_events, 'R', timestamp))
- return -1;
+ goto out_put;
}
add_sched_in_event(in_events, timestamp);
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(sched_out);
+ thread__put(sched_in);
+ return err;
}
static int latency_runtime_event(struct perf_sched *sched,
@@ -1021,23 +1029,29 @@
struct thread *thread = machine__findnew_thread(machine, -1, pid);
struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
u64 timestamp = sample->time;
- int cpu = sample->cpu;
+ int cpu = sample->cpu, err = -1;
+
+ if (thread == NULL)
+ return -1;
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
if (!atoms) {
if (thread_atoms_insert(sched, thread))
- return -1;
+ goto out_put;
atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
if (!atoms) {
pr_err("in-event: Internal tree error");
- return -1;
+ goto out_put;
}
if (add_sched_out_event(atoms, 'R', timestamp))
- return -1;
+ goto out_put;
}
add_runtime_event(atoms, runtime, timestamp);
- return 0;
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static int latency_wakeup_event(struct perf_sched *sched,
@@ -1050,19 +1064,22 @@
struct work_atom *atom;
struct thread *wakee;
u64 timestamp = sample->time;
+ int err = -1;
wakee = machine__findnew_thread(machine, -1, pid);
+ if (wakee == NULL)
+ return -1;
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, wakee))
- return -1;
+ goto out_put;
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
pr_err("wakeup-event: Internal tree error");
- return -1;
+ goto out_put;
}
if (add_sched_out_event(atoms, 'S', timestamp))
- return -1;
+ goto out_put;
}
BUG_ON(list_empty(&atoms->work_list));
@@ -1081,17 +1098,21 @@
* skip in this case.
*/
if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
- return 0;
+ goto out_ok;
sched->nr_timestamps++;
if (atom->sched_out_time > timestamp) {
sched->nr_unordered_timestamps++;
- return 0;
+ goto out_ok;
}
atom->state = THREAD_WAIT_CPU;
atom->wake_up_time = timestamp;
- return 0;
+out_ok:
+ err = 0;
+out_put:
+ thread__put(wakee);
+ return err;
}
static int latency_migrate_task_event(struct perf_sched *sched,
@@ -1104,6 +1125,7 @@
struct work_atoms *atoms;
struct work_atom *atom;
struct thread *migrant;
+ int err = -1;
/*
* Only need to worry about migration when profiling one CPU.
@@ -1112,18 +1134,20 @@
return 0;
migrant = machine__findnew_thread(machine, -1, pid);
+ if (migrant == NULL)
+ return -1;
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, migrant))
- return -1;
+ goto out_put;
register_pid(sched, migrant->tid, thread__comm_str(migrant));
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
if (!atoms) {
pr_err("migration-event: Internal tree error");
- return -1;
+ goto out_put;
}
if (add_sched_out_event(atoms, 'R', timestamp))
- return -1;
+ goto out_put;
}
BUG_ON(list_empty(&atoms->work_list));
@@ -1135,8 +1159,10 @@
if (atom->sched_out_time > timestamp)
sched->nr_unordered_timestamps++;
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(migrant);
+ return err;
}
static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
@@ -1330,8 +1356,10 @@
}
sched_in = machine__findnew_thread(machine, -1, next_pid);
+ if (sched_in == NULL)
+ return -1;
- sched->curr_thread[this_cpu] = sched_in;
+ sched->curr_thread[this_cpu] = thread__get(sched_in);
printf(" ");
@@ -1381,6 +1409,8 @@
printf("\n");
}
+ thread__put(sched_in);
+
return 0;
}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 58f10b8..24809787 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -16,6 +16,7 @@
#include "util/evsel.h"
#include "util/sort.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <linux/bitmap.h>
static char const *script_name;
@@ -26,6 +27,7 @@
static bool no_callchain;
static bool latency_format;
static bool system_wide;
+static bool print_flags;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -146,9 +148,10 @@
#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x)
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
- u64 sample_type, const char *sample_msg,
- enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field,
+ bool allow_user_set)
{
struct perf_event_attr *attr = &evsel->attr;
int type = attr->type;
@@ -158,6 +161,8 @@
return 0;
if (output[type].user_set) {
+ if (allow_user_set)
+ return 0;
evname = perf_evsel__name(evsel);
pr_err("Samples for '%s' event do not have %s attribute set. "
"Cannot print '%s' field.\n",
@@ -175,10 +180,22 @@
return 0;
}
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field)
+{
+ return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+ false);
+}
+
static int perf_evsel__check_attr(struct perf_evsel *evsel,
struct perf_session *session)
{
struct perf_event_attr *attr = &evsel->attr;
+ bool allow_user_set;
+
+ allow_user_set = perf_header__has_feat(&session->header,
+ HEADER_AUXTRACE);
if (PRINT_FIELD(TRACE) &&
!perf_session__has_traces(session, "record -R"))
@@ -191,8 +208,8 @@
}
if (PRINT_FIELD(ADDR) &&
- perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
- PERF_OUTPUT_ADDR))
+ perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+ PERF_OUTPUT_ADDR, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
@@ -229,8 +246,8 @@
return -EINVAL;
if (PRINT_FIELD(CPU) &&
- perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
- PERF_OUTPUT_CPU))
+ perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+ PERF_OUTPUT_CPU, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(PERIOD) &&
@@ -445,6 +462,25 @@
printf("\n");
}
+static void print_sample_flags(u32 flags)
+{
+ const char *chars = PERF_IP_FLAG_CHARS;
+ const int n = strlen(PERF_IP_FLAG_CHARS);
+ char str[33];
+ int i, pos = 0;
+
+ for (i = 0; i < n; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = chars[i];
+ }
+ for (; i < 32; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = '?';
+ }
+ str[pos] = 0;
+ printf(" %-4s ", str);
+}
+
static void process_event(union perf_event *event, struct perf_sample *sample,
struct perf_evsel *evsel, struct addr_location *al)
{
@@ -464,6 +500,9 @@
printf("%s: ", evname ? evname : "[unknown]");
}
+ if (print_flags)
+ print_sample_flags(sample->flags);
+
if (is_bts_event(attr)) {
print_sample_bts(event, sample, evsel, thread, al);
return;
@@ -568,13 +607,14 @@
}
if (al.filtered)
- return 0;
+ goto out_put;
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
- return 0;
+ goto out_put;
scripting_ops->process_event(event, sample, evsel, &al);
-
+out_put:
+ addr_location__put(&al);
return 0;
}
@@ -642,8 +682,8 @@
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
ret = 0;
-
out:
+ thread__put(thread);
return ret;
}
@@ -674,6 +714,7 @@
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
+ thread__put(thread);
return 0;
}
@@ -682,6 +723,7 @@
struct perf_sample *sample,
struct machine *machine)
{
+ int err = 0;
struct thread *thread;
struct perf_script *script = container_of(tool, struct perf_script, tool);
struct perf_session *session = script->session;
@@ -703,9 +745,10 @@
perf_event__fprintf(event, stdout);
if (perf_event__process_exit(tool, event, sample, machine) < 0)
- return -1;
+ err = -1;
- return 0;
+ thread__put(thread);
+ return err;
}
static int process_mmap_event(struct perf_tool *tool,
@@ -735,7 +778,7 @@
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
-
+ thread__put(thread);
return 0;
}
@@ -766,7 +809,7 @@
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
-
+ thread__put(thread);
return 0;
}
@@ -999,12 +1042,15 @@
}
}
- tok = strtok(tok, ",");
- while (tok) {
+ for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
for (i = 0; i < imax; ++i) {
if (strcmp(tok, all_output_options[i].str) == 0)
break;
}
+ if (i == imax && strcmp(tok, "flags") == 0) {
+ print_flags = true;
+ continue;
+ }
if (i == imax) {
fprintf(stderr, "Invalid field requested.\n");
rc = -EINVAL;
@@ -1032,8 +1078,6 @@
}
output[type].fields |= all_output_options[i].field;
}
-
- tok = strtok(NULL, ",");
}
if (type >= 0) {
@@ -1497,6 +1541,7 @@
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = { .set = false, };
char *script_path = NULL;
const char **__argv;
int i, j, err = 0;
@@ -1511,6 +1556,10 @@
.attr = process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
+ .auxtrace_error = perf_event__process_auxtrace_error,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -1549,7 +1598,7 @@
"comma separated output fields prepend with 'type:'. "
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period", parse_output_fields),
+ "addr,symoff,period,flags", parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -1570,6 +1619,9 @@
OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
"Show the mmap events"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
@@ -1765,6 +1817,8 @@
script.session = session;
+ session->itrace_synth_opts = &itrace_synth_opts;
+
if (cpu_list) {
err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
if (err < 0)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f7b8218..fd577f7 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -247,21 +247,50 @@
return -1;
}
+enum {
+ CTX_BIT_USER = 1 << 0,
+ CTX_BIT_KERNEL = 1 << 1,
+ CTX_BIT_HV = 1 << 2,
+ CTX_BIT_HOST = 1 << 3,
+ CTX_BIT_IDLE = 1 << 4,
+ CTX_BIT_MAX = 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
-static struct stats runtime_branches_stats[MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
static struct stats walltime_nsecs_stats;
-static struct stats runtime_transaction_stats[MAX_NR_CPUS];
-static struct stats runtime_elision_stats[MAX_NR_CPUS];
+static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+
+static int evsel_context(struct perf_evsel *evsel)
+{
+ int ctx = 0;
+
+ if (evsel->attr.exclude_kernel)
+ ctx |= CTX_BIT_KERNEL;
+ if (evsel->attr.exclude_user)
+ ctx |= CTX_BIT_USER;
+ if (evsel->attr.exclude_hv)
+ ctx |= CTX_BIT_HV;
+ if (evsel->attr.exclude_host)
+ ctx |= CTX_BIT_HOST;
+ if (evsel->attr.exclude_idle)
+ ctx |= CTX_BIT_IDLE;
+
+ return ctx;
+}
static void perf_stat__reset_stats(struct perf_evlist *evlist)
{
@@ -356,37 +385,39 @@
static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
int cpu)
{
+ int ctx = evsel_context(counter);
+
if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
update_stats(&runtime_nsecs_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[cpu], count[0]);
+ update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
else if (transaction_run &&
perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
- update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]);
+ update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
else if (transaction_run &&
perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
- update_stats(&runtime_transaction_stats[cpu], count[0]);
+ update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
else if (transaction_run &&
perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
- update_stats(&runtime_elision_stats[cpu], count[0]);
+ update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
- update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]);
+ update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
- update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]);
+ update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[cpu], count[0]);
+ update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_stats(&runtime_cacherefs_stats[cpu], count[0]);
+ update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_stats(&runtime_l1_dcache_stats[cpu], count[0]);
+ update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_stats(&runtime_l1_icache_stats[cpu], count[0]);
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_stats(&runtime_ll_cache_stats[cpu], count[0]);
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_stats(&runtime_dtlb_cache_stats[cpu], count[0]);
+ update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_stats(&runtime_itlb_cache_stats[cpu], count[0]);
+ update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
}
static void zero_per_pkg(struct perf_evsel *counter)
@@ -908,8 +939,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_cycles_stats[cpu]);
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -927,8 +959,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_cycles_stats[cpu]);
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -946,8 +979,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_branches_stats[cpu]);
+ total = avg_stats(&runtime_branches_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -965,8 +999,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+ total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -984,8 +1019,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_l1_icache_stats[cpu]);
+ total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -1003,8 +1039,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
+ total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -1022,8 +1059,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_itlb_cache_stats[cpu]);
+ total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -1041,8 +1079,9 @@
{
double total, ratio = 0.0;
const char *color;
+ int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_ll_cache_stats[cpu]);
+ total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
if (total)
ratio = avg / total * 100.0;
@@ -1060,6 +1099,7 @@
double sc = evsel->scale;
const char *fmt;
int cpu = cpu_map__id_to_cpu(id);
+ int ctx = evsel_context(evsel);
if (csv_output) {
fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
@@ -1091,15 +1131,15 @@
return;
if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = avg_stats(&runtime_cycles_stats[cpu]);
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total) {
ratio = avg / total;
fprintf(output, " # %5.2f insns per cycle ", ratio);
} else {
fprintf(output, " ");
}
- total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
- total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
+ total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
+ total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
if (total && avg) {
ratio = total / avg;
@@ -1110,46 +1150,46 @@
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[cpu].n != 0) {
+ runtime_branches_stats[ctx][cpu].n != 0) {
print_branch_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_l1_dcache_stats[cpu].n != 0) {
+ runtime_l1_dcache_stats[ctx][cpu].n != 0) {
print_l1_dcache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_l1_icache_stats[cpu].n != 0) {
+ runtime_l1_icache_stats[ctx][cpu].n != 0) {
print_l1_icache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_dtlb_cache_stats[cpu].n != 0) {
+ runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
print_dtlb_cache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_itlb_cache_stats[cpu].n != 0) {
+ runtime_itlb_cache_stats[ctx][cpu].n != 0) {
print_itlb_cache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_ll_cache_stats[cpu].n != 0) {
+ runtime_ll_cache_stats[ctx][cpu].n != 0) {
print_ll_cache_misses(cpu, evsel, avg);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[cpu].n != 0) {
- total = avg_stats(&runtime_cacherefs_stats[cpu]);
+ runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
if (total)
ratio = avg * 100 / total;
@@ -1171,15 +1211,15 @@
}
} else if (transaction_run &&
perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
- total = avg_stats(&runtime_cycles_stats[cpu]);
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total)
fprintf(output,
" # %5.2f%% transactional cycles ",
100.0 * (avg / total));
} else if (transaction_run &&
perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
- total = avg_stats(&runtime_cycles_stats[cpu]);
- total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (total2 < avg)
total2 = avg;
if (total)
@@ -1189,8 +1229,8 @@
} else if (transaction_run &&
perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
avg > 0 &&
- runtime_cycles_in_tx_stats[cpu].n != 0) {
- total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+ runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (total)
ratio = total / avg;
@@ -1199,8 +1239,8 @@
} else if (transaction_run &&
perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
avg > 0 &&
- runtime_cycles_in_tx_stats[cpu].n != 0) {
- total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+ runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (total)
ratio = total / avg;
@@ -1541,7 +1581,7 @@
unsigned i;
for (i = 0; i < len; i++) {
- if (parse_events(evsel_list, attrs[i]))
+ if (parse_events(evsel_list, attrs[i], NULL))
return -1;
}
return 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e50fe11..30e5962 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -61,13 +61,13 @@
tasks_only,
with_backtrace,
topology;
+ bool force;
/* IO related settings */
- u64 io_events;
bool io_only,
skip_eagain;
+ u64 io_events;
u64 min_time,
merge_dist;
- bool force;
};
struct per_pidcomm;
@@ -523,7 +523,7 @@
* Discard all.
*/
zfree(&p);
- goto exit;
+ goto exit_put;
}
continue;
}
@@ -538,7 +538,8 @@
else
fprintf(f, "..... %016" PRIx64 "\n", ip);
}
-
+exit_put:
+ addr_location__put(&al);
exit:
fclose(f);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6a4d5d4..a193517 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -793,7 +793,7 @@
pthread_mutex_unlock(&hists->lock);
}
- return;
+ addr_location__put(&al);
}
static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e122970..a05490d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,7 +16,6 @@
#include <libaudit.h>
#include <stdlib.h>
-#include <sys/eventfd.h>
#include <sys/mman.h>
#include <linux/futex.h>
@@ -41,6 +40,34 @@
# define EFD_SEMAPHORE 1
#endif
+#ifndef EFD_NONBLOCK
+# define EFD_NONBLOCK 00004000
+#endif
+
+#ifndef EFD_CLOEXEC
+# define EFD_CLOEXEC 02000000
+#endif
+
+#ifndef O_CLOEXEC
+# define O_CLOEXEC 02000000
+#endif
+
+#ifndef SOCK_DCCP
+# define SOCK_DCCP 6
+#endif
+
+#ifndef SOCK_CLOEXEC
+# define SOCK_CLOEXEC 02000000
+#endif
+
+#ifndef SOCK_NONBLOCK
+# define SOCK_NONBLOCK 00004000
+#endif
+
+#ifndef MSG_CMSG_CLOEXEC
+# define MSG_CMSG_CLOEXEC 0x40000000
+#endif
+
struct tp_field {
int offset;
union {
@@ -1712,7 +1739,7 @@
void *args;
size_t printed = 0;
struct thread *thread;
- int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+ int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
@@ -1725,14 +1752,14 @@
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
- return -1;
+ goto out_put;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
if (ttrace->entry_str == NULL) {
ttrace->entry_str = malloc(1024);
if (!ttrace->entry_str)
- return -1;
+ goto out_put;
}
if (!trace->summary_only)
@@ -1757,8 +1784,10 @@
thread__put(trace->current);
trace->current = thread__get(thread);
}
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
@@ -1768,7 +1797,7 @@
long ret;
u64 duration = 0;
struct thread *thread;
- int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+ int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
@@ -1781,7 +1810,7 @@
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
- return -1;
+ goto out_put;
if (trace->summary)
thread__update_stats(ttrace, id, sample);
@@ -1835,8 +1864,10 @@
fputc('\n', trace->output);
out:
ttrace->entry_pending = false;
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
@@ -1863,6 +1894,7 @@
ttrace->runtime_ms += runtime_ms;
trace->runtime_ms += runtime_ms;
+ thread__put(thread);
return 0;
out_dump:
@@ -1872,6 +1904,7 @@
(pid_t)perf_evsel__intval(evsel, sample, "pid"),
runtime,
perf_evsel__intval(evsel, sample, "vruntime"));
+ thread__put(thread);
return 0;
}
@@ -1924,11 +1957,12 @@
struct addr_location al;
char map_type = 'd';
struct thread_trace *ttrace;
+ int err = -1;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
- return -1;
+ goto out_put;
if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
ttrace->pfmaj++;
@@ -1936,7 +1970,7 @@
ttrace->pfmin++;
if (trace->summary_only)
- return 0;
+ goto out;
thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
sample->ip, &al);
@@ -1967,8 +2001,11 @@
print_location(trace->output, sample, &al, true, false);
fprintf(trace->output, " (%c%c)\n", map_type, al.level);
-
- return 0;
+out:
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static bool skip_sample(struct trace *trace, struct perf_sample *sample)
@@ -2666,16 +2703,15 @@
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
- OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
- "list of events to trace"),
+ OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
"trace events on existing process id"),
OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
"trace events on existing thread id"),
- OPT_CALLBACK(0, "filter-pids", &trace, "float",
- "show only events with duration > N.M ms", trace__set_filter_pids),
+ OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
+ "pids to filter (by the kernel)", trace__set_filter_pids),
OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
@@ -2712,11 +2748,10 @@
signal(SIGFPE, sighandler_dump_stack);
trace.evlist = perf_evlist__new();
- if (trace.evlist == NULL)
- return -ENOMEM;
if (trace.evlist == NULL) {
pr_err("Not enough memory to run!\n");
+ err = -ENOMEM;
goto out;
}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 59a98c6..1b957a1 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -268,6 +268,10 @@
endif # libelf support
endif # NO_LIBELF
+ifdef NO_DWARF
+ NO_LIBDW_DWARF_UNWIND := 1
+endif
+
ifndef NO_LIBELF
CFLAGS += -DHAVE_LIBELF_SUPPORT
EXTLIBS += -lelf
@@ -610,6 +614,11 @@
endif
endif
+ifndef NO_AUXTRACE
+ $(call detected,CONFIG_AUXTRACE)
+ CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+endif
+
# Among the variables below, these:
# perfexecdir
# template_dir
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 6ef6816..83a25ce 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,11 +6,9 @@
#include <sys/syscall.h>
#include <linux/types.h>
#include <linux/perf_event.h>
+#include <asm/barrier.h>
#if defined(__i386__)
-#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
#define CPUINFO_PROC {"model name"}
#ifndef __NR_perf_event_open
@@ -25,9 +23,6 @@
#endif
#if defined(__x86_64__)
-#define mb() asm volatile("mfence" ::: "memory")
-#define wmb() asm volatile("sfence" ::: "memory")
-#define rmb() asm volatile("lfence" ::: "memory")
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
#define CPUINFO_PROC {"model name"}
#ifndef __NR_perf_event_open
@@ -43,129 +38,63 @@
#ifdef __powerpc__
#include "../../arch/powerpc/include/uapi/asm/unistd.h"
-#define mb() asm volatile ("sync" ::: "memory")
-#define wmb() asm volatile ("sync" ::: "memory")
-#define rmb() asm volatile ("sync" ::: "memory")
#define CPUINFO_PROC {"cpu"}
#endif
#ifdef __s390__
-#define mb() asm volatile("bcr 15,0" ::: "memory")
-#define wmb() asm volatile("bcr 15,0" ::: "memory")
-#define rmb() asm volatile("bcr 15,0" ::: "memory")
#define CPUINFO_PROC {"vendor_id"}
#endif
#ifdef __sh__
-#if defined(__SH4A__) || defined(__SH5__)
-# define mb() asm volatile("synco" ::: "memory")
-# define wmb() asm volatile("synco" ::: "memory")
-# define rmb() asm volatile("synco" ::: "memory")
-#else
-# define mb() asm volatile("" ::: "memory")
-# define wmb() asm volatile("" ::: "memory")
-# define rmb() asm volatile("" ::: "memory")
-#endif
#define CPUINFO_PROC {"cpu type"}
#endif
#ifdef __hppa__
-#define mb() asm volatile("" ::: "memory")
-#define wmb() asm volatile("" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"cpu"}
#endif
#ifdef __sparc__
-#ifdef __LP64__
-#define mb() asm volatile("ba,pt %%xcc, 1f\n" \
- "membar #StoreLoad\n" \
- "1:\n":::"memory")
-#else
-#define mb() asm volatile("":::"memory")
-#endif
-#define wmb() asm volatile("":::"memory")
-#define rmb() asm volatile("":::"memory")
#define CPUINFO_PROC {"cpu"}
#endif
#ifdef __alpha__
-#define mb() asm volatile("mb" ::: "memory")
-#define wmb() asm volatile("wmb" ::: "memory")
-#define rmb() asm volatile("mb" ::: "memory")
#define CPUINFO_PROC {"cpu model"}
#endif
#ifdef __ia64__
-#define mb() asm volatile ("mf" ::: "memory")
-#define wmb() asm volatile ("mf" ::: "memory")
-#define rmb() asm volatile ("mf" ::: "memory")
#define cpu_relax() asm volatile ("hint @pause" ::: "memory")
#define CPUINFO_PROC {"model name"}
#endif
#ifdef __arm__
-/*
- * Use the __kuser_memory_barrier helper in the CPU helper page. See
- * arch/arm/kernel/entry-armv.S in the kernel source for details.
- */
-#define mb() ((void(*)(void))0xffff0fa0)()
-#define wmb() ((void(*)(void))0xffff0fa0)()
-#define rmb() ((void(*)(void))0xffff0fa0)()
#define CPUINFO_PROC {"model name", "Processor"}
#endif
#ifdef __aarch64__
-#define mb() asm volatile("dmb ish" ::: "memory")
-#define wmb() asm volatile("dmb ishst" ::: "memory")
-#define rmb() asm volatile("dmb ishld" ::: "memory")
#define cpu_relax() asm volatile("yield" ::: "memory")
#endif
#ifdef __mips__
-#define mb() asm volatile( \
- ".set mips2\n\t" \
- "sync\n\t" \
- ".set mips0" \
- : /* no output */ \
- : /* no input */ \
- : "memory")
-#define wmb() mb()
-#define rmb() mb()
#define CPUINFO_PROC {"cpu model"}
#endif
#ifdef __arc__
-#define mb() asm volatile("" ::: "memory")
-#define wmb() asm volatile("" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"Processor"}
#endif
#ifdef __metag__
-#define mb() asm volatile("" ::: "memory")
-#define wmb() asm volatile("" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"CPU"}
#endif
#ifdef __xtensa__
-#define mb() asm volatile("memw" ::: "memory")
-#define wmb() asm volatile("memw" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"core ID"}
#endif
#ifdef __tile__
-#define mb() asm volatile ("mf" ::: "memory")
-#define wmb() asm volatile ("mf" ::: "memory")
-#define rmb() asm volatile ("mf" ::: "memory")
#define cpu_relax() asm volatile ("mfspr zero, PASS" ::: "memory")
#define CPUINFO_PROC {"model name"}
#endif
-#define barrier() asm volatile ("" ::: "memory")
-
#ifndef cpu_relax
#define cpu_relax() barrier()
#endif
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e14bb63..aa79fb8 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,12 +54,17 @@
bool period;
bool sample_intr_regs;
bool running_time;
+ bool full_auxtrace;
+ bool auxtrace_snapshot_mode;
unsigned int freq;
unsigned int mmap_pages;
+ unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 default_interval;
u64 user_interval;
+ size_t auxtrace_snapshot_size;
+ const char *auxtrace_snapshot_opts;
bool sample_transaction;
unsigned initial_delay;
bool use_clockid;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4f40981..f42af98 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -219,7 +219,7 @@
wait(&status);
if (WIFEXITED(status)) {
- err = WEXITSTATUS(status);
+ err = (signed char)WEXITSTATUS(status);
pr_debug("test child finished with %d\n", err);
} else if (WIFSIGNALED(status)) {
err = -1;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f671ec3..e2a432b 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -248,6 +248,7 @@
struct perf_sample sample;
struct thread *thread;
u8 cpumode;
+ int ret;
if (perf_evlist__parse_sample(evlist, event, &sample)) {
pr_debug("perf_evlist__parse_sample failed\n");
@@ -262,7 +263,9 @@
cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- return read_object_code(sample.ip, READLEN, cpumode, thread, state);
+ ret = read_object_code(sample.ip, READLEN, cpumode, thread, state);
+ thread__put(thread);
+ return ret;
}
static int process_event(struct machine *machine, struct perf_evlist *evlist,
@@ -457,13 +460,13 @@
thread = machine__findnew_thread(machine, pid, pid);
if (!thread) {
pr_debug("machine__findnew_thread failed\n");
- goto out_err;
+ goto out_put;
}
cpus = cpu_map__new(NULL);
if (!cpus) {
pr_debug("cpu_map__new failed\n");
- goto out_err;
+ goto out_put;
}
while (1) {
@@ -472,7 +475,7 @@
evlist = perf_evlist__new();
if (!evlist) {
pr_debug("perf_evlist__new failed\n");
- goto out_err;
+ goto out_put;
}
perf_evlist__set_maps(evlist, cpus, threads);
@@ -482,10 +485,10 @@
else
str = "cycles";
pr_debug("Parsing event '%s'\n", str);
- ret = parse_events(evlist, str);
+ ret = parse_events(evlist, str, NULL);
if (ret < 0) {
pr_debug("parse_events failed\n");
- goto out_err;
+ goto out_put;
}
perf_evlist__config(evlist, &opts);
@@ -506,7 +509,7 @@
continue;
}
pr_debug("perf_evlist__open failed\n");
- goto out_err;
+ goto out_put;
}
break;
}
@@ -514,7 +517,7 @@
ret = perf_evlist__mmap(evlist, UINT_MAX, false);
if (ret < 0) {
pr_debug("perf_evlist__mmap failed\n");
- goto out_err;
+ goto out_put;
}
perf_evlist__enable(evlist);
@@ -525,7 +528,7 @@
ret = process_events(machine, evlist, &state);
if (ret < 0)
- goto out_err;
+ goto out_put;
if (!have_vmlinux && !have_kcore && !try_kcore)
err = TEST_CODE_READING_NO_KERNEL_OBJ;
@@ -535,7 +538,10 @@
err = TEST_CODE_READING_NO_ACCESS;
else
err = TEST_CODE_READING_OK;
+out_put:
+ thread__put(thread);
out_err:
+
if (evlist) {
perf_evlist__delete(evlist);
} else {
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 0bf06be..9b748e1 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -170,6 +170,7 @@
}
err = krava_1(thread);
+ thread__put(thread);
out:
machine__delete_threads(machine);
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index b8d8341..3fa7159 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -23,7 +23,7 @@
for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
__perf_evsel__hw_cache_type_op_res_name(type, op, i,
name, sizeof(name));
- err = parse_events(evlist, name);
+ err = parse_events(evlist, name, NULL);
if (err)
ret = err;
}
@@ -71,7 +71,7 @@
return -ENOMEM;
for (i = 0; i < nr_names; ++i) {
- err = parse_events(evlist, names[i]);
+ err = parse_events(evlist, names[i], NULL);
if (err) {
pr_debug("failed to parse event '%s', err %d\n",
names[i], err);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index a62c091..456f884 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -96,6 +96,7 @@
goto out;
thread__set_comm(thread, fake_threads[i].comm, 0);
+ thread__put(thread);
}
for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 1861996..620f626 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -105,8 +105,10 @@
goto out;
if (hist_entry_iter__add(&iter, &al, evsel, &sample,
- PERF_MAX_STACK_DEPTH, NULL) < 0)
+ PERF_MAX_STACK_DEPTH, NULL) < 0) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
@@ -695,7 +697,7 @@
TEST_ASSERT_VAL("No memory", evlist);
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 59e53db..82e1ee5 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -82,8 +82,10 @@
goto out;
if (hist_entry_iter__add(&iter, &al, evsel, &sample,
- PERF_MAX_STACK_DEPTH, NULL) < 0)
+ PERF_MAX_STACK_DEPTH, NULL) < 0) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
@@ -108,10 +110,10 @@
TEST_ASSERT_VAL("No memory", evlist);
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
- err = parse_events(evlist, "task-clock");
+ err = parse_events(evlist, "task-clock", NULL);
if (err)
goto out;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 278ba834..8c102b0 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -91,8 +91,10 @@
he = __hists__add_entry(hists, &al, NULL,
NULL, NULL, 1, 1, 0, true);
- if (he == NULL)
+ if (he == NULL) {
+ addr_location__put(&al);
goto out;
+ }
fake_common_samples[k].thread = al.thread;
fake_common_samples[k].map = al.map;
@@ -115,8 +117,10 @@
he = __hists__add_entry(hists, &al, NULL,
NULL, NULL, 1, 1, 0, true);
- if (he == NULL)
+ if (he == NULL) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i][k].thread = al.thread;
fake_samples[i][k].map = al.map;
@@ -282,10 +286,10 @@
if (evlist == NULL)
return -ENOMEM;
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
- err = parse_events(evlist, "task-clock");
+ err = parse_events(evlist, "task-clock", NULL);
if (err)
goto out;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index b52c9fa..fd7ec4f 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -71,8 +71,10 @@
goto out;
if (hist_entry_iter__add(&iter, &al, evsel, &sample,
- PERF_MAX_STACK_DEPTH, NULL) < 0)
+ PERF_MAX_STACK_DEPTH, NULL) < 0) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
@@ -590,7 +592,7 @@
TEST_ASSERT_VAL("No memory", evlist);
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 7a5ab7b..5b171d1 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -78,8 +78,8 @@
perf_evlist__set_maps(evlist, cpus, threads);
- CHECK__(parse_events(evlist, "dummy:u"));
- CHECK__(parse_events(evlist, "cycles:u"));
+ CHECK__(parse_events(evlist, "dummy:u", NULL));
+ CHECK__(parse_events(evlist, "cycles:u", NULL));
perf_evlist__config(evlist, &opts);
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index bff8532..65280d2 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -32,6 +32,7 @@
make_no_libnuma := NO_LIBNUMA=1
make_no_libaudit := NO_LIBAUDIT=1
make_no_libbionic := NO_LIBBIONIC=1
+make_no_auxtrace := NO_AUXTRACE=1
make_tags := tags
make_cscope := cscope
make_help := help
@@ -52,7 +53,7 @@
make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
-make_minimal += NO_LIBDW_DWARF_UNWIND=1
+make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1
# $(run) contains all available tests
run := make_pure
@@ -74,6 +75,7 @@
run += make_no_libnuma
run += make_no_libaudit
run += make_no_libbionic
+run += make_no_auxtrace
run += make_help
run += make_doc
run += make_perf_o
@@ -223,7 +225,19 @@
echo "- $@: $$cmd" && echo $$cmd > $@ && \
( eval $$cmd ) >> $@ 2>&1
-all: $(run) $(run_O) tarpkg
+make_kernelsrc:
+ @echo " - make -C <kernelsrc> tools/perf"
+ $(call clean); \
+ (make -C ../.. tools/perf) > $@ 2>&1 && \
+ test -x perf && rm -f $@ || (cat $@ ; false)
+
+make_kernelsrc_tools:
+ @echo " - make -C <kernelsrc>/tools perf"
+ $(call clean); \
+ (make -C ../../tools perf) > $@ 2>&1 && \
+ test -x perf && rm -f $@ || (cat $@ ; false)
+
+all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
@echo OK
out: $(run_O)
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 2113f1c..264e215 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -191,6 +191,8 @@
PERF_RECORD_MISC_USER, MAP__FUNCTION,
(unsigned long) (td->map + 1), &al);
+ thread__put(thread);
+
if (!al.map) {
pr_debug("failed, couldn't find map\n");
err = -1;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 3de7449..82d2a16 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1571,7 +1571,7 @@
if (evlist == NULL)
return -ENOMEM;
- ret = parse_events(evlist, e->name);
+ ret = parse_events(evlist, e->name, NULL);
if (ret) {
pr_debug("failed to parse event '%s', err %d\n",
e->name, ret);
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index f238442..5f49484 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -68,7 +68,7 @@
perf_evlist__set_maps(evlist, cpus, threads);
- CHECK__(parse_events(evlist, "cycles:u"));
+ CHECK__(parse_events(evlist, "cycles:u", NULL));
perf_evlist__config(evlist, &opts);
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index eeb68bb1..faa04e9 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,8 @@
if (ret)
break;
- ret = perf_pmu__config_terms(&formats, &attr, terms, false);
+ ret = perf_pmu__config_terms(&formats, &attr, terms,
+ false, NULL);
if (ret)
break;
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index cc68648..0d31403 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -347,7 +347,7 @@
perf_evlist__set_maps(evlist, cpus, threads);
/* First event */
- err = parse_events(evlist, "cpu-clock:u");
+ err = parse_events(evlist, "cpu-clock:u", NULL);
if (err) {
pr_debug("Failed to parse event dummy:u\n");
goto out_err;
@@ -356,7 +356,7 @@
cpu_clocks_evsel = perf_evlist__last(evlist);
/* Second event */
- err = parse_events(evlist, "cycles:u");
+ err = parse_events(evlist, "cycles:u", NULL);
if (err) {
pr_debug("Failed to parse event cycles:u\n");
goto out_err;
@@ -371,7 +371,7 @@
goto out;
}
- err = parse_events(evlist, sched_switch);
+ err = parse_events(evlist, sched_switch, NULL);
if (err) {
pr_debug("Failed to parse event %s\n", sched_switch);
goto out_err;
@@ -401,7 +401,7 @@
perf_evsel__set_sample_bit(cycles_evsel, TIME);
/* Fourth event */
- err = parse_events(evlist, "dummy:u");
+ err = parse_events(evlist, "dummy:u", NULL);
if (err) {
pr_debug("Failed to parse event dummy:u\n");
goto out_err;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 52758a3..a10eaf5 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -9,6 +9,15 @@
} \
} while (0)
+#define TEST_ASSERT_EQUAL(text, val, expected) \
+do { \
+ if (val != expected) { \
+ pr_debug("FAILED %s:%d %s (%d != %d)\n", \
+ __FILE__, __LINE__, text, val, expected); \
+ return -1; \
+ } \
+} while (0)
+
enum {
TEST_OK = 0,
TEST_FAIL = -1,
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index b028499..01fabb1 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -43,7 +43,7 @@
leader && t1 && t2 && t3 && other);
mg = leader->mg;
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
/* test the map groups pointer is shared */
TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -58,33 +58,40 @@
other_leader = machine__find_thread(machine, 4, 4);
TEST_ASSERT_VAL("failed to find other leader", other_leader);
+ /*
+ * Ok, now that all the rbtree related operations were done,
+ * lets remove all of them from there so that we can do the
+ * refcounting tests.
+ */
+ machine__remove_thread(machine, leader);
+ machine__remove_thread(machine, t1);
+ machine__remove_thread(machine, t2);
+ machine__remove_thread(machine, t3);
+ machine__remove_thread(machine, other);
+ machine__remove_thread(machine, other_leader);
+
other_mg = other->mg;
- TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
/* release thread group */
- thread__delete(leader);
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+ thread__put(leader);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
- thread__delete(t1);
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+ thread__put(t1);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
- thread__delete(t2);
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+ thread__put(t2);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
- thread__delete(t3);
+ thread__put(t3);
/* release other group */
- thread__delete(other_leader);
- TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+ thread__put(other_leader);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
- thread__delete(other);
-
- /*
- * Cannot call machine__delete_threads(machine) now,
- * because we've already released all the threads.
- */
+ thread__put(other);
machines__exit(&machines);
return 0;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 995b7a8..f981cb8 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -25,6 +25,9 @@
struct hists *hists;
struct hist_entry *he_selection;
struct map_symbol *selection;
+ struct hist_browser_timer *hbt;
+ struct pstack *pstack;
+ struct perf_session_env *env;
int print_seq;
bool show_dso;
bool show_headers;
@@ -60,7 +63,7 @@
struct hist_entry *he =
rb_entry(nd, struct hist_entry, rb_node);
- if (he->ms.unfolded)
+ if (he->unfolded)
unfolded_rows += he->nr_rows;
}
return unfolded_rows;
@@ -136,24 +139,19 @@
return unfolded ? '-' : '+';
}
-static char map_symbol__folded(const struct map_symbol *ms)
-{
- return ms->has_children ? tree__folded_sign(ms->unfolded) : ' ';
-}
-
static char hist_entry__folded(const struct hist_entry *he)
{
- return map_symbol__folded(&he->ms);
+ return he->has_children ? tree__folded_sign(he->unfolded) : ' ';
}
static char callchain_list__folded(const struct callchain_list *cl)
{
- return map_symbol__folded(&cl->ms);
+ return cl->has_children ? tree__folded_sign(cl->unfolded) : ' ';
}
-static void map_symbol__set_folding(struct map_symbol *ms, bool unfold)
+static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
{
- ms->unfolded = unfold ? ms->has_children : false;
+ cl->unfolded = unfold ? cl->has_children : false;
}
static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
@@ -189,7 +187,7 @@
list_for_each_entry(chain, &node->val, list) {
++n;
- unfolded = chain->ms.unfolded;
+ unfolded = chain->unfolded;
}
if (unfolded)
@@ -211,15 +209,27 @@
return n;
}
-static bool map_symbol__toggle_fold(struct map_symbol *ms)
+static bool hist_entry__toggle_fold(struct hist_entry *he)
{
- if (!ms)
+ if (!he)
return false;
- if (!ms->has_children)
+ if (!he->has_children)
return false;
- ms->unfolded = !ms->unfolded;
+ he->unfolded = !he->unfolded;
+ return true;
+}
+
+static bool callchain_list__toggle_fold(struct callchain_list *cl)
+{
+ if (!cl)
+ return false;
+
+ if (!cl->has_children)
+ return false;
+
+ cl->unfolded = !cl->unfolded;
return true;
}
@@ -235,10 +245,10 @@
list_for_each_entry(chain, &child->val, list) {
if (first) {
first = false;
- chain->ms.has_children = chain->list.next != &child->val ||
+ chain->has_children = chain->list.next != &child->val ||
!RB_EMPTY_ROOT(&child->rb_root);
} else
- chain->ms.has_children = chain->list.next == &child->val &&
+ chain->has_children = chain->list.next == &child->val &&
!RB_EMPTY_ROOT(&child->rb_root);
}
@@ -252,11 +262,11 @@
struct callchain_list *chain;
chain = list_entry(node->val.next, struct callchain_list, list);
- chain->ms.has_children = has_sibling;
+ chain->has_children = has_sibling;
if (!list_empty(&node->val)) {
chain = list_entry(node->val.prev, struct callchain_list, list);
- chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+ chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
}
callchain_node__init_have_children_rb_tree(node);
@@ -276,7 +286,7 @@
static void hist_entry__init_have_children(struct hist_entry *he)
{
if (!he->init_have_children) {
- he->ms.has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
+ he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
callchain__init_have_children(&he->sorted_chain);
he->init_have_children = true;
}
@@ -284,14 +294,22 @@
static bool hist_browser__toggle_fold(struct hist_browser *browser)
{
- if (map_symbol__toggle_fold(browser->selection)) {
- struct hist_entry *he = browser->he_selection;
+ struct hist_entry *he = browser->he_selection;
+ struct map_symbol *ms = browser->selection;
+ struct callchain_list *cl = container_of(ms, struct callchain_list, ms);
+ bool has_children;
+ if (ms == &he->ms)
+ has_children = hist_entry__toggle_fold(he);
+ else
+ has_children = callchain_list__toggle_fold(cl);
+
+ if (has_children) {
hist_entry__init_have_children(he);
browser->b.nr_entries -= he->nr_rows;
browser->nr_callchain_rows -= he->nr_rows;
- if (he->ms.unfolded)
+ if (he->unfolded)
he->nr_rows = callchain__count_rows(&he->sorted_chain);
else
he->nr_rows = 0;
@@ -318,8 +336,8 @@
list_for_each_entry(chain, &child->val, list) {
++n;
- map_symbol__set_folding(&chain->ms, unfold);
- has_children = chain->ms.has_children;
+ callchain_list__set_folding(chain, unfold);
+ has_children = chain->has_children;
}
if (has_children)
@@ -337,8 +355,8 @@
list_for_each_entry(chain, &node->val, list) {
++n;
- map_symbol__set_folding(&chain->ms, unfold);
- has_children = chain->ms.has_children;
+ callchain_list__set_folding(chain, unfold);
+ has_children = chain->has_children;
}
if (has_children)
@@ -363,9 +381,9 @@
static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
{
hist_entry__init_have_children(he);
- map_symbol__set_folding(&he->ms, unfold);
+ he->unfolded = unfold ? he->has_children : false;
- if (he->ms.has_children) {
+ if (he->has_children) {
int n = callchain__set_folding(&he->sorted_chain, unfold);
he->nr_rows = unfold ? n : 0;
} else
@@ -406,11 +424,11 @@
"Or reduce the sampling frequency.");
}
-static int hist_browser__run(struct hist_browser *browser,
- struct hist_browser_timer *hbt)
+static int hist_browser__run(struct hist_browser *browser)
{
int key;
char title[160];
+ struct hist_browser_timer *hbt = browser->hbt;
int delay_secs = hbt ? hbt->refresh : 0;
browser->b.entries = &browser->hists->entries;
@@ -1016,7 +1034,7 @@
if (offset > 0) {
do {
h = rb_entry(nd, struct hist_entry, rb_node);
- if (h->ms.unfolded) {
+ if (h->unfolded) {
u16 remaining = h->nr_rows - h->row_offset;
if (offset > remaining) {
offset -= remaining;
@@ -1037,7 +1055,7 @@
} else if (offset < 0) {
while (1) {
h = rb_entry(nd, struct hist_entry, rb_node);
- if (h->ms.unfolded) {
+ if (h->unfolded) {
if (first) {
if (-offset > h->row_offset) {
offset += h->row_offset;
@@ -1074,7 +1092,7 @@
* row_offset at its last entry.
*/
h = rb_entry(nd, struct hist_entry, rb_node);
- if (h->ms.unfolded)
+ if (h->unfolded)
h->row_offset = h->nr_rows;
break;
}
@@ -1195,7 +1213,9 @@
return 0;
}
-static struct hist_browser *hist_browser__new(struct hists *hists)
+static struct hist_browser *hist_browser__new(struct hists *hists,
+ struct hist_browser_timer *hbt,
+ struct perf_session_env *env)
{
struct hist_browser *browser = zalloc(sizeof(*browser));
@@ -1206,6 +1226,8 @@
browser->b.seek = ui_browser__hists_seek;
browser->b.use_navkeypressed = true;
browser->show_headers = symbol_conf.show_hist_headers;
+ browser->hbt = hbt;
+ browser->env = env;
}
return browser;
@@ -1395,6 +1417,257 @@
return ret;
}
+struct popup_action {
+ struct thread *thread;
+ struct dso *dso;
+ struct map_symbol ms;
+
+ int (*fn)(struct hist_browser *browser, struct popup_action *act);
+};
+
+static int
+do_annotate(struct hist_browser *browser, struct popup_action *act)
+{
+ struct perf_evsel *evsel;
+ struct annotation *notes;
+ struct hist_entry *he;
+ int err;
+
+ if (!objdump_path && perf_session_env__lookup_objdump(browser->env))
+ return 0;
+
+ notes = symbol__annotation(act->ms.sym);
+ if (!notes->src)
+ return 0;
+
+ evsel = hists_to_evsel(browser->hists);
+ err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt);
+ he = hist_browser__selected_entry(browser);
+ /*
+ * offer option to annotate the other branch source or target
+ * (if they exists) when returning from annotate
+ */
+ if ((err == 'q' || err == CTRL('c')) && he->branch_info)
+ return 1;
+
+ ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+ if (err)
+ ui_browser__handle_resize(&browser->b);
+ return 0;
+}
+
+static int
+add_annotate_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr,
+ struct map *map, struct symbol *sym)
+{
+ if (sym == NULL || map->dso->annotate_warned)
+ return 0;
+
+ if (asprintf(optstr, "Annotate %s", sym->name) < 0)
+ return 0;
+
+ act->ms.map = map;
+ act->ms.sym = sym;
+ act->fn = do_annotate;
+ return 1;
+}
+
+static int
+do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
+{
+ struct thread *thread = act->thread;
+
+ if (browser->hists->thread_filter) {
+ pstack__remove(browser->pstack, &browser->hists->thread_filter);
+ perf_hpp__set_elide(HISTC_THREAD, false);
+ thread__zput(browser->hists->thread_filter);
+ ui_helpline__pop();
+ } else {
+ ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+ thread->comm_set ? thread__comm_str(thread) : "",
+ thread->tid);
+ browser->hists->thread_filter = thread__get(thread);
+ perf_hpp__set_elide(HISTC_THREAD, false);
+ pstack__push(browser->pstack, &browser->hists->thread_filter);
+ }
+
+ hists__filter_by_thread(browser->hists);
+ hist_browser__reset(browser);
+ return 0;
+}
+
+static int
+add_thread_opt(struct hist_browser *browser, struct popup_action *act,
+ char **optstr, struct thread *thread)
+{
+ if (thread == NULL)
+ return 0;
+
+ if (asprintf(optstr, "Zoom %s %s(%d) thread",
+ browser->hists->thread_filter ? "out of" : "into",
+ thread->comm_set ? thread__comm_str(thread) : "",
+ thread->tid) < 0)
+ return 0;
+
+ act->thread = thread;
+ act->fn = do_zoom_thread;
+ return 1;
+}
+
+static int
+do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
+{
+ struct dso *dso = act->dso;
+
+ if (browser->hists->dso_filter) {
+ pstack__remove(browser->pstack, &browser->hists->dso_filter);
+ perf_hpp__set_elide(HISTC_DSO, false);
+ browser->hists->dso_filter = NULL;
+ ui_helpline__pop();
+ } else {
+ if (dso == NULL)
+ return 0;
+ ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+ dso->kernel ? "the Kernel" : dso->short_name);
+ browser->hists->dso_filter = dso;
+ perf_hpp__set_elide(HISTC_DSO, true);
+ pstack__push(browser->pstack, &browser->hists->dso_filter);
+ }
+
+ hists__filter_by_dso(browser->hists);
+ hist_browser__reset(browser);
+ return 0;
+}
+
+static int
+add_dso_opt(struct hist_browser *browser, struct popup_action *act,
+ char **optstr, struct dso *dso)
+{
+ if (dso == NULL)
+ return 0;
+
+ if (asprintf(optstr, "Zoom %s %s DSO",
+ browser->hists->dso_filter ? "out of" : "into",
+ dso->kernel ? "the Kernel" : dso->short_name) < 0)
+ return 0;
+
+ act->dso = dso;
+ act->fn = do_zoom_dso;
+ return 1;
+}
+
+static int
+do_browse_map(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act)
+{
+ map__browse(act->ms.map);
+ return 0;
+}
+
+static int
+add_map_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr, struct map *map)
+{
+ if (map == NULL)
+ return 0;
+
+ if (asprintf(optstr, "Browse map details") < 0)
+ return 0;
+
+ act->ms.map = map;
+ act->fn = do_browse_map;
+ return 1;
+}
+
+static int
+do_run_script(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act)
+{
+ char script_opt[64];
+ memset(script_opt, 0, sizeof(script_opt));
+
+ if (act->thread) {
+ scnprintf(script_opt, sizeof(script_opt), " -c %s ",
+ thread__comm_str(act->thread));
+ } else if (act->ms.sym) {
+ scnprintf(script_opt, sizeof(script_opt), " -S %s ",
+ act->ms.sym->name);
+ }
+
+ script_browse(script_opt);
+ return 0;
+}
+
+static int
+add_script_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr,
+ struct thread *thread, struct symbol *sym)
+{
+ if (thread) {
+ if (asprintf(optstr, "Run scripts for samples of thread [%s]",
+ thread__comm_str(thread)) < 0)
+ return 0;
+ } else if (sym) {
+ if (asprintf(optstr, "Run scripts for samples of symbol [%s]",
+ sym->name) < 0)
+ return 0;
+ } else {
+ if (asprintf(optstr, "Run scripts for all samples") < 0)
+ return 0;
+ }
+
+ act->thread = thread;
+ act->ms.sym = sym;
+ act->fn = do_run_script;
+ return 1;
+}
+
+static int
+do_switch_data(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act __maybe_unused)
+{
+ if (switch_data_file()) {
+ ui__warning("Won't switch the data files due to\n"
+ "no valid data file get selected!\n");
+ return 0;
+ }
+
+ return K_SWITCH_INPUT_DATA;
+}
+
+static int
+add_switch_opt(struct hist_browser *browser,
+ struct popup_action *act, char **optstr)
+{
+ if (!is_report_browser(browser->hbt))
+ return 0;
+
+ if (asprintf(optstr, "Switch to another data file in PWD") < 0)
+ return 0;
+
+ act->fn = do_switch_data;
+ return 1;
+}
+
+static int
+do_exit_browser(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act __maybe_unused)
+{
+ return 0;
+}
+
+static int
+add_exit_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr)
+{
+ if (asprintf(optstr, "Exit") < 0)
+ return 0;
+
+ act->fn = do_exit_browser;
+ return 1;
+}
+
static void hist_browser__update_nr_entries(struct hist_browser *hb)
{
u64 nr_entries = 0;
@@ -1421,14 +1694,14 @@
struct perf_session_env *env)
{
struct hists *hists = evsel__hists(evsel);
- struct hist_browser *browser = hist_browser__new(hists);
+ struct hist_browser *browser = hist_browser__new(hists, hbt, env);
struct branch_info *bi;
- struct pstack *fstack;
- char *options[16];
+#define MAX_OPTIONS 16
+ char *options[MAX_OPTIONS];
+ struct popup_action actions[MAX_OPTIONS];
int nr_options = 0;
int key = -1;
char buf[64];
- char script_opt[64];
int delay_secs = hbt ? hbt->refresh : 0;
struct perf_hpp_fmt *fmt;
@@ -1473,13 +1746,14 @@
hist_browser__update_nr_entries(browser);
}
- fstack = pstack__new(2);
- if (fstack == NULL)
+ browser->pstack = pstack__new(2);
+ if (browser->pstack == NULL)
goto out;
ui_helpline__push(helpline);
memset(options, 0, sizeof(options));
+ memset(actions, 0, sizeof(actions));
perf_hpp__for_each_format(fmt)
perf_hpp__reset_width(fmt, hists);
@@ -1489,16 +1763,12 @@
while (1) {
struct thread *thread = NULL;
- const struct dso *dso = NULL;
- int choice = 0,
- annotate = -2, zoom_dso = -2, zoom_thread = -2,
- annotate_f = -2, annotate_t = -2, browse_map = -2;
- int scripts_comm = -2, scripts_symbol = -2,
- scripts_all = -2, switch_data = -2;
+ struct dso *dso = NULL;
+ int choice = 0;
nr_options = 0;
- key = hist_browser__run(browser, hbt);
+ key = hist_browser__run(browser);
if (browser->he_selection != NULL) {
thread = hist_browser__selected_thread(browser);
@@ -1526,17 +1796,25 @@
browser->selection->sym == NULL ||
browser->selection->map->dso->annotate_warned)
continue;
- goto do_annotate;
+
+ actions->ms.map = browser->selection->map;
+ actions->ms.sym = browser->selection->sym;
+ do_annotate(browser, actions);
+ continue;
case 'P':
hist_browser__dump(browser);
continue;
case 'd':
- goto zoom_dso;
+ actions->dso = dso;
+ do_zoom_dso(browser, actions);
+ continue;
case 'V':
browser->show_dso = !browser->show_dso;
continue;
case 't':
- goto zoom_thread;
+ actions->thread = thread;
+ do_zoom_thread(browser, actions);
+ continue;
case '/':
if (ui_browser__input_window("Symbol to show",
"Please enter the name of symbol you want to see",
@@ -1548,12 +1826,18 @@
}
continue;
case 'r':
- if (is_report_browser(hbt))
- goto do_scripts;
+ if (is_report_browser(hbt)) {
+ actions->thread = NULL;
+ actions->ms.sym = NULL;
+ do_run_script(browser, actions);
+ }
continue;
case 's':
- if (is_report_browser(hbt))
- goto do_data_switch;
+ if (is_report_browser(hbt)) {
+ key = do_switch_data(browser, actions);
+ if (key == K_SWITCH_INPUT_DATA)
+ goto out_free_stack;
+ }
continue;
case 'i':
/* env->arch is NULL for live-mode (i.e. perf top) */
@@ -1583,7 +1867,7 @@
case K_LEFT: {
const void *top;
- if (pstack__empty(fstack)) {
+ if (pstack__empty(browser->pstack)) {
/*
* Go back to the perf_evsel_menu__run or other user
*/
@@ -1591,11 +1875,17 @@
goto out_free_stack;
continue;
}
- top = pstack__pop(fstack);
- if (top == &browser->hists->dso_filter)
- goto zoom_out_dso;
+ top = pstack__peek(browser->pstack);
+ if (top == &browser->hists->dso_filter) {
+ /*
+ * No need to set actions->dso here since
+ * it's just to remove the current filter.
+ * Ditto for thread below.
+ */
+ do_zoom_dso(browser, actions);
+ }
if (top == &browser->hists->thread_filter)
- goto zoom_out_thread;
+ do_zoom_thread(browser, actions);
continue;
}
case K_ESC:
@@ -1623,196 +1913,71 @@
if (bi == NULL)
goto skip_annotation;
- if (bi->from.sym != NULL &&
- !bi->from.map->dso->annotate_warned &&
- asprintf(&options[nr_options], "Annotate %s", bi->from.sym->name) > 0) {
- annotate_f = nr_options++;
- }
-
- if (bi->to.sym != NULL &&
- !bi->to.map->dso->annotate_warned &&
- (bi->to.sym != bi->from.sym ||
- bi->to.map->dso != bi->from.map->dso) &&
- asprintf(&options[nr_options], "Annotate %s", bi->to.sym->name) > 0) {
- annotate_t = nr_options++;
- }
+ nr_options += add_annotate_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ bi->from.map,
+ bi->from.sym);
+ if (bi->to.sym != bi->from.sym)
+ nr_options += add_annotate_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ bi->to.map,
+ bi->to.sym);
} else {
- if (browser->selection->sym != NULL &&
- !browser->selection->map->dso->annotate_warned) {
- struct annotation *notes;
-
- notes = symbol__annotation(browser->selection->sym);
-
- if (notes->src &&
- asprintf(&options[nr_options], "Annotate %s",
- browser->selection->sym->name) > 0) {
- annotate = nr_options++;
- }
- }
+ nr_options += add_annotate_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ browser->selection->map,
+ browser->selection->sym);
}
skip_annotation:
- if (thread != NULL &&
- asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
- (browser->hists->thread_filter ? "out of" : "into"),
- (thread->comm_set ? thread__comm_str(thread) : ""),
- thread->tid) > 0)
- zoom_thread = nr_options++;
-
- if (dso != NULL &&
- asprintf(&options[nr_options], "Zoom %s %s DSO",
- (browser->hists->dso_filter ? "out of" : "into"),
- (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
- zoom_dso = nr_options++;
-
- if (browser->selection != NULL &&
- browser->selection->map != NULL &&
- asprintf(&options[nr_options], "Browse map details") > 0)
- browse_map = nr_options++;
+ nr_options += add_thread_opt(browser, &actions[nr_options],
+ &options[nr_options], thread);
+ nr_options += add_dso_opt(browser, &actions[nr_options],
+ &options[nr_options], dso);
+ nr_options += add_map_opt(browser, &actions[nr_options],
+ &options[nr_options],
+ browser->selection->map);
/* perf script support */
if (browser->he_selection) {
- struct symbol *sym;
-
- if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]",
- thread__comm_str(browser->he_selection->thread)) > 0)
- scripts_comm = nr_options++;
-
- sym = browser->he_selection->ms.sym;
- if (sym && sym->namelen &&
- asprintf(&options[nr_options], "Run scripts for samples of symbol [%s]",
- sym->name) > 0)
- scripts_symbol = nr_options++;
+ nr_options += add_script_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ thread, NULL);
+ nr_options += add_script_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ NULL, browser->selection->sym);
}
-
- if (asprintf(&options[nr_options], "Run scripts for all samples") > 0)
- scripts_all = nr_options++;
-
- if (is_report_browser(hbt) && asprintf(&options[nr_options],
- "Switch to another data file in PWD") > 0)
- switch_data = nr_options++;
+ nr_options += add_script_opt(browser, &actions[nr_options],
+ &options[nr_options], NULL, NULL);
+ nr_options += add_switch_opt(browser, &actions[nr_options],
+ &options[nr_options]);
add_exit_option:
- options[nr_options++] = (char *)"Exit";
-retry_popup_menu:
- choice = ui__popup_menu(nr_options, options);
+ nr_options += add_exit_opt(browser, &actions[nr_options],
+ &options[nr_options]);
- if (choice == nr_options - 1)
- break;
+ do {
+ struct popup_action *act;
- if (choice == -1) {
- free_popup_options(options, nr_options - 1);
- continue;
- }
-
- if (choice == annotate || choice == annotate_t || choice == annotate_f) {
- struct hist_entry *he;
- struct annotation *notes;
- struct map_symbol ms;
- int err;
-do_annotate:
- if (!objdump_path && perf_session_env__lookup_objdump(env))
- continue;
-
- he = hist_browser__selected_entry(browser);
- if (he == NULL)
- continue;
-
- if (choice == annotate_f) {
- ms.map = he->branch_info->from.map;
- ms.sym = he->branch_info->from.sym;
- } else if (choice == annotate_t) {
- ms.map = he->branch_info->to.map;
- ms.sym = he->branch_info->to.sym;
- } else {
- ms = *browser->selection;
- }
-
- notes = symbol__annotation(ms.sym);
- if (!notes->src)
- continue;
-
- err = map_symbol__tui_annotate(&ms, evsel, hbt);
- /*
- * offer option to annotate the other branch source or target
- * (if they exists) when returning from annotate
- */
- if ((err == 'q' || err == CTRL('c'))
- && annotate_t != -2 && annotate_f != -2)
- goto retry_popup_menu;
-
- ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
- if (err)
- ui_browser__handle_resize(&browser->b);
-
- } else if (choice == browse_map)
- map__browse(browser->selection->map);
- else if (choice == zoom_dso) {
-zoom_dso:
- if (browser->hists->dso_filter) {
- pstack__remove(fstack, &browser->hists->dso_filter);
-zoom_out_dso:
- ui_helpline__pop();
- browser->hists->dso_filter = NULL;
- perf_hpp__set_elide(HISTC_DSO, false);
- } else {
- if (dso == NULL)
- continue;
- ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
- dso->kernel ? "the Kernel" : dso->short_name);
- browser->hists->dso_filter = dso;
- perf_hpp__set_elide(HISTC_DSO, true);
- pstack__push(fstack, &browser->hists->dso_filter);
- }
- hists__filter_by_dso(hists);
- hist_browser__reset(browser);
- } else if (choice == zoom_thread) {
-zoom_thread:
- if (browser->hists->thread_filter) {
- pstack__remove(fstack, &browser->hists->thread_filter);
-zoom_out_thread:
- ui_helpline__pop();
- thread__zput(browser->hists->thread_filter);
- perf_hpp__set_elide(HISTC_THREAD, false);
- } else {
- ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
- thread->comm_set ? thread__comm_str(thread) : "",
- thread->tid);
- browser->hists->thread_filter = thread__get(thread);
- perf_hpp__set_elide(HISTC_THREAD, false);
- pstack__push(fstack, &browser->hists->thread_filter);
- }
- hists__filter_by_thread(hists);
- hist_browser__reset(browser);
- }
- /* perf scripts support */
- else if (choice == scripts_all || choice == scripts_comm ||
- choice == scripts_symbol) {
-do_scripts:
- memset(script_opt, 0, 64);
-
- if (choice == scripts_comm)
- sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread));
-
- if (choice == scripts_symbol)
- sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name);
-
- script_browse(script_opt);
- }
- /* Switch to another data file */
- else if (choice == switch_data) {
-do_data_switch:
- if (!switch_data_file()) {
- key = K_SWITCH_INPUT_DATA;
+ choice = ui__popup_menu(nr_options, options);
+ if (choice == -1 || choice >= nr_options)
break;
- } else
- ui__warning("Won't switch the data files due to\n"
- "no valid data file get selected!\n");
- }
+
+ act = &actions[choice];
+ key = act->fn(browser, act);
+ } while (key == 1);
+
+ if (key == K_SWITCH_INPUT_DATA)
+ break;
}
out_free_stack:
- pstack__delete(fstack);
+ pstack__delete(browser->pstack);
out:
hist_browser__delete(browser);
- free_popup_options(options, nr_options - 1);
+ free_popup_options(options, MAX_OPTIONS);
return key;
}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a..6966d07 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -74,6 +74,7 @@
libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -101,23 +102,23 @@
$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
$(call rule_mkdir)
- @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+ $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
$(call rule_mkdir)
- @$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+ $(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
$(call rule_mkdir)
- @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+ $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
$(OUTPUT)util/pmu-bison.c: util/pmu.y
$(call rule_mkdir)
- @$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
+ $(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
CFLAGS_parse-events-flex.o += -w
CFLAGS_pmu-flex.o += -w
-CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
new file mode 100644
index 0000000..df66966
--- /dev/null
+++ b/tools/perf/util/auxtrace.c
@@ -0,0 +1,1352 @@
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/string.h>
+
+#include <sys/param.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
+#include <linux/list.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+#include <linux/hash.h>
+
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+#include "parse-options.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd)
+{
+ struct perf_event_mmap_page *pc = userpg;
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pr_err("Cannot use AUX area tracing mmaps\n");
+ return -1;
+#endif
+
+ WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+ mm->userpg = userpg;
+ mm->mask = mp->mask;
+ mm->len = mp->len;
+ mm->prev = 0;
+ mm->idx = mp->idx;
+ mm->tid = mp->tid;
+ mm->cpu = mp->cpu;
+
+ if (!mp->len) {
+ mm->base = NULL;
+ return 0;
+ }
+
+ pc->aux_offset = mp->offset;
+ pc->aux_size = mp->len;
+
+ mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+ if (mm->base == MAP_FAILED) {
+ pr_debug2("failed to mmap AUX area\n");
+ mm->base = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+ if (mm->base) {
+ munmap(mm->base, mm->len);
+ mm->base = NULL;
+ }
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
+{
+ if (auxtrace_pages) {
+ mp->offset = auxtrace_offset;
+ mp->len = auxtrace_pages * (size_t)page_size;
+ mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+ mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+ pr_debug2("AUX area mmap length %zu\n", mp->len);
+ } else {
+ mp->len = 0;
+ }
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu)
+{
+ mp->idx = idx;
+
+ if (per_cpu) {
+ mp->cpu = evlist->cpus->map[idx];
+ if (evlist->threads)
+ mp->tid = evlist->threads->map[0];
+ else
+ mp->tid = -1;
+ } else {
+ mp->cpu = -1;
+ mp->tid = evlist->threads->map[idx];
+ }
+}
+
+#define AUXTRACE_INIT_NR_QUEUES 32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+ struct auxtrace_queue *queue_array;
+ unsigned int max_nr_queues, i;
+
+ max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+ if (nr_queues > max_nr_queues)
+ return NULL;
+
+ queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+ if (!queue_array)
+ return NULL;
+
+ for (i = 0; i < nr_queues; i++) {
+ INIT_LIST_HEAD(&queue_array[i].head);
+ queue_array[i].priv = NULL;
+ }
+
+ return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+ queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+ queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+ if (!queues->queue_array)
+ return -ENOMEM;
+ return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+ unsigned int new_nr_queues)
+{
+ unsigned int nr_queues = queues->nr_queues;
+ struct auxtrace_queue *queue_array;
+ unsigned int i;
+
+ if (!nr_queues)
+ nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+ while (nr_queues && nr_queues < new_nr_queues)
+ nr_queues <<= 1;
+
+ if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+ return -EINVAL;
+
+ queue_array = auxtrace_alloc_queue_array(nr_queues);
+ if (!queue_array)
+ return -ENOMEM;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ list_splice_tail(&queues->queue_array[i].head,
+ &queue_array[i].head);
+ queue_array[i].priv = queues->queue_array[i].priv;
+ }
+
+ queues->nr_queues = nr_queues;
+ queues->queue_array = queue_array;
+
+ return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+ int fd = perf_data_file__fd(session->file);
+ void *p;
+ ssize_t ret;
+
+ if (size > SSIZE_MAX)
+ return NULL;
+
+ p = malloc(size);
+ if (!p)
+ return NULL;
+
+ ret = readn(fd, p, size);
+ if (ret != (ssize_t)size) {
+ free(p);
+ return NULL;
+ }
+
+ return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (idx >= queues->nr_queues) {
+ err = auxtrace_queues__grow(queues, idx + 1);
+ if (err)
+ return err;
+ }
+
+ queue = &queues->queue_array[idx];
+
+ if (!queue->set) {
+ queue->set = true;
+ queue->tid = buffer->tid;
+ queue->cpu = buffer->cpu;
+ } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+ pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+ queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+ return -EINVAL;
+ }
+
+ buffer->buffer_nr = queues->next_buffer_nr++;
+
+ list_add_tail(&buffer->list, &queue->head);
+
+ queues->new_data = true;
+ queues->populated = true;
+
+ return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ u64 sz = buffer->size;
+ bool consecutive = false;
+ struct auxtrace_buffer *b;
+ int err;
+
+ while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+ b = memdup(buffer, sizeof(struct auxtrace_buffer));
+ if (!b)
+ return -ENOMEM;
+ b->size = BUFFER_LIMIT_FOR_32_BIT;
+ b->consecutive = consecutive;
+ err = auxtrace_queues__add_buffer(queues, idx, b);
+ if (err) {
+ auxtrace_buffer__free(b);
+ return err;
+ }
+ buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+ sz -= BUFFER_LIMIT_FOR_32_BIT;
+ consecutive = true;
+ }
+
+ buffer->size = sz;
+ buffer->consecutive = consecutive;
+
+ return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ if (session->one_mmap) {
+ buffer->data = buffer->data_offset - session->one_mmap_offset +
+ session->one_mmap_addr;
+ } else if (perf_data_file__is_pipe(session->file)) {
+ buffer->data = auxtrace_copy_data(buffer->size, session);
+ if (!buffer->data)
+ return -ENOMEM;
+ buffer->data_needs_freeing = true;
+ } else if (BITS_PER_LONG == 32 &&
+ buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+ int err;
+
+ err = auxtrace_queues__split_buffer(queues, idx, buffer);
+ if (err)
+ return err;
+ }
+
+ return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr)
+{
+ struct auxtrace_buffer *buffer;
+ unsigned int idx;
+ int err;
+
+ buffer = zalloc(sizeof(struct auxtrace_buffer));
+ if (!buffer)
+ return -ENOMEM;
+
+ buffer->pid = -1;
+ buffer->tid = event->auxtrace.tid;
+ buffer->cpu = event->auxtrace.cpu;
+ buffer->data_offset = data_offset;
+ buffer->offset = event->auxtrace.offset;
+ buffer->reference = event->auxtrace.reference;
+ buffer->size = event->auxtrace.size;
+ idx = event->auxtrace.idx;
+
+ err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+ if (err)
+ goto out_err;
+
+ if (buffer_ptr)
+ *buffer_ptr = buffer;
+
+ return 0;
+
+out_err:
+ auxtrace_buffer__free(buffer);
+ return err;
+}
+
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ off_t file_offset, size_t sz)
+{
+ union perf_event *event;
+ int err;
+ char buf[PERF_SAMPLE_MAX_SIZE];
+
+ err = perf_session__peek_event(session, file_offset, buf,
+ PERF_SAMPLE_MAX_SIZE, &event, NULL);
+ if (err)
+ return err;
+
+ if (event->header.type == PERF_RECORD_AUXTRACE) {
+ if (event->header.size < sizeof(struct auxtrace_event) ||
+ event->header.size != sz) {
+ err = -EINVAL;
+ goto out;
+ }
+ file_offset += event->header.size;
+ err = auxtrace_queues__add_event(queues, session, event,
+ file_offset, NULL);
+ }
+out:
+ return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ while (!list_empty(&queues->queue_array[i].head)) {
+ struct auxtrace_buffer *buffer;
+
+ buffer = list_entry(queues->queue_array[i].head.next,
+ struct auxtrace_buffer, list);
+ list_del(&buffer->list);
+ auxtrace_buffer__free(buffer);
+ }
+ }
+
+ zfree(&queues->queue_array);
+ queues->nr_queues = 0;
+}
+
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+ unsigned int pos, unsigned int queue_nr,
+ u64 ordinal)
+{
+ unsigned int parent;
+
+ while (pos) {
+ parent = (pos - 1) >> 1;
+ if (heap_array[parent].ordinal <= ordinal)
+ break;
+ heap_array[pos] = heap_array[parent];
+ pos = parent;
+ }
+ heap_array[pos].queue_nr = queue_nr;
+ heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal)
+{
+ struct auxtrace_heap_item *heap_array;
+
+ if (queue_nr >= heap->heap_sz) {
+ unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+ while (heap_sz <= queue_nr)
+ heap_sz <<= 1;
+ heap_array = realloc(heap->heap_array,
+ heap_sz * sizeof(struct auxtrace_heap_item));
+ if (!heap_array)
+ return -ENOMEM;
+ heap->heap_array = heap_array;
+ heap->heap_sz = heap_sz;
+ }
+
+ auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+ return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+ zfree(&heap->heap_array);
+ heap->heap_cnt = 0;
+ heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+ unsigned int pos, last, heap_cnt = heap->heap_cnt;
+ struct auxtrace_heap_item *heap_array;
+
+ if (!heap_cnt)
+ return;
+
+ heap->heap_cnt -= 1;
+
+ heap_array = heap->heap_array;
+
+ pos = 0;
+ while (1) {
+ unsigned int left, right;
+
+ left = (pos << 1) + 1;
+ if (left >= heap_cnt)
+ break;
+ right = left + 1;
+ if (right >= heap_cnt) {
+ heap_array[pos] = heap_array[left];
+ return;
+ }
+ if (heap_array[left].ordinal < heap_array[right].ordinal) {
+ heap_array[pos] = heap_array[left];
+ pos = left;
+ } else {
+ heap_array[pos] = heap_array[right];
+ pos = right;
+ }
+ }
+
+ last = heap_cnt - 1;
+ auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+ heap_array[last].ordinal);
+}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->info_priv_size(itr);
+ return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+ pr_err("AUX area tracing is not supported on this architecture\n");
+ return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size)
+{
+ if (itr)
+ return itr->info_fill(itr, session, auxtrace_info, priv_size);
+ return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+ if (itr)
+ itr->free(itr);
+}
+
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
+{
+ if (itr && itr->snapshot_start)
+ return itr->snapshot_start(itr);
+ return 0;
+}
+
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+{
+ if (itr && itr->snapshot_finish)
+ return itr->snapshot_finish(itr);
+ return 0;
+}
+
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm,
+ unsigned char *data, u64 *head, u64 *old)
+{
+ if (itr && itr->find_snapshot)
+ return itr->find_snapshot(itr, idx, mm, data, head, old);
+ return 0;
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts)
+{
+ if (itr)
+ return itr->recording_options(itr, evlist, opts);
+ return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->reference(itr);
+ return 0;
+}
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts, const char *str)
+{
+ if (!str)
+ return 0;
+
+ if (itr)
+ return itr->parse_snapshot_options(itr, opts, str);
+
+ pr_err("No AUX area tracing to snapshot\n");
+ return -EINVAL;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+ *err = 0;
+ return NULL;
+}
+
+static int auxtrace_index__alloc(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+
+ auxtrace_index = malloc(sizeof(struct auxtrace_index));
+ if (!auxtrace_index)
+ return -ENOMEM;
+
+ auxtrace_index->nr = 0;
+ INIT_LIST_HEAD(&auxtrace_index->list);
+
+ list_add_tail(&auxtrace_index->list, head);
+
+ return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index, *n;
+
+ list_for_each_entry_safe(auxtrace_index, n, head, list) {
+ list_del(&auxtrace_index->list);
+ free(auxtrace_index);
+ }
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+ int err;
+
+ if (list_empty(head)) {
+ err = auxtrace_index__alloc(head);
+ if (err)
+ return NULL;
+ }
+
+ auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+ if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+ err = auxtrace_index__alloc(head);
+ if (err)
+ return NULL;
+ auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+ list);
+ }
+
+ return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+ union perf_event *event, off_t file_offset)
+{
+ struct auxtrace_index *auxtrace_index;
+ size_t nr;
+
+ auxtrace_index = auxtrace_index__last(head);
+ if (!auxtrace_index)
+ return -ENOMEM;
+
+ nr = auxtrace_index->nr;
+ auxtrace_index->entries[nr].file_offset = file_offset;
+ auxtrace_index->entries[nr].sz = event->header.size;
+ auxtrace_index->nr += 1;
+
+ return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+ struct auxtrace_index *auxtrace_index)
+{
+ struct auxtrace_index_entry ent;
+ size_t i;
+
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ ent.file_offset = auxtrace_index->entries[i].file_offset;
+ ent.sz = auxtrace_index->entries[i].sz;
+ if (writen(fd, &ent, sizeof(ent)) != sizeof(ent))
+ return -errno;
+ }
+ return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+ u64 total = 0;
+ int err;
+
+ list_for_each_entry(auxtrace_index, head, list)
+ total += auxtrace_index->nr;
+
+ if (writen(fd, &total, sizeof(total)) != sizeof(total))
+ return -errno;
+
+ list_for_each_entry(auxtrace_index, head, list) {
+ err = auxtrace_index__do_write(fd, auxtrace_index);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+ bool needs_swap)
+{
+ struct auxtrace_index *auxtrace_index;
+ struct auxtrace_index_entry ent;
+ size_t nr;
+
+ if (readn(fd, &ent, sizeof(ent)) != sizeof(ent))
+ return -1;
+
+ auxtrace_index = auxtrace_index__last(head);
+ if (!auxtrace_index)
+ return -1;
+
+ nr = auxtrace_index->nr;
+ if (needs_swap) {
+ auxtrace_index->entries[nr].file_offset =
+ bswap_64(ent.file_offset);
+ auxtrace_index->entries[nr].sz = bswap_64(ent.sz);
+ } else {
+ auxtrace_index->entries[nr].file_offset = ent.file_offset;
+ auxtrace_index->entries[nr].sz = ent.sz;
+ }
+
+ auxtrace_index->nr = nr + 1;
+
+ return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+ bool needs_swap)
+{
+ struct list_head *head = &session->auxtrace_index;
+ u64 nr;
+
+ if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+ return -1;
+
+ if (needs_swap)
+ nr = bswap_64(nr);
+
+ if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) > size)
+ return -1;
+
+ while (nr--) {
+ int err;
+
+ err = auxtrace_index__process_entry(fd, head, needs_swap);
+ if (err)
+ return -1;
+ }
+
+ return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ struct auxtrace_index_entry *ent)
+{
+ return auxtrace_queues__add_indexed_event(queues, session,
+ ent->file_offset, ent->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+ struct perf_session *session)
+{
+ struct auxtrace_index *auxtrace_index;
+ struct auxtrace_index_entry *ent;
+ size_t i;
+ int err;
+
+ list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ ent = &auxtrace_index->entries[i];
+ err = auxtrace_queues__process_index_entry(queues,
+ session,
+ ent);
+ if (err)
+ return err;
+ }
+ }
+ return 0;
+}
+
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer)
+{
+ if (buffer) {
+ if (list_is_last(&buffer->list, &queue->head))
+ return NULL;
+ return list_entry(buffer->list.next, struct auxtrace_buffer,
+ list);
+ } else {
+ if (list_empty(&queue->head))
+ return NULL;
+ return list_entry(queue->head.next, struct auxtrace_buffer,
+ list);
+ }
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+ size_t adj = buffer->data_offset & (page_size - 1);
+ size_t size = buffer->size + adj;
+ off_t file_offset = buffer->data_offset - adj;
+ void *addr;
+
+ if (buffer->data)
+ return buffer->data;
+
+ addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+ if (addr == MAP_FAILED)
+ return NULL;
+
+ buffer->mmap_addr = addr;
+ buffer->mmap_size = size;
+
+ buffer->data = addr + adj;
+
+ return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+ if (!buffer->data || !buffer->mmap_addr)
+ return;
+ munmap(buffer->mmap_addr, buffer->mmap_size);
+ buffer->mmap_addr = NULL;
+ buffer->mmap_size = 0;
+ buffer->data = NULL;
+ buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__put_data(buffer);
+ if (buffer->data_needs_freeing) {
+ buffer->data_needs_freeing = false;
+ zfree(&buffer->data);
+ buffer->use_data = NULL;
+ buffer->size = 0;
+ }
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__drop_data(buffer);
+ free(buffer);
+}
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg)
+{
+ size_t size;
+
+ memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+ auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+ auxtrace_error->type = type;
+ auxtrace_error->code = code;
+ auxtrace_error->cpu = cpu;
+ auxtrace_error->pid = pid;
+ auxtrace_error->tid = tid;
+ auxtrace_error->ip = ip;
+ strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+ size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+ strlen(auxtrace_error->msg) + 1;
+ auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process)
+{
+ union perf_event *ev;
+ size_t priv_size;
+ int err;
+
+ pr_debug2("Synthesizing auxtrace information\n");
+ priv_size = auxtrace_record__info_priv_size(itr);
+ ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+ if (!ev)
+ return -ENOMEM;
+
+ ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+ ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+ priv_size;
+ err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+ priv_size);
+ if (err)
+ goto out_free;
+
+ err = process(tool, ev, NULL, NULL);
+out_free:
+ free(ev);
+ return err;
+}
+
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+ return !session->itrace_synth_opts ||
+ session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ enum auxtrace_type type = event->auxtrace_info.type;
+
+ if (dump_trace)
+ fprintf(stdout, " type: %u\n", type);
+
+ switch (type) {
+ case PERF_AUXTRACE_UNKNOWN:
+ default:
+ return -EINVAL;
+ }
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ s64 err;
+
+ if (dump_trace)
+ fprintf(stdout, " size: %#"PRIx64" offset: %#"PRIx64" ref: %#"PRIx64" idx: %u tid: %d cpu: %d\n",
+ event->auxtrace.size, event->auxtrace.offset,
+ event->auxtrace.reference, event->auxtrace.idx,
+ event->auxtrace.tid, event->auxtrace.cpu);
+
+ if (auxtrace__dont_decode(session))
+ return event->auxtrace.size;
+
+ if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+ return -EINVAL;
+
+ err = session->auxtrace->process_auxtrace_event(session, event, tool);
+ if (err < 0)
+ return err;
+
+ return event->auxtrace.size;
+}
+
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD 100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+ synth_opts->instructions = true;
+ synth_opts->branches = true;
+ synth_opts->transactions = true;
+ synth_opts->errors = true;
+ synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+/*
+ * Please check tools/perf/Documentation/perf-script.txt for information
+ * about the options parsed here, which is introduced after this cset,
+ * when support in 'perf script' for these options is introduced.
+ */
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset)
+{
+ struct itrace_synth_opts *synth_opts = opt->value;
+ const char *p;
+ char *endptr;
+
+ synth_opts->set = true;
+
+ if (unset) {
+ synth_opts->dont_decode = true;
+ return 0;
+ }
+
+ if (!str) {
+ itrace_synth_opts__set_default(synth_opts);
+ return 0;
+ }
+
+ for (p = str; *p;) {
+ switch (*p++) {
+ case 'i':
+ synth_opts->instructions = true;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ synth_opts->period = strtoull(p, &endptr, 10);
+ p = endptr;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ switch (*p++) {
+ case 'i':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_INSTRUCTIONS;
+ break;
+ case 't':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_TICKS;
+ break;
+ case 'm':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'u':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'n':
+ if (*p++ != 's')
+ goto out_err;
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_NANOSECS;
+ break;
+ case '\0':
+ goto out;
+ default:
+ goto out_err;
+ }
+ }
+ break;
+ case 'b':
+ synth_opts->branches = true;
+ break;
+ case 'x':
+ synth_opts->transactions = true;
+ break;
+ case 'e':
+ synth_opts->errors = true;
+ break;
+ case 'd':
+ synth_opts->log = true;
+ break;
+ case 'c':
+ synth_opts->branches = true;
+ synth_opts->calls = true;
+ break;
+ case 'r':
+ synth_opts->branches = true;
+ synth_opts->returns = true;
+ break;
+ case 'g':
+ synth_opts->callchain = true;
+ synth_opts->callchain_sz =
+ PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ unsigned int val;
+
+ val = strtoul(p, &endptr, 10);
+ p = endptr;
+ if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+ goto out_err;
+ synth_opts->callchain_sz = val;
+ }
+ break;
+ case ' ':
+ case ',':
+ break;
+ default:
+ goto out_err;
+ }
+ }
+out:
+ if (synth_opts->instructions) {
+ if (!synth_opts->period_type)
+ synth_opts->period_type =
+ PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ if (!synth_opts->period)
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ }
+
+ return 0;
+
+out_err:
+ pr_err("Bad Instruction Tracing options '%s'\n", str);
+ return -EINVAL;
+}
+
+static const char * const auxtrace_error_type_name[] = {
+ [PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+ const char *error_type_name = NULL;
+
+ if (type < PERF_AUXTRACE_ERROR_MAX)
+ error_type_name = auxtrace_error_type_name[type];
+ if (!error_type_name)
+ error_type_name = "unknown AUX";
+ return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+ int ret;
+
+ ret = fprintf(fp, " %s error type %u",
+ auxtrace_error_name(e->type), e->type);
+ ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+ e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+ return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+
+ if (e->type < PERF_AUXTRACE_ERROR_MAX)
+ session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+ int i;
+
+ for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+ if (!stats->nr_auxtrace_errors[i])
+ continue;
+ ui__warning("%u %s errors\n",
+ stats->nr_auxtrace_errors[i],
+ auxtrace_error_name(i));
+ }
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (auxtrace__dont_decode(session))
+ return 0;
+
+ perf_event__fprintf_auxtrace_error(event, stdout);
+ return 0;
+}
+
+static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ bool snapshot, size_t snapshot_size)
+{
+ u64 head, old = mm->prev, offset, ref;
+ unsigned char *data = mm->base;
+ size_t size, head_off, old_off, len1, len2, padding;
+ union perf_event ev;
+ void *data1, *data2;
+
+ if (snapshot) {
+ head = auxtrace_mmap__read_snapshot_head(mm);
+ if (auxtrace_record__find_snapshot(itr, mm->idx, mm, data,
+ &head, &old))
+ return -1;
+ } else {
+ head = auxtrace_mmap__read_head(mm);
+ }
+
+ if (old == head)
+ return 0;
+
+ pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+ mm->idx, old, head, head - old);
+
+ if (mm->mask) {
+ head_off = head & mm->mask;
+ old_off = old & mm->mask;
+ } else {
+ head_off = head % mm->len;
+ old_off = old % mm->len;
+ }
+
+ if (head_off > old_off)
+ size = head_off - old_off;
+ else
+ size = mm->len - (old_off - head_off);
+
+ if (snapshot && size > snapshot_size)
+ size = snapshot_size;
+
+ ref = auxtrace_record__reference(itr);
+
+ if (head > old || size <= head || mm->mask) {
+ offset = head - size;
+ } else {
+ /*
+ * When the buffer size is not a power of 2, 'head' wraps at the
+ * highest multiple of the buffer size, so we have to subtract
+ * the remainder here.
+ */
+ u64 rem = (0ULL - mm->len) % mm->len;
+
+ offset = head - size - rem;
+ }
+
+ if (size > head_off) {
+ len1 = size - head_off;
+ data1 = &data[mm->len - len1];
+ len2 = head_off;
+ data2 = &data[0];
+ } else {
+ len1 = size;
+ data1 = &data[head_off - len1];
+ len2 = 0;
+ data2 = NULL;
+ }
+
+ /* padding must be written by fn() e.g. record__process_auxtrace() */
+ padding = size & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ memset(&ev, 0, sizeof(ev));
+ ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+ ev.auxtrace.header.size = sizeof(ev.auxtrace);
+ ev.auxtrace.size = size + padding;
+ ev.auxtrace.offset = offset;
+ ev.auxtrace.reference = ref;
+ ev.auxtrace.idx = mm->idx;
+ ev.auxtrace.tid = mm->tid;
+ ev.auxtrace.cpu = mm->cpu;
+
+ if (fn(tool, &ev, data1, len1, data2, len2))
+ return -1;
+
+ mm->prev = head;
+
+ if (!snapshot) {
+ auxtrace_mmap__write_tail(mm, head);
+ if (itr->read_finish) {
+ int err;
+
+ err = itr->read_finish(itr, mm->idx);
+ if (err < 0)
+ return err;
+ }
+ }
+
+ return 1;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn)
+{
+ return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+}
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ size_t snapshot_size)
+{
+ return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ * is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+ struct hlist_head *hashtable;
+ size_t sz;
+ size_t entry_size;
+ size_t limit;
+ size_t cnt;
+ unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent)
+{
+ struct auxtrace_cache *c;
+ struct hlist_head *ht;
+ size_t sz, i;
+
+ c = zalloc(sizeof(struct auxtrace_cache));
+ if (!c)
+ return NULL;
+
+ sz = 1UL << bits;
+
+ ht = calloc(sz, sizeof(struct hlist_head));
+ if (!ht)
+ goto out_free;
+
+ for (i = 0; i < sz; i++)
+ INIT_HLIST_HEAD(&ht[i]);
+
+ c->hashtable = ht;
+ c->sz = sz;
+ c->entry_size = entry_size;
+ c->limit = (c->sz * limit_percent) / 100;
+ c->bits = bits;
+
+ return c;
+
+out_free:
+ free(c);
+ return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_node *tmp;
+ size_t i;
+
+ if (!c)
+ return;
+
+ for (i = 0; i < c->sz; i++) {
+ hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+ hlist_del(&entry->hash);
+ auxtrace_cache__free_entry(c, entry);
+ }
+ }
+
+ c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+ if (!c)
+ return;
+
+ auxtrace_cache__drop(c);
+ free(c->hashtable);
+ free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+ return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+ void *entry)
+{
+ free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry)
+{
+ if (c->limit && ++c->cnt > c->limit)
+ auxtrace_cache__drop(c);
+
+ entry->key = key;
+ hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+ return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_head *hlist;
+
+ if (!c)
+ return NULL;
+
+ hlist = &c->hashtable[hash_32(key, c->bits)];
+ hlist_for_each_entry(entry, hlist, hash) {
+ if (entry->key == key)
+ return entry;
+ }
+
+ return NULL;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
new file mode 100644
index 0000000..a171abb
--- /dev/null
+++ b/tools/perf/util/auxtrace.h
@@ -0,0 +1,643 @@
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+
+union perf_event;
+struct perf_session;
+struct perf_evlist;
+struct perf_tool;
+struct option;
+struct record_opts;
+struct auxtrace_info_event;
+struct events_stats;
+
+enum auxtrace_type {
+ PERF_AUXTRACE_UNKNOWN,
+};
+
+enum itrace_period_type {
+ PERF_ITRACE_PERIOD_INSTRUCTIONS,
+ PERF_ITRACE_PERIOD_TICKS,
+ PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ * because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+ bool set;
+ bool inject;
+ bool instructions;
+ bool branches;
+ bool transactions;
+ bool errors;
+ bool dont_decode;
+ bool log;
+ bool calls;
+ bool returns;
+ bool callchain;
+ unsigned int callchain_sz;
+ unsigned long long period;
+ enum itrace_period_type period_type;
+};
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ * perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+ u64 file_offset;
+ u64 sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ * file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+ struct list_head list;
+ size_t nr;
+ struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+ int (*process_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool);
+ int (*process_auxtrace_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool);
+ int (*flush_events)(struct perf_session *session,
+ struct perf_tool *tool);
+ void (*free_events)(struct perf_session *session);
+ void (*free)(struct perf_session *session);
+};
+
+/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ * needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ * to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ * perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ * recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+ struct list_head list;
+ size_t size;
+ pid_t pid;
+ pid_t tid;
+ int cpu;
+ void *data;
+ off_t data_offset;
+ void *mmap_addr;
+ size_t mmap_size;
+ bool data_needs_freeing;
+ bool consecutive;
+ u64 offset;
+ u64 reference;
+ u64 buffer_nr;
+ size_t use_size;
+ void *use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+ struct list_head head;
+ pid_t tid;
+ int cpu;
+ bool set;
+ void *priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+ struct auxtrace_queue *queue_array;
+ unsigned int nr_queues;
+ bool new_data;
+ bool populated;
+ u64 next_buffer_nr;
+};
+
+/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ * to be a timestamp
+ */
+struct auxtrace_heap_item {
+ unsigned int queue_nr;
+ u64 ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+ struct auxtrace_heap_item *heap_array;
+ unsigned int heap_cnt;
+ unsigned int heap_sz;
+};
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+ void *base;
+ void *userpg;
+ size_t mask;
+ size_t len;
+ u64 prev;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+ size_t mask;
+ off_t offset;
+ size_t len;
+ int prot;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @snapshot_start: starting a snapshot
+ * @snapshot_finish: finishing a snapshot
+ * @find_snapshot: find data to snapshot within auxtrace mmap
+ * @parse_snapshot_options: parse snapshot options
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+ int (*recording_options)(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+ size_t (*info_priv_size)(struct auxtrace_record *itr);
+ int (*info_fill)(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+ void (*free)(struct auxtrace_record *itr);
+ int (*snapshot_start)(struct auxtrace_record *itr);
+ int (*snapshot_finish)(struct auxtrace_record *itr);
+ int (*find_snapshot)(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm, unsigned char *data,
+ u64 *head, u64 *old);
+ int (*parse_snapshot_options)(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str);
+ u64 (*reference)(struct auxtrace_record *itr);
+ int (*read_finish)(struct auxtrace_record *itr, int idx);
+};
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+/*
+ * In snapshot mode the mmapped page is read-only which makes using
+ * __sync_val_compare_and_swap() problematic. However, snapshot mode expects
+ * the buffer is not updated while the snapshot is made (e.g. Intel PT disables
+ * the event) so there is not a race anyway.
+ */
+static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+ u64 head = ACCESS_ONCE(pc->aux_head);
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+ u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 old_tail;
+#endif
+
+ /* Ensure all reads are done before we write the tail out */
+ mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pc->aux_tail = tail;
+#else
+ do {
+ old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+ } while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2);
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn);
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ size_t snapshot_size);
+
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+ struct perf_session *session);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
+struct auxtrace_cache_entry {
+ struct hlist_node hash;
+ u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+ int *err);
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str);
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm,
+ unsigned char *data, u64 *head, u64 *old);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+ off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+ bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg);
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process);
+int perf_event__process_auxtrace_info(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+int perf_event__process_auxtrace_error(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
+static inline int auxtrace__process_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free(session);
+}
+
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+ int *err __maybe_unused)
+{
+ *err = 0;
+ return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+ struct perf_tool *tool __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ perf_event__handler_t process __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ struct record_opts *opts __maybe_unused)
+{
+ return 0;
+}
+
+#define perf_event__process_auxtrace_info 0
+#define perf_event__process_auxtrace 0
+#define perf_event__process_auxtrace_error 0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+ __maybe_unused,
+ union perf_event *event
+ __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+ __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+ struct record_opts *opts __maybe_unused,
+ const char *str)
+{
+ if (!str)
+ return 0;
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_sample *sample __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+ struct list_head *head __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+ u64 size __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ bool needs_swap __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+#endif
+
+#endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 61867df..ad8cfcb 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -43,6 +43,7 @@
if (al.map != NULL)
al.map->dso->hit = 1;
+ thread__put(thread);
return 0;
}
@@ -59,8 +60,10 @@
dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
event->fork.ppid, event->fork.ptid);
- if (thread)
+ if (thread) {
machine__remove_thread(machine, thread);
+ thread__put(thread);
+ }
return 0;
}
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fbcca21..c861373 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -30,7 +30,6 @@
/* pager.c */
extern void setup_pager(void);
-extern const char *pager_program;
extern int pager_in_use(void);
extern int pager_use_color;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6033a0a..679c2c6 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -72,6 +72,10 @@
struct callchain_list {
u64 ip;
struct map_symbol ms;
+ struct /* for TUI */ {
+ bool unfolded;
+ bool has_children;
+ };
char *srcline;
struct list_head list;
};
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 88f7be3..32e12ecf 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -115,23 +115,19 @@
goto found;
n++;
}
- if (cgrp->refcnt == 0)
+ if (atomic_read(&cgrp->refcnt) == 0)
free(cgrp);
return -1;
found:
- cgrp->refcnt++;
+ atomic_inc(&cgrp->refcnt);
counter->cgrp = cgrp;
return 0;
}
void close_cgroup(struct cgroup_sel *cgrp)
{
- if (!cgrp)
- return;
-
- /* XXX: not reentrant */
- if (--cgrp->refcnt == 0) {
+ if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
close(cgrp->fd);
zfree(&cgrp->name);
free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 89acd6d..b4b8cb4 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,12 +1,14 @@
#ifndef __CGROUP_H__
#define __CGROUP_H__
+#include <linux/atomic.h>
+
struct option;
struct cgroup_sel {
char *name;
int fd;
- int refcnt;
+ atomic_t refcnt;
};
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index dd17c9a..5bfc119 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -14,6 +14,7 @@
#include <babeltrace/ctf-writer/event.h>
#include <babeltrace/ctf-writer/event-types.h>
#include <babeltrace/ctf-writer/event-fields.h>
+#include <babeltrace/ctf-ir/utils.h>
#include <babeltrace/ctf/events.h>
#include <traceevent/event-parse.h>
#include "asm/bug.h"
@@ -38,12 +39,21 @@
struct bt_ctf_event_class *event_class;
};
+#define MAX_CPUS 4096
+
+struct ctf_stream {
+ struct bt_ctf_stream *stream;
+ int cpu;
+ u32 count;
+};
+
struct ctf_writer {
/* writer primitives */
- struct bt_ctf_writer *writer;
- struct bt_ctf_stream *stream;
- struct bt_ctf_stream_class *stream_class;
- struct bt_ctf_clock *clock;
+ struct bt_ctf_writer *writer;
+ struct ctf_stream **stream;
+ int stream_cnt;
+ struct bt_ctf_stream_class *stream_class;
+ struct bt_ctf_clock *clock;
/* data types */
union {
@@ -65,6 +75,9 @@
u64 events_size;
u64 events_count;
+
+ /* Ordered events configured queue size. */
+ u64 queue_size;
};
static int value_set(struct bt_ctf_field_type *type,
@@ -153,6 +166,43 @@
return cw->data.u32;
}
+static unsigned long long adjust_signedness(unsigned long long value_int, int size)
+{
+ unsigned long long value_mask;
+
+ /*
+ * value_mask = (1 << (size * 8 - 1)) - 1.
+ * Directly set value_mask for code readers.
+ */
+ switch (size) {
+ case 1:
+ value_mask = 0x7fULL;
+ break;
+ case 2:
+ value_mask = 0x7fffULL;
+ break;
+ case 4:
+ value_mask = 0x7fffffffULL;
+ break;
+ case 8:
+ /*
+ * For 64 bit value, return it self. There is no need
+ * to fill high bit.
+ */
+ /* Fall through */
+ default:
+ /* BUG! */
+ return value_int;
+ }
+
+ /* If it is a positive value, don't adjust. */
+ if ((value_int & (~0ULL - value_mask)) == 0)
+ return value_int;
+
+ /* Fill upper part of value_int with 1 to make it a negative long long. */
+ return (value_int & value_mask) | ~value_mask;
+}
+
static int add_tracepoint_field_value(struct ctf_writer *cw,
struct bt_ctf_event_class *event_class,
struct bt_ctf_event *event,
@@ -164,7 +214,6 @@
struct bt_ctf_field *field;
const char *name = fmtf->name;
void *data = sample->raw_data;
- unsigned long long value_int;
unsigned long flags = fmtf->flags;
unsigned int n_items;
unsigned int i;
@@ -172,6 +221,7 @@
unsigned int len;
int ret;
+ name = fmtf->alias;
offset = fmtf->offset;
len = fmtf->size;
if (flags & FIELD_IS_STRING)
@@ -208,11 +258,6 @@
type = get_tracepoint_field_type(cw, fmtf);
for (i = 0; i < n_items; i++) {
- if (!(flags & FIELD_IS_STRING))
- value_int = pevent_read_number(
- fmtf->event->pevent,
- data + offset + i * len, len);
-
if (flags & FIELD_IS_ARRAY)
field = bt_ctf_field_array_get_field(array_field, i);
else
@@ -226,12 +271,21 @@
if (flags & FIELD_IS_STRING)
ret = bt_ctf_field_string_set_value(field,
data + offset + i * len);
- else if (!(flags & FIELD_IS_SIGNED))
- ret = bt_ctf_field_unsigned_integer_set_value(
- field, value_int);
- else
- ret = bt_ctf_field_signed_integer_set_value(
- field, value_int);
+ else {
+ unsigned long long value_int;
+
+ value_int = pevent_read_number(
+ fmtf->event->pevent,
+ data + offset + i * len, len);
+
+ if (!(flags & FIELD_IS_SIGNED))
+ ret = bt_ctf_field_unsigned_integer_set_value(
+ field, value_int);
+ else
+ ret = bt_ctf_field_signed_integer_set_value(
+ field, adjust_signedness(value_int, len));
+ }
+
if (ret) {
pr_err("failed to set file value %s\n", name);
goto err_put_field;
@@ -346,12 +400,6 @@
return -1;
}
- if (type & PERF_SAMPLE_CPU) {
- ret = value_set_u32(cw, event, "perf_cpu", sample->cpu);
- if (ret)
- return -1;
- }
-
if (type & PERF_SAMPLE_PERIOD) {
ret = value_set_u64(cw, event, "perf_period", sample->period);
if (ret)
@@ -381,6 +429,129 @@
return 0;
}
+static int ctf_stream__flush(struct ctf_stream *cs)
+{
+ int err = 0;
+
+ if (cs) {
+ err = bt_ctf_stream_flush(cs->stream);
+ if (err)
+ pr_err("CTF stream %d flush failed\n", cs->cpu);
+
+ pr("Flush stream for cpu %d (%u samples)\n",
+ cs->cpu, cs->count);
+
+ cs->count = 0;
+ }
+
+ return err;
+}
+
+static struct ctf_stream *ctf_stream__create(struct ctf_writer *cw, int cpu)
+{
+ struct ctf_stream *cs;
+ struct bt_ctf_field *pkt_ctx = NULL;
+ struct bt_ctf_field *cpu_field = NULL;
+ struct bt_ctf_stream *stream = NULL;
+ int ret;
+
+ cs = zalloc(sizeof(*cs));
+ if (!cs) {
+ pr_err("Failed to allocate ctf stream\n");
+ return NULL;
+ }
+
+ stream = bt_ctf_writer_create_stream(cw->writer, cw->stream_class);
+ if (!stream) {
+ pr_err("Failed to create CTF stream\n");
+ goto out;
+ }
+
+ pkt_ctx = bt_ctf_stream_get_packet_context(stream);
+ if (!pkt_ctx) {
+ pr_err("Failed to obtain packet context\n");
+ goto out;
+ }
+
+ cpu_field = bt_ctf_field_structure_get_field(pkt_ctx, "cpu_id");
+ bt_ctf_field_put(pkt_ctx);
+ if (!cpu_field) {
+ pr_err("Failed to obtain cpu field\n");
+ goto out;
+ }
+
+ ret = bt_ctf_field_unsigned_integer_set_value(cpu_field, (u32) cpu);
+ if (ret) {
+ pr_err("Failed to update CPU number\n");
+ goto out;
+ }
+
+ bt_ctf_field_put(cpu_field);
+
+ cs->cpu = cpu;
+ cs->stream = stream;
+ return cs;
+
+out:
+ if (cpu_field)
+ bt_ctf_field_put(cpu_field);
+ if (stream)
+ bt_ctf_stream_put(stream);
+
+ free(cs);
+ return NULL;
+}
+
+static void ctf_stream__delete(struct ctf_stream *cs)
+{
+ if (cs) {
+ bt_ctf_stream_put(cs->stream);
+ free(cs);
+ }
+}
+
+static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu)
+{
+ struct ctf_stream *cs = cw->stream[cpu];
+
+ if (!cs) {
+ cs = ctf_stream__create(cw, cpu);
+ cw->stream[cpu] = cs;
+ }
+
+ return cs;
+}
+
+static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample,
+ struct perf_evsel *evsel)
+{
+ int cpu = 0;
+
+ if (evsel->attr.sample_type & PERF_SAMPLE_CPU)
+ cpu = sample->cpu;
+
+ if (cpu > cw->stream_cnt) {
+ pr_err("Event was recorded for CPU %d, limit is at %d.\n",
+ cpu, cw->stream_cnt);
+ cpu = 0;
+ }
+
+ return cpu;
+}
+
+#define STREAM_FLUSH_COUNT 100000
+
+/*
+ * Currently we have no other way to determine the
+ * time for the stream flush other than keep track
+ * of the number of events and check it against
+ * threshold.
+ */
+static bool is_flush_needed(struct ctf_stream *cs)
+{
+ return cs->count >= STREAM_FLUSH_COUNT;
+}
+
static int process_sample_event(struct perf_tool *tool,
union perf_event *_event __maybe_unused,
struct perf_sample *sample,
@@ -390,6 +561,7 @@
struct convert *c = container_of(tool, struct convert, tool);
struct evsel_priv *priv = evsel->priv;
struct ctf_writer *cw = &c->writer;
+ struct ctf_stream *cs;
struct bt_ctf_event_class *event_class;
struct bt_ctf_event *event;
int ret;
@@ -424,9 +596,93 @@
return -1;
}
- bt_ctf_stream_append_event(cw->stream, event);
+ cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
+ if (cs) {
+ if (is_flush_needed(cs))
+ ctf_stream__flush(cs);
+
+ cs->count++;
+ bt_ctf_stream_append_event(cs->stream, event);
+ }
+
bt_ctf_event_put(event);
- return 0;
+ return cs ? 0 : -1;
+}
+
+/* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
+static char *change_name(char *name, char *orig_name, int dup)
+{
+ char *new_name = NULL;
+ size_t len;
+
+ if (!name)
+ name = orig_name;
+
+ if (dup >= 10)
+ goto out;
+ /*
+ * Add '_' prefix to potential keywork. According to
+ * Mathieu Desnoyers (https://lkml.org/lkml/2015/1/23/652),
+ * futher CTF spec updating may require us to use '$'.
+ */
+ if (dup < 0)
+ len = strlen(name) + sizeof("_");
+ else
+ len = strlen(orig_name) + sizeof("_dupl_X");
+
+ new_name = malloc(len);
+ if (!new_name)
+ goto out;
+
+ if (dup < 0)
+ snprintf(new_name, len, "_%s", name);
+ else
+ snprintf(new_name, len, "%s_dupl_%d", orig_name, dup);
+
+out:
+ if (name != orig_name)
+ free(name);
+ return new_name;
+}
+
+static int event_class_add_field(struct bt_ctf_event_class *event_class,
+ struct bt_ctf_field_type *type,
+ struct format_field *field)
+{
+ struct bt_ctf_field_type *t = NULL;
+ char *name;
+ int dup = 1;
+ int ret;
+
+ /* alias was already assigned */
+ if (field->alias != field->name)
+ return bt_ctf_event_class_add_field(event_class, type,
+ (char *)field->alias);
+
+ name = field->name;
+
+ /* If 'name' is a keywork, add prefix. */
+ if (bt_ctf_validate_identifier(name))
+ name = change_name(name, field->name, -1);
+
+ if (!name) {
+ pr_err("Failed to fix invalid identifier.");
+ return -1;
+ }
+ while ((t = bt_ctf_event_class_get_field_by_name(event_class, name))) {
+ bt_ctf_field_type_put(t);
+ name = change_name(name, field->name, dup++);
+ if (!name) {
+ pr_err("Failed to create dup name for '%s'\n", field->name);
+ return -1;
+ }
+ }
+
+ ret = bt_ctf_event_class_add_field(event_class, type, name);
+ if (!ret)
+ field->alias = name;
+
+ return ret;
}
static int add_tracepoint_fields_types(struct ctf_writer *cw,
@@ -457,14 +713,14 @@
if (flags & FIELD_IS_ARRAY)
type = bt_ctf_field_type_array_create(type, field->arraylen);
- ret = bt_ctf_event_class_add_field(event_class, type,
- field->name);
+ ret = event_class_add_field(event_class, type, field);
if (flags & FIELD_IS_ARRAY)
bt_ctf_field_type_put(type);
if (ret) {
- pr_err("Failed to add field '%s\n", field->name);
+ pr_err("Failed to add field '%s': %d\n",
+ field->name, ret);
return -1;
}
}
@@ -508,7 +764,7 @@
do { \
pr2(" field '%s'\n", n); \
if (bt_ctf_event_class_add_field(cl, t, n)) { \
- pr_err("Failed to add field '%s;\n", n); \
+ pr_err("Failed to add field '%s';\n", n); \
return -1; \
} \
} while (0)
@@ -528,9 +784,6 @@
if (type & PERF_SAMPLE_STREAM_ID)
ADD_FIELD(event_class, cw->data.u64, "perf_stream_id");
- if (type & PERF_SAMPLE_CPU)
- ADD_FIELD(event_class, cw->data.u32, "perf_cpu");
-
if (type & PERF_SAMPLE_PERIOD)
ADD_FIELD(event_class, cw->data.u64, "perf_period");
@@ -604,6 +857,39 @@
return 0;
}
+static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
+{
+ struct ctf_stream **stream;
+ struct perf_header *ph = &session->header;
+ int ncpus;
+
+ /*
+ * Try to get the number of cpus used in the data file,
+ * if not present fallback to the MAX_CPUS.
+ */
+ ncpus = ph->env.nr_cpus_avail ?: MAX_CPUS;
+
+ stream = zalloc(sizeof(*stream) * ncpus);
+ if (!stream) {
+ pr_err("Failed to allocate streams.\n");
+ return -ENOMEM;
+ }
+
+ cw->stream = stream;
+ cw->stream_cnt = ncpus;
+ return 0;
+}
+
+static void free_streams(struct ctf_writer *cw)
+{
+ int cpu;
+
+ for (cpu = 0; cpu < cw->stream_cnt; cpu++)
+ ctf_stream__delete(cw->stream[cpu]);
+
+ free(cw->stream);
+}
+
static int ctf_writer__setup_env(struct ctf_writer *cw,
struct perf_session *session)
{
@@ -713,7 +999,7 @@
ctf_writer__cleanup_data(cw);
bt_ctf_clock_put(cw->clock);
- bt_ctf_stream_put(cw->stream);
+ free_streams(cw);
bt_ctf_stream_class_put(cw->stream_class);
bt_ctf_writer_put(cw->writer);
@@ -725,8 +1011,9 @@
{
struct bt_ctf_writer *writer;
struct bt_ctf_stream_class *stream_class;
- struct bt_ctf_stream *stream;
struct bt_ctf_clock *clock;
+ struct bt_ctf_field_type *pkt_ctx_type;
+ int ret;
/* CTF writer */
writer = bt_ctf_writer_create(path);
@@ -767,14 +1054,15 @@
if (ctf_writer__init_data(cw))
goto err_cleanup;
- /* CTF stream instance */
- stream = bt_ctf_writer_create_stream(writer, stream_class);
- if (!stream) {
- pr("Failed to create CTF stream.\n");
+ /* Add cpu_id for packet context */
+ pkt_ctx_type = bt_ctf_stream_class_get_packet_context_type(stream_class);
+ if (!pkt_ctx_type)
goto err_cleanup;
- }
- cw->stream = stream;
+ ret = bt_ctf_field_type_structure_add_field(pkt_ctx_type, cw->data.u32, "cpu_id");
+ bt_ctf_field_type_put(pkt_ctx_type);
+ if (ret)
+ goto err_cleanup;
/* CTF clock writer setup */
if (bt_ctf_writer_add_clock(writer, clock)) {
@@ -791,6 +1079,28 @@
return -1;
}
+static int ctf_writer__flush_streams(struct ctf_writer *cw)
+{
+ int cpu, ret = 0;
+
+ for (cpu = 0; cpu < cw->stream_cnt && !ret; cpu++)
+ ret = ctf_stream__flush(cw->stream[cpu]);
+
+ return ret;
+}
+
+static int convert__config(const char *var, const char *value, void *cb)
+{
+ struct convert *c = cb;
+
+ if (!strcmp(var, "convert.queue-size")) {
+ c->queue_size = perf_config_u64(var, value);
+ return 0;
+ }
+
+ return perf_default_config(var, value, cb);
+}
+
int bt_convert__perf2ctf(const char *input, const char *path, bool force)
{
struct perf_session *session;
@@ -817,6 +1127,8 @@
struct ctf_writer *cw = &c.writer;
int err = -1;
+ perf_config(convert__config, &c);
+
/* CTF writer */
if (ctf_writer__init(cw, path))
return -1;
@@ -826,6 +1138,11 @@
if (!session)
goto free_writer;
+ if (c.queue_size) {
+ ordered_events__set_alloc_size(&session->ordered_events,
+ c.queue_size);
+ }
+
/* CTF writer env/clock setup */
if (ctf_writer__setup_env(cw, session))
goto free_session;
@@ -834,9 +1151,14 @@
if (setup_events(cw, session))
goto free_session;
+ if (setup_streams(cw, session))
+ goto free_session;
+
err = perf_session__process_events(session);
if (!err)
- err = bt_ctf_stream_flush(cw->stream);
+ err = ctf_writer__flush_streams(cw);
+ else
+ pr_err("Error during conversion.\n");
fprintf(stderr,
"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
@@ -847,11 +1169,15 @@
(double) c.events_size / 1024.0 / 1024.0,
c.events_count);
- /* its all good */
+ perf_session__delete(session);
+ ctf_writer__cleanup(cw);
+
+ return err;
+
free_session:
perf_session__delete(session);
-
free_writer:
ctf_writer__cleanup(cw);
+ pr_err("Error during conversion setup.\n");
return err;
}
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index bb39a3f..eb7a2ac 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -122,6 +122,7 @@
int db_export__thread(struct db_export *dbe, struct thread *thread,
struct machine *machine, struct comm *comm)
{
+ struct thread *main_thread;
u64 main_thread_db_id = 0;
int err;
@@ -131,8 +132,6 @@
thread->db_id = ++dbe->thread_last_db_id;
if (thread->pid_ != -1) {
- struct thread *main_thread;
-
if (thread->pid_ == thread->tid) {
main_thread = thread;
} else {
@@ -144,14 +143,16 @@
err = db_export__thread(dbe, main_thread, machine,
comm);
if (err)
- return err;
+ goto out_put;
if (comm) {
err = db_export__comm_thread(dbe, comm, thread);
if (err)
- return err;
+ goto out_put;
}
}
main_thread_db_id = main_thread->db_id;
+ if (main_thread != thread)
+ thread__put(main_thread);
}
if (dbe->export_thread)
@@ -159,6 +160,10 @@
machine);
return 0;
+
+out_put:
+ thread__put(main_thread);
+ return err;
}
int db_export__comm(struct db_export *dbe, struct comm *comm,
@@ -303,6 +308,7 @@
if (err)
return err;
+ /* FIXME: check refcounting for get_main_thread, that calls machine__find_thread... */
main_thread = get_main_thread(al->machine, thread);
if (main_thread)
comm = machine__thread_exec_comm(al->machine, main_thread);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc0ddd5..1b96c8d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -4,6 +4,7 @@
#include "symbol.h"
#include "dso.h"
#include "machine.h"
+#include "auxtrace.h"
#include "util.h"
#include "debug.h"
@@ -264,6 +265,7 @@
*/
static LIST_HEAD(dso__data_open);
static long dso__data_open_cnt;
+static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
static void dso__list_add(struct dso *dso)
{
@@ -433,7 +435,9 @@
*/
void dso__data_close(struct dso *dso)
{
+ pthread_mutex_lock(&dso__data_open_lock);
close_dso(dso);
+ pthread_mutex_unlock(&dso__data_open_lock);
}
/**
@@ -456,6 +460,8 @@
if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
+ pthread_mutex_lock(&dso__data_open_lock);
+
if (dso->data.fd >= 0)
goto out;
@@ -478,6 +484,7 @@
else
dso->data.status = DSO_DATA_STATUS_ERROR;
+ pthread_mutex_unlock(&dso__data_open_lock);
return dso->data.fd;
}
@@ -494,10 +501,12 @@
}
static void
-dso_cache__free(struct rb_root *root)
+dso_cache__free(struct dso *dso)
{
+ struct rb_root *root = &dso->data.cache;
struct rb_node *next = rb_first(root);
+ pthread_mutex_lock(&dso->lock);
while (next) {
struct dso_cache *cache;
@@ -506,10 +515,12 @@
rb_erase(&cache->rb_node, root);
free(cache);
}
+ pthread_mutex_unlock(&dso->lock);
}
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
{
+ const struct rb_root *root = &dso->data.cache;
struct rb_node * const *p = &root->rb_node;
const struct rb_node *parent = NULL;
struct dso_cache *cache;
@@ -528,17 +539,20 @@
else
return cache;
}
+
return NULL;
}
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+static struct dso_cache *
+dso_cache__insert(struct dso *dso, struct dso_cache *new)
{
+ struct rb_root *root = &dso->data.cache;
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct dso_cache *cache;
u64 offset = new->offset;
+ pthread_mutex_lock(&dso->lock);
while (*p != NULL) {
u64 end;
@@ -550,10 +564,17 @@
p = &(*p)->rb_left;
else if (offset >= end)
p = &(*p)->rb_right;
+ else
+ goto out;
}
rb_link_node(&new->rb_node, parent, p);
rb_insert_color(&new->rb_node, root);
+
+ cache = NULL;
+out:
+ pthread_mutex_unlock(&dso->lock);
+ return cache;
}
static ssize_t
@@ -568,19 +589,34 @@
}
static ssize_t
-dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
+ struct dso_cache *old;
ssize_t ret;
do {
u64 cache_offset;
- ret = -ENOMEM;
-
cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
if (!cache)
- break;
+ return -ENOMEM;
+
+ pthread_mutex_lock(&dso__data_open_lock);
+
+ /*
+ * dso->data.fd might be closed if other thread opened another
+ * file (dso) due to open file limit (RLIMIT_NOFILE).
+ */
+ if (dso->data.fd < 0) {
+ dso->data.fd = open_dso(dso, machine);
+ if (dso->data.fd < 0) {
+ ret = -errno;
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ break;
+ }
+ }
cache_offset = offset & DSO__DATA_CACHE_MASK;
@@ -590,11 +626,20 @@
cache->offset = cache_offset;
cache->size = ret;
- dso_cache__insert(&dso->data.cache, cache);
+ } while (0);
+
+ pthread_mutex_unlock(&dso__data_open_lock);
+
+ if (ret > 0) {
+ old = dso_cache__insert(dso, cache);
+ if (old) {
+ /* we lose the race */
+ free(cache);
+ cache = old;
+ }
ret = dso_cache__memcpy(cache, offset, data, size);
-
- } while (0);
+ }
if (ret <= 0)
free(cache);
@@ -602,16 +647,16 @@
return ret;
}
-static ssize_t dso_cache_read(struct dso *dso, u64 offset,
- u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
- cache = dso_cache__find(&dso->data.cache, offset);
+ cache = dso_cache__find(dso, offset);
if (cache)
return dso_cache__memcpy(cache, offset, data, size);
else
- return dso_cache__read(dso, offset, data, size);
+ return dso_cache__read(dso, machine, offset, data, size);
}
/*
@@ -619,7 +664,8 @@
* in the rb_tree. Any read to already cached data is served
* by cached data.
*/
-static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+static ssize_t cached_read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
ssize_t r = 0;
u8 *p = data;
@@ -627,7 +673,7 @@
do {
ssize_t ret;
- ret = dso_cache_read(dso, offset, p, size);
+ ret = dso_cache_read(dso, machine, offset, p, size);
if (ret < 0)
return ret;
@@ -647,21 +693,42 @@
return r;
}
-static int data_file_size(struct dso *dso)
+static int data_file_size(struct dso *dso, struct machine *machine)
{
+ int ret = 0;
struct stat st;
char sbuf[STRERR_BUFSIZE];
- if (!dso->data.file_size) {
- if (fstat(dso->data.fd, &st)) {
- pr_err("dso mmap failed, fstat: %s\n",
- strerror_r(errno, sbuf, sizeof(sbuf)));
- return -1;
+ if (dso->data.file_size)
+ return 0;
+
+ pthread_mutex_lock(&dso__data_open_lock);
+
+ /*
+ * dso->data.fd might be closed if other thread opened another
+ * file (dso) due to open file limit (RLIMIT_NOFILE).
+ */
+ if (dso->data.fd < 0) {
+ dso->data.fd = open_dso(dso, machine);
+ if (dso->data.fd < 0) {
+ ret = -errno;
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ goto out;
}
- dso->data.file_size = st.st_size;
}
- return 0;
+ if (fstat(dso->data.fd, &st) < 0) {
+ ret = -errno;
+ pr_err("dso cache fstat failed: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ goto out;
+ }
+ dso->data.file_size = st.st_size;
+
+out:
+ pthread_mutex_unlock(&dso__data_open_lock);
+ return ret;
}
/**
@@ -679,17 +746,17 @@
if (fd < 0)
return fd;
- if (data_file_size(dso))
+ if (data_file_size(dso, machine))
return -1;
/* For now just estimate dso data size is close to file size */
return dso->data.file_size;
}
-static ssize_t data_read_offset(struct dso *dso, u64 offset,
- u8 *data, ssize_t size)
+static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
- if (data_file_size(dso))
+ if (data_file_size(dso, machine))
return -1;
/* Check the offset sanity. */
@@ -699,7 +766,7 @@
if (offset + size < offset)
return -1;
- return cached_read(dso, offset, data, size);
+ return cached_read(dso, machine, offset, data, size);
}
/**
@@ -716,10 +783,10 @@
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
- if (dso__data_fd(dso, machine) < 0)
+ if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
- return data_read_offset(dso, offset, data, size);
+ return data_read_offset(dso, machine, offset, data, size);
}
/**
@@ -935,6 +1002,7 @@
RB_CLEAR_NODE(&dso->rb_node);
INIT_LIST_HEAD(&dso->node);
INIT_LIST_HEAD(&dso->data.open_entry);
+ pthread_mutex_init(&dso->lock, NULL);
}
return dso;
@@ -961,9 +1029,11 @@
}
dso__data_close(dso);
- dso_cache__free(&dso->data.cache);
+ auxtrace_cache__free(dso->auxtrace_cache);
+ dso_cache__free(dso);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
+ pthread_mutex_destroy(&dso->lock);
free(dso);
}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e0901b4..b26ec3a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -126,7 +126,10 @@
struct rb_root root; /* rbtree root sorted by long name */
};
+struct auxtrace_cache;
+
struct dso {
+ pthread_mutex_t lock;
struct list_head node;
struct rb_node rb_node; /* rbtree node sorted by long name */
struct rb_root symbols[MAP__NR_TYPES];
@@ -156,6 +159,7 @@
u16 long_name_len;
u16 short_name_len;
void *dwfl; /* DWARF debug info */
+ struct auxtrace_cache *auxtrace_cache;
/* dso data file */
struct {
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index c34e024..57f3ef4 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -139,11 +139,27 @@
bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
{
const char *name;
+
name = dwarf_diename(dw_die);
return name ? (strcmp(tname, name) == 0) : false;
}
/**
+ * die_match_name - Match diename and glob
+ * @dw_die: a DIE
+ * @glob: a string of target glob pattern
+ *
+ * Glob matching the name of @dw_die and @glob. Return false if matching fail.
+ */
+bool die_match_name(Dwarf_Die *dw_die, const char *glob)
+{
+ const char *name;
+
+ name = dwarf_diename(dw_die);
+ return name ? strglobmatch(name, glob) : false;
+}
+
+/**
* die_get_call_lineno - Get callsite line number of inline-function instance
* @in_die: a DIE of an inlined function instance
*
@@ -417,6 +433,43 @@
Dwarf_Die *die_mem;
};
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+ struct __addr_die_search_param *ad = data;
+ Dwarf_Addr addr = 0;
+
+ if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+ !dwarf_highpc(fn_die, &addr) &&
+ addr == ad->addr) {
+ memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+ return DWARF_CB_ABORT;
+ }
+ return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ Dwarf_Die *die_mem)
+{
+ struct __addr_die_search_param ad;
+ ad.addr = addr;
+ ad.die_mem = die_mem;
+ /* dwarf_getscopes can't find subprogram. */
+ if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+ return NULL;
+ else
+ return die_mem;
+}
+
/* die_find callback for non-inlined function search */
static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
{
@@ -832,19 +885,17 @@
/**
* die_get_typename - Get the name of given variable DIE
* @vr_die: a variable DIE
- * @buf: a buffer for result type name
- * @len: a max-length of @buf
+ * @buf: a strbuf for result type name
*
- * Get the name of @vr_die and stores it to @buf. Return the actual length
- * of type name if succeeded. Return -E2BIG if @len is not enough long, and
- * Return -ENOENT if failed to find type name.
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
* Note that the result will stores typedef name if possible, and stores
* "*(function_type)" if the type is a function pointer.
*/
-int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
{
Dwarf_Die type;
- int tag, ret, ret2;
+ int tag, ret;
const char *tmp = "";
if (__die_get_real_type(vr_die, &type) == NULL)
@@ -855,8 +906,8 @@
tmp = "*";
else if (tag == DW_TAG_subroutine_type) {
/* Function pointer */
- ret = snprintf(buf, len, "(function_type)");
- return (ret >= len) ? -E2BIG : ret;
+ strbuf_addf(buf, "(function_type)");
+ return 0;
} else {
if (!dwarf_diename(&type))
return -ENOENT;
@@ -867,39 +918,156 @@
else if (tag == DW_TAG_enumeration_type)
tmp = "enum ";
/* Write a base name */
- ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
- return (ret >= len) ? -E2BIG : ret;
+ strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
+ return 0;
}
- ret = die_get_typename(&type, buf, len);
- if (ret > 0) {
- ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
- ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
- }
+ ret = die_get_typename(&type, buf);
+ if (ret == 0)
+ strbuf_addf(buf, "%s", tmp);
+
return ret;
}
/**
* die_get_varname - Get the name and type of given variable DIE
* @vr_die: a variable DIE
- * @buf: a buffer for type and variable name
- * @len: the max-length of @buf
+ * @buf: a strbuf for type and variable name
*
* Get the name and type of @vr_die and stores it in @buf as "type\tname".
*/
-int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
{
- int ret, ret2;
+ int ret;
- ret = die_get_typename(vr_die, buf, len);
+ ret = die_get_typename(vr_die, buf);
if (ret < 0) {
pr_debug("Failed to get type, make it unknown.\n");
- ret = snprintf(buf, len, "(unknown_type)");
+ strbuf_addf(buf, "(unknown_type)");
}
- if (ret > 0) {
- ret2 = snprintf(buf + ret, len - ret, "\t%s",
- dwarf_diename(vr_die));
- ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+
+ strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
+
+ return 0;
+}
+
+/**
+ * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for variable byte offset range
+ *
+ * Get the innermost scope range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+ struct strbuf *buf)
+{
+ Dwarf_Die *scopes;
+ int count;
+ size_t offset = 0;
+ Dwarf_Addr base;
+ Dwarf_Addr start, end;
+ Dwarf_Addr entry;
+ int ret;
+ bool first = true;
+ const char *name;
+
+ ret = dwarf_entrypc(sp_die, &entry);
+ if (ret)
+ return ret;
+
+ name = dwarf_diename(sp_die);
+ if (!name)
+ return -ENOENT;
+
+ count = dwarf_getscopes_die(vr_die, &scopes);
+
+ /* (*SCOPES)[1] is the DIE for the scope containing that scope */
+ if (count <= 1) {
+ ret = -EINVAL;
+ goto out;
}
+
+ while ((offset = dwarf_ranges(&scopes[1], offset, &base,
+ &start, &end)) > 0) {
+ start -= entry;
+ end -= entry;
+
+ if (first) {
+ strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+ name, start, end);
+ first = false;
+ } else {
+ strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+ start, end);
+ }
+ }
+
+ if (!first)
+ strbuf_addf(buf, "]>");
+
+out:
+ free(scopes);
return ret;
}
+/**
+ * die_get_var_range - Get byte offset range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for type and variable name and byte offset range
+ *
+ * Get the byte offset range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
+{
+ int ret = 0;
+ Dwarf_Addr base;
+ Dwarf_Addr start, end;
+ Dwarf_Addr entry;
+ Dwarf_Op *op;
+ size_t nops;
+ size_t offset = 0;
+ Dwarf_Attribute attr;
+ bool first = true;
+ const char *name;
+
+ ret = dwarf_entrypc(sp_die, &entry);
+ if (ret)
+ return ret;
+
+ name = dwarf_diename(sp_die);
+ if (!name)
+ return -ENOENT;
+
+ if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+ return -EINVAL;
+
+ while ((offset = dwarf_getlocations(
+ &attr, offset, &base,
+ &start, &end, &op, &nops)) > 0) {
+ if (start == 0) {
+ /* Single Location Descriptions */
+ ret = die_get_var_innermost_scope(sp_die, vr_die, buf);
+ return ret;
+ }
+
+ /* Location Lists */
+ start -= entry;
+ end -= entry;
+ if (first) {
+ strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+ name, start, end);
+ first = false;
+ } else {
+ strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+ start, end);
+ }
+ }
+
+ if (!first)
+ strbuf_addf(buf, "]>");
+
+ return ret;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index af7dbcd..c42ec36 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -47,6 +47,9 @@
/* Compare diename and tname */
extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
+/* Matching diename with glob pattern */
+extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+
/* Get callsite line number of inline-function instance */
extern int die_get_call_lineno(Dwarf_Die *in_die);
@@ -82,6 +85,10 @@
extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ Dwarf_Die *die_mem);
+
/* Search the top inlined function including given address */
extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
@@ -114,8 +121,10 @@
Dwarf_Die *die_mem);
/* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
/* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+ struct strbuf *buf);
#endif
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
index 275b0ee..7405123 100644
--- a/tools/perf/util/environment.c
+++ b/tools/perf/util/environment.c
@@ -5,5 +5,4 @@
*/
#include "cache.h"
-const char *pager_program;
int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ff866c4..a513a51 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -23,12 +23,17 @@
[PERF_RECORD_FORK] = "FORK",
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
+ [PERF_RECORD_AUX] = "AUX",
+ [PERF_RECORD_ITRACE_START] = "ITRACE_START",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
[PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
+ [PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
+ [PERF_RECORD_AUXTRACE] = "AUXTRACE",
+ [PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR",
};
const char *perf_event__name(unsigned int id)
@@ -692,6 +697,22 @@
return machine__process_lost_event(machine, event, sample);
}
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_aux_event(machine, event);
+}
+
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_itrace_start_event(machine, event);
+}
+
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -755,6 +776,21 @@
return machine__process_exit_event(machine, event, sample);
}
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+ event->aux.aux_offset, event->aux.aux_size,
+ event->aux.flags,
+ event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+ event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " pid: %u tid: %u\n",
+ event->itrace_start.pid, event->itrace_start.tid);
+}
+
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -774,6 +810,12 @@
case PERF_RECORD_MMAP2:
ret += perf_event__fprintf_mmap2(event, fp);
break;
+ case PERF_RECORD_AUX:
+ ret += perf_event__fprintf_aux(event, fp);
+ break;
+ case PERF_RECORD_ITRACE_START:
+ ret += perf_event__fprintf_itrace_start(event, fp);
+ break;
default:
ret += fprintf(fp, "\n");
}
@@ -877,6 +919,10 @@
al->sym = NULL;
}
+/*
+ * Callers need to drop the reference to al->thread, obtained in
+ * machine__findnew_thread()
+ */
int perf_event__preprocess_sample(const union perf_event *event,
struct machine *machine,
struct addr_location *al,
@@ -937,6 +983,17 @@
return 0;
}
+/*
+ * The preprocess_sample method will return with reference counts for the
+ * in it, when done using (and perhaps getting ref counts if needing to
+ * keep a pointer to one of those entries) it must be paired with
+ * addr_location__put(), so that the refcounts can be decremented.
+ */
+void addr_location__put(struct addr_location *al)
+{
+ thread__zput(al->thread);
+}
+
bool is_bts_event(struct perf_event_attr *attr)
{
return attr->type == PERF_TYPE_HARDWARE &&
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 09b9e8d..97179ab 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -157,6 +157,8 @@
PERF_IP_FLAG_IN_TX = 1ULL << 10,
};
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
#define PERF_BRANCH_MASK (\
PERF_IP_FLAG_BRANCH |\
PERF_IP_FLAG_CALL |\
@@ -215,9 +217,17 @@
PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_FINISHED_ROUND = 68,
PERF_RECORD_ID_INDEX = 69,
+ PERF_RECORD_AUXTRACE_INFO = 70,
+ PERF_RECORD_AUXTRACE = 71,
+ PERF_RECORD_AUXTRACE_ERROR = 72,
PERF_RECORD_HEADER_MAX
};
+enum auxtrace_error_type {
+ PERF_AUXTRACE_ERROR_ITRACE = 1,
+ PERF_AUXTRACE_ERROR_MAX
+};
+
/*
* The kernel collects the number of events it couldn't send in a stretch and
* when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -242,6 +252,7 @@
u32 nr_invalid_chains;
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
+ u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
};
struct attr_event {
@@ -280,6 +291,50 @@
struct id_index_entry entries[0];
};
+struct auxtrace_info_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 reserved__; /* For alignment */
+ u64 priv[];
+};
+
+struct auxtrace_event {
+ struct perf_event_header header;
+ u64 size;
+ u64 offset;
+ u64 reference;
+ u32 idx;
+ u32 tid;
+ u32 cpu;
+ u32 reserved__; /* For alignment */
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 code;
+ u32 cpu;
+ u32 pid;
+ u32 tid;
+ u32 reserved__; /* For alignment */
+ u64 ip;
+ char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+struct aux_event {
+ struct perf_event_header header;
+ u64 aux_offset;
+ u64 aux_size;
+ u64 flags;
+};
+
+struct itrace_start_event {
+ struct perf_event_header header;
+ u32 pid, tid;
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -295,6 +350,11 @@
struct tracing_data_event tracing_data;
struct build_id_event build_id;
struct id_index_event id_index;
+ struct auxtrace_info_event auxtrace_info;
+ struct auxtrace_event auxtrace;
+ struct auxtrace_error_event auxtrace_error;
+ struct aux_event aux;
+ struct itrace_start_event itrace_start;
};
void perf_event__print_totals(void);
@@ -330,6 +390,14 @@
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -358,6 +426,8 @@
struct addr_location *al,
struct perf_sample *sample);
+void addr_location__put(struct addr_location *al);
+
struct thread;
bool is_bts_event(struct perf_event_attr *attr);
@@ -387,6 +457,8 @@
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 080be93..dc1dc2c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -695,19 +695,19 @@
static bool perf_mmap__empty(struct perf_mmap *md)
{
- return perf_mmap__read_head(md) == md->prev;
+ return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
}
static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
{
- ++evlist->mmap[idx].refcnt;
+ atomic_inc(&evlist->mmap[idx].refcnt);
}
static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
{
- BUG_ON(evlist->mmap[idx].refcnt == 0);
+ BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
- if (--evlist->mmap[idx].refcnt == 0)
+ if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
__perf_evlist__munmap(evlist, idx);
}
@@ -721,17 +721,46 @@
perf_mmap__write_tail(md, old);
}
- if (md->refcnt == 1 && perf_mmap__empty(md))
+ if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
perf_evlist__mmap_put(evlist, idx);
}
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ void *userpg __maybe_unused,
+ int fd __maybe_unused)
+{
+ return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ off_t auxtrace_offset __maybe_unused,
+ unsigned int auxtrace_pages __maybe_unused,
+ bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ int idx __maybe_unused,
+ bool per_cpu __maybe_unused)
+{
+}
+
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
{
if (evlist->mmap[idx].base != NULL) {
munmap(evlist->mmap[idx].base, evlist->mmap_len);
evlist->mmap[idx].base = NULL;
- evlist->mmap[idx].refcnt = 0;
+ atomic_set(&evlist->mmap[idx].refcnt, 0);
}
+ auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
}
void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -759,6 +788,7 @@
struct mmap_params {
int prot;
int mask;
+ struct auxtrace_mmap_params auxtrace_mp;
};
static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
@@ -777,7 +807,7 @@
* evlist layer can't just drop it when filtering events in
* perf_evlist__filter_pollfd().
*/
- evlist->mmap[idx].refcnt = 2;
+ atomic_set(&evlist->mmap[idx].refcnt, 2);
evlist->mmap[idx].prev = 0;
evlist->mmap[idx].mask = mp->mask;
evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -789,6 +819,10 @@
return -1;
}
+ if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+ &mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+ return -1;
+
return 0;
}
@@ -853,6 +887,9 @@
for (cpu = 0; cpu < nr_cpus; cpu++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+ true);
+
for (thread = 0; thread < nr_threads; thread++) {
if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
thread, &output))
@@ -878,6 +915,9 @@
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+ false);
+
if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
&output))
goto out_unmap;
@@ -960,10 +1000,8 @@
return pages;
}
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
- int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
{
- unsigned int *mmap_pages = opt->value;
unsigned long max = UINT_MAX;
long pages;
@@ -980,20 +1018,32 @@
return 0;
}
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
/**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
* @evlist: list of events
* @pages: map length in pages
* @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
*
* If @overwrite is %false the user needs to signal event consumption using
* perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this
* automatically.
*
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
* Return: %0 on success, negative error code otherwise.
*/
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
- bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
@@ -1013,6 +1063,9 @@
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
+ auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+ auxtrace_pages, auxtrace_overwrite);
+
evlist__for_each(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
@@ -1026,6 +1079,12 @@
return perf_evlist__mmap_per_cpu(evlist, &mp);
}
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite)
+{
+ return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
{
evlist->threads = thread_map__new_str(target->pid, target->tid,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b5cce95..955bf31 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
#ifndef __PERF_EVLIST_H
#define __PERF_EVLIST_H 1
+#include <linux/atomic.h>
#include <linux/list.h>
#include <api/fd/array.h>
#include <stdio.h>
@@ -8,6 +9,7 @@
#include "event.h"
#include "evsel.h"
#include "util.h"
+#include "auxtrace.h"
#include <unistd.h>
struct pollfd;
@@ -26,8 +28,9 @@
struct perf_mmap {
void *base;
int mask;
- int refcnt;
+ atomic_t refcnt;
u64 prev;
+ struct auxtrace_mmap auxtrace_mmap;
char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
};
@@ -37,6 +40,7 @@
int nr_entries;
int nr_groups;
int nr_mmaps;
+ bool overwrite;
size_t mmap_len;
int id_pos;
int is_pos;
@@ -45,7 +49,6 @@
int cork_fd;
pid_t pid;
} workload;
- bool overwrite;
struct fdarray pollfd;
struct perf_mmap *mmap;
struct thread_map *threads;
@@ -122,10 +125,14 @@
struct option;
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8..c886b9f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1121,6 +1121,7 @@
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
PRINT_ATTRf(sample_regs_intr, p_hex);
+ PRINT_ATTRf(aux_watermark, p_unsigned);
return ret;
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e486151..21ec082 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -73,7 +73,6 @@
char *name;
double scale;
const char *unit;
- bool snapshot;
struct event_format *tp_format;
union {
void *priv;
@@ -86,6 +85,7 @@
unsigned int sample_size;
int id_pos;
int is_pos;
+ bool snapshot;
bool supported;
bool needs_swap;
bool no_aux_samples;
@@ -93,11 +93,11 @@
bool system_wide;
bool tracking;
bool per_pkg;
- unsigned long *per_pkg_mask;
/* parse modifier helper */
int exclude_GH;
int nr_members;
int sample_read;
+ unsigned long *per_pkg_mask;
struct perf_evsel *leader;
char *group_name;
};
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 918fd8a..3f0d809 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,6 +869,20 @@
return 0;
}
+static int write_auxtrace(int fd, struct perf_header *h,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ struct perf_session *session;
+ int err;
+
+ session = container_of(h, struct perf_session, header);
+
+ err = auxtrace_index__write(fd, &session->auxtrace_index);
+ if (err < 0)
+ pr_err("Failed to write auxtrace index\n");
+ return err;
+}
+
static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@@ -1151,6 +1165,12 @@
fprintf(fp, "# contains samples with branch stack\n");
}
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+ int fd __maybe_unused, FILE *fp)
+{
+ fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@@ -1821,6 +1841,22 @@
return ret;
}
+static int process_auxtrace(struct perf_file_section *section,
+ struct perf_header *ph, int fd,
+ void *data __maybe_unused)
+{
+ struct perf_session *session;
+ int err;
+
+ session = container_of(ph, struct perf_session, header);
+
+ err = auxtrace_index__process(fd, section->size, session,
+ ph->needs_swap);
+ if (err < 0)
+ pr_err("Failed to process auxtrace index\n");
+ return err;
+}
+
struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1861,6 +1897,7 @@
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
FEAT_OPP(HEADER_GROUP_DESC, group_desc),
+ FEAT_OPP(HEADER_AUXTRACE, auxtrace),
};
struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb90ac..d4d5796 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -30,6 +30,7 @@
HEADER_BRANCH_STACK,
HEADER_PMU_MAPPINGS,
HEADER_GROUP_DESC,
+ HEADER_AUXTRACE,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cc22b91..3387706 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1163,7 +1163,7 @@
return;
/* force fold unfiltered entry for simplicity */
- h->ms.unfolded = false;
+ h->unfolded = false;
h->row_offset = 0;
h->nr_rows = 0;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527e032..daa5591 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -14,6 +14,8 @@
#include "unwind.h"
#include "linux/hash.h"
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
+
static void dsos__init(struct dsos *dsos)
{
INIT_LIST_HEAD(&dsos->head);
@@ -28,6 +30,7 @@
dsos__init(&machine->kernel_dsos);
machine->threads = RB_ROOT;
+ pthread_rwlock_init(&machine->threads_lock, NULL);
INIT_LIST_HEAD(&machine->dead_threads);
machine->last_match = NULL;
@@ -54,6 +57,7 @@
snprintf(comm, sizeof(comm), "[guest/%d]", pid);
thread__set_comm(thread, comm, 0);
+ thread__put(thread);
}
machine->current_tid = NULL;
@@ -91,14 +95,17 @@
void machine__delete_threads(struct machine *machine)
{
- struct rb_node *nd = rb_first(&machine->threads);
+ struct rb_node *nd;
+ pthread_rwlock_wrlock(&machine->threads_lock);
+ nd = rb_first(&machine->threads);
while (nd) {
struct thread *t = rb_entry(nd, struct thread, rb_node);
nd = rb_next(nd);
- machine__remove_thread(machine, t);
+ __machine__remove_thread(machine, t, false);
}
+ pthread_rwlock_unlock(&machine->threads_lock);
}
void machine__exit(struct machine *machine)
@@ -109,6 +116,7 @@
vdso__exit(machine);
zfree(&machine->root_dir);
zfree(&machine->current_tid);
+ pthread_rwlock_destroy(&machine->threads_lock);
}
void machine__delete(struct machine *machine)
@@ -303,7 +311,7 @@
if (th->pid_ == th->tid)
return;
- leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+ leader = __machine__findnew_thread(machine, th->pid_, th->pid_);
if (!leader)
goto out_err;
@@ -336,9 +344,9 @@
pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
}
-static struct thread *__machine__findnew_thread(struct machine *machine,
- pid_t pid, pid_t tid,
- bool create)
+static struct thread *____machine__findnew_thread(struct machine *machine,
+ pid_t pid, pid_t tid,
+ bool create)
{
struct rb_node **p = &machine->threads.rb_node;
struct rb_node *parent = NULL;
@@ -356,7 +364,7 @@
return th;
}
- thread__zput(machine->last_match);
+ machine->last_match = NULL;
}
while (*p != NULL) {
@@ -364,7 +372,7 @@
th = rb_entry(parent, struct thread, rb_node);
if (th->tid == tid) {
- machine->last_match = thread__get(th);
+ machine->last_match = th;
machine__update_thread_pid(machine, th, pid);
return th;
}
@@ -393,6 +401,7 @@
*/
if (thread__init_map_groups(th, machine)) {
rb_erase(&th->rb_node, &machine->threads);
+ RB_CLEAR_NODE(&th->rb_node);
thread__delete(th);
return NULL;
}
@@ -400,22 +409,36 @@
* It is now in the rbtree, get a ref
*/
thread__get(th);
- machine->last_match = thread__get(th);
+ machine->last_match = th;
}
return th;
}
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
+{
+ return ____machine__findnew_thread(machine, pid, tid, true);
+}
+
struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
pid_t tid)
{
- return __machine__findnew_thread(machine, pid, tid, true);
+ struct thread *th;
+
+ pthread_rwlock_wrlock(&machine->threads_lock);
+ th = thread__get(__machine__findnew_thread(machine, pid, tid));
+ pthread_rwlock_unlock(&machine->threads_lock);
+ return th;
}
struct thread *machine__find_thread(struct machine *machine, pid_t pid,
pid_t tid)
{
- return __machine__findnew_thread(machine, pid, tid, false);
+ struct thread *th;
+ pthread_rwlock_rdlock(&machine->threads_lock);
+ th = thread__get(____machine__findnew_thread(machine, pid, tid, false));
+ pthread_rwlock_unlock(&machine->threads_lock);
+ return th;
}
struct comm *machine__thread_exec_comm(struct machine *machine,
@@ -434,6 +457,7 @@
event->comm.pid,
event->comm.tid);
bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+ int err = 0;
if (exec)
machine->comm_exec = true;
@@ -444,10 +468,12 @@
if (thread == NULL ||
__thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
- return -1;
+ err = -1;
}
- return 0;
+ thread__put(thread);
+
+ return err;
}
int machine__process_lost_event(struct machine *machine __maybe_unused,
@@ -486,6 +512,22 @@
return dso;
}
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_aux(event, stdout);
+ return 0;
+}
+
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_itrace_start(event, stdout);
+ return 0;
+}
+
struct map *machine__new_module(struct machine *machine, u64 start,
const char *filename)
{
@@ -575,12 +617,16 @@
size_t ret = 0;
struct rb_node *nd;
+ pthread_rwlock_rdlock(&machine->threads_lock);
+
for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
struct thread *pos = rb_entry(nd, struct thread, rb_node);
ret += thread__fprintf(pos, fp);
}
+ pthread_rwlock_unlock(&machine->threads_lock);
+
return ret;
}
@@ -1197,11 +1243,14 @@
event->mmap2.filename, type, thread);
if (map == NULL)
- goto out_problem;
+ goto out_problem_map;
thread__insert_map(thread, map);
+ thread__put(thread);
return 0;
+out_problem_map:
+ thread__put(thread);
out_problem:
dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
return 0;
@@ -1244,31 +1293,45 @@
type, thread);
if (map == NULL)
- goto out_problem;
+ goto out_problem_map;
thread__insert_map(thread, map);
+ thread__put(thread);
return 0;
+out_problem_map:
+ thread__put(thread);
out_problem:
dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
return 0;
}
-void machine__remove_thread(struct machine *machine, struct thread *th)
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
{
if (machine->last_match == th)
- thread__zput(machine->last_match);
+ machine->last_match = NULL;
+ BUG_ON(atomic_read(&th->refcnt) == 0);
+ if (lock)
+ pthread_rwlock_wrlock(&machine->threads_lock);
rb_erase(&th->rb_node, &machine->threads);
+ RB_CLEAR_NODE(&th->rb_node);
/*
* Move it first to the dead_threads list, then drop the reference,
* if this is the last reference, then the thread__delete destructor
* will be called and we will remove it from the dead_threads list.
*/
list_add_tail(&th->node, &machine->dead_threads);
+ if (lock)
+ pthread_rwlock_unlock(&machine->threads_lock);
thread__put(th);
}
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+ return __machine__remove_thread(machine, th, true);
+}
+
int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
{
@@ -1278,10 +1341,13 @@
struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
+ int err = 0;
/* if a thread currently exists for the thread id remove it */
- if (thread != NULL)
+ if (thread != NULL) {
machine__remove_thread(machine, thread);
+ thread__put(thread);
+ }
thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
@@ -1291,10 +1357,12 @@
if (thread == NULL || parent == NULL ||
thread__fork(thread, parent, sample->time) < 0) {
dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
- return -1;
+ err = -1;
}
+ thread__put(thread);
+ thread__put(parent);
- return 0;
+ return err;
}
int machine__process_exit_event(struct machine *machine, union perf_event *event,
@@ -1307,8 +1375,10 @@
if (dump_trace)
perf_event__fprintf_task(event, stdout);
- if (thread != NULL)
+ if (thread != NULL) {
thread__exited(thread);
+ thread__put(thread);
+ }
return 0;
}
@@ -1331,6 +1401,11 @@
ret = machine__process_exit_event(machine, event, sample); break;
case PERF_RECORD_LOST:
ret = machine__process_lost_event(machine, event, sample); break;
+ case PERF_RECORD_AUX:
+ ret = machine__process_aux_event(machine, event); break;
+ case PERF_RECORD_ITRACE_START:
+ ret = machine__process_itrace_start_event(machine, event);
+ break;
default:
ret = -1;
break;
@@ -1820,6 +1895,7 @@
return -ENOMEM;
thread->cpu = cpu;
+ thread__put(thread);
return 0;
}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 6d64ced..c7963c6 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -30,6 +30,7 @@
bool comm_exec;
char *root_dir;
struct rb_root threads;
+ pthread_rwlock_t threads_lock;
struct list_head dead_threads;
struct thread *last_match;
struct vdso_info *vdso_info;
@@ -81,6 +82,10 @@
struct perf_sample *sample);
int machine__process_lost_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+ union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+ union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
@@ -147,8 +152,8 @@
return machine ? machine->pid == HOST_KERNEL_ID : false;
}
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
- pid_t tid);
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
size_t machine__fprintf(struct machine *machine, FILE *fp);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a14f08f..2d20c5f 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -292,6 +292,11 @@
return 0;
}
+int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+ return strcmp(namea, nameb);
+}
+
struct symbol *map__find_symbol(struct map *map, u64 addr,
symbol_filter_t filter)
{
@@ -421,7 +426,7 @@
INIT_LIST_HEAD(&mg->removed_maps[i]);
}
mg->machine = machine;
- mg->refcnt = 1;
+ atomic_set(&mg->refcnt, 1);
}
static void maps__delete(struct rb_root *maps)
@@ -489,7 +494,7 @@
void map_groups__put(struct map_groups *mg)
{
- if (--mg->refcnt == 0)
+ if (mg && atomic_dec_and_test(&mg->refcnt))
map_groups__delete(mg);
}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ec19c59..7f39217 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,6 +1,7 @@
#ifndef __PERF_MAP_H
#define __PERF_MAP_H
+#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/rbtree.h>
@@ -61,7 +62,7 @@
struct rb_root maps[MAP__NR_TYPES];
struct list_head removed_maps[MAP__NR_TYPES];
struct machine *machine;
- int refcnt;
+ atomic_t refcnt;
};
struct map_groups *map_groups__new(struct machine *machine);
@@ -70,7 +71,8 @@
static inline struct map_groups *map_groups__get(struct map_groups *mg)
{
- ++mg->refcnt;
+ if (mg)
+ atomic_inc(&mg->refcnt);
return mg;
}
@@ -124,7 +126,7 @@
*/
#define __map__for_each_symbol_by_name(map, sym_name, pos, filter) \
for (pos = map__find_symbol_by_name(map, sym_name, filter); \
- pos && strcmp(pos->name, sym_name) == 0; \
+ pos && arch__compare_symbol_names(pos->name, sym_name) == 0; \
pos = symbol__next_by_name(pos))
#define map__for_each_symbol_by_name(map, sym_name, pos) \
@@ -132,6 +134,7 @@
typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
+int arch__compare_symbol_names(const char *namea, const char *nameb);
void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso);
struct map *map__new(struct machine *machine, u64 start, u64 len,
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 31ee02d..53ef006 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -50,11 +50,6 @@
if (!isatty(1))
return;
- if (!pager) {
- if (!pager_program)
- perf_config(perf_default_config, NULL);
- pager = pager_program;
- }
if (!pager)
pager = getenv("PAGER");
if (!(pager || access("/usr/bin/pager", X_OK)))
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index be06553..80a50fd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -17,6 +17,7 @@
#include "parse-events-flex.h"
#include "pmu.h"
#include "thread_map.h"
+#include "asm/bug.h"
#define MAX_NAME_LEN 100
@@ -24,6 +25,12 @@
extern int parse_events_debug;
#endif
int parse_events_parse(void *data, void *scanner);
+int parse_events_term__num(struct parse_events_term **term,
+ int type_term, char *config, u64 num,
+ YYLTYPE *loc_term, YYLTYPE *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+ int type_term, char *config, char *str,
+ YYLTYPE *loc_term, YYLTYPE *loc_val);
static struct perf_pmu_event_symbol *perf_pmu_events_list;
/*
@@ -538,16 +545,40 @@
return add_event(list, idx, &attr, NULL);
}
-static int config_term(struct perf_event_attr *attr,
- struct parse_events_term *term)
+static int check_type_val(struct parse_events_term *term,
+ struct parse_events_error *err,
+ int type)
{
-#define CHECK_TYPE_VAL(type) \
-do { \
- if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val) \
- return -EINVAL; \
+ if (type == term->type_val)
+ return 0;
+
+ if (err) {
+ err->idx = term->err_val;
+ if (type == PARSE_EVENTS__TERM_TYPE_NUM)
+ err->str = strdup("expected numeric value");
+ else
+ err->str = strdup("expected string value");
+ }
+ return -EINVAL;
+}
+
+static int config_term(struct perf_event_attr *attr,
+ struct parse_events_term *term,
+ struct parse_events_error *err)
+{
+#define CHECK_TYPE_VAL(type) \
+do { \
+ if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \
+ return -EINVAL; \
} while (0)
switch (term->type_term) {
+ case PARSE_EVENTS__TERM_TYPE_USER:
+ /*
+ * Always succeed for sysfs terms, as we dont know
+ * at this point what type they need to have.
+ */
+ return 0;
case PARSE_EVENTS__TERM_TYPE_CONFIG:
CHECK_TYPE_VAL(NUM);
attr->config = term->val.num;
@@ -582,18 +613,20 @@
}
static int config_attr(struct perf_event_attr *attr,
- struct list_head *head, int fail)
+ struct list_head *head,
+ struct parse_events_error *err)
{
struct parse_events_term *term;
list_for_each_entry(term, head, list)
- if (config_term(attr, term) && fail)
+ if (config_term(attr, term, err))
return -EINVAL;
return 0;
}
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+ struct list_head *list,
u32 type, u64 config,
struct list_head *head_config)
{
@@ -604,10 +637,10 @@
attr.config = config;
if (head_config &&
- config_attr(&attr, head_config, 1))
+ config_attr(&attr, head_config, data->error))
return -EINVAL;
- return add_event(list, idx, &attr, NULL);
+ return add_event(list, &data->idx, &attr, NULL);
}
static int parse_events__is_name_term(struct parse_events_term *term)
@@ -626,8 +659,9 @@
return NULL;
}
-int parse_events_add_pmu(struct list_head *list, int *idx,
- char *name, struct list_head *head_config)
+int parse_events_add_pmu(struct parse_events_evlist *data,
+ struct list_head *list, char *name,
+ struct list_head *head_config)
{
struct perf_event_attr attr;
struct perf_pmu_info info;
@@ -647,7 +681,7 @@
if (!head_config) {
attr.type = pmu->type;
- evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+ evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus);
return evsel ? 0 : -ENOMEM;
}
@@ -658,13 +692,14 @@
* Configure hardcoded terms first, no need to check
* return value when called with fail == 0 ;)
*/
- config_attr(&attr, head_config, 0);
-
- if (perf_pmu__config(pmu, &attr, head_config))
+ if (config_attr(&attr, head_config, data->error))
return -EINVAL;
- evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
- pmu->cpus);
+ if (perf_pmu__config(pmu, &attr, head_config, data->error))
+ return -EINVAL;
+
+ evsel = __add_event(list, &data->idx, &attr,
+ pmu_event_name(head_config), pmu->cpus);
if (evsel) {
evsel->unit = info.unit;
evsel->scale = info.scale;
@@ -1019,11 +1054,13 @@
return ret;
}
-int parse_events(struct perf_evlist *evlist, const char *str)
+int parse_events(struct perf_evlist *evlist, const char *str,
+ struct parse_events_error *err)
{
struct parse_events_evlist data = {
- .list = LIST_HEAD_INIT(data.list),
- .idx = evlist->nr_entries,
+ .list = LIST_HEAD_INIT(data.list),
+ .idx = evlist->nr_entries,
+ .error = err,
};
int ret;
@@ -1044,16 +1081,87 @@
return ret;
}
+#define MAX_WIDTH 1000
+static int get_term_width(void)
+{
+ struct winsize ws;
+
+ get_term_dimensions(&ws);
+ return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
+}
+
+static void parse_events_print_error(struct parse_events_error *err,
+ const char *event)
+{
+ const char *str = "invalid or unsupported event: ";
+ char _buf[MAX_WIDTH];
+ char *buf = (char *) event;
+ int idx = 0;
+
+ if (err->str) {
+ /* -2 for extra '' in the final fprintf */
+ int width = get_term_width() - 2;
+ int len_event = strlen(event);
+ int len_str, max_len, cut = 0;
+
+ /*
+ * Maximum error index indent, we will cut
+ * the event string if it's bigger.
+ */
+ int max_err_idx = 10;
+
+ /*
+ * Let's be specific with the message when
+ * we have the precise error.
+ */
+ str = "event syntax error: ";
+ len_str = strlen(str);
+ max_len = width - len_str;
+
+ buf = _buf;
+
+ /* We're cutting from the beggining. */
+ if (err->idx > max_err_idx)
+ cut = err->idx - max_err_idx;
+
+ strncpy(buf, event + cut, max_len);
+
+ /* Mark cut parts with '..' on both sides. */
+ if (cut)
+ buf[0] = buf[1] = '.';
+
+ if ((len_event - cut) > max_len) {
+ buf[max_len - 1] = buf[max_len - 2] = '.';
+ buf[max_len] = 0;
+ }
+
+ idx = len_str + err->idx - cut;
+ }
+
+ fprintf(stderr, "%s'%s'\n", str, buf);
+ if (idx) {
+ fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
+ if (err->help)
+ fprintf(stderr, "\n%s\n", err->help);
+ free(err->str);
+ free(err->help);
+ }
+
+ fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+}
+
+#undef MAX_WIDTH
+
int parse_events_option(const struct option *opt, const char *str,
int unset __maybe_unused)
{
struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
- int ret = parse_events(evlist, str);
+ struct parse_events_error err = { .idx = 0, };
+ int ret = parse_events(evlist, str, &err);
- if (ret) {
- fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
- fprintf(stderr, "Run 'perf list' for a list of valid events\n");
- }
+ if (ret)
+ parse_events_print_error(&err, str);
+
return ret;
}
@@ -1460,7 +1568,7 @@
static int new_term(struct parse_events_term **_term, int type_val,
int type_term, char *config,
- char *str, u64 num)
+ char *str, u64 num, int err_term, int err_val)
{
struct parse_events_term *term;
@@ -1472,6 +1580,8 @@
term->type_val = type_val;
term->type_term = type_term;
term->config = config;
+ term->err_term = err_term;
+ term->err_val = err_val;
switch (type_val) {
case PARSE_EVENTS__TERM_TYPE_NUM:
@@ -1490,17 +1600,23 @@
}
int parse_events_term__num(struct parse_events_term **term,
- int type_term, char *config, u64 num)
+ int type_term, char *config, u64 num,
+ YYLTYPE *loc_term, YYLTYPE *loc_val)
{
return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
- config, NULL, num);
+ config, NULL, num,
+ loc_term ? loc_term->first_column : 0,
+ loc_val ? loc_val->first_column : 0);
}
int parse_events_term__str(struct parse_events_term **term,
- int type_term, char *config, char *str)
+ int type_term, char *config, char *str,
+ YYLTYPE *loc_term, YYLTYPE *loc_val)
{
return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
- config, str, 0);
+ config, str, 0,
+ loc_term ? loc_term->first_column : 0,
+ loc_val ? loc_val->first_column : 0);
}
int parse_events_term__sym_hw(struct parse_events_term **term,
@@ -1514,18 +1630,20 @@
if (config)
return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
PARSE_EVENTS__TERM_TYPE_USER, config,
- (char *) sym->symbol, 0);
+ (char *) sym->symbol, 0, 0, 0);
else
return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
PARSE_EVENTS__TERM_TYPE_USER,
- (char *) "event", (char *) sym->symbol, 0);
+ (char *) "event", (char *) sym->symbol,
+ 0, 0, 0);
}
int parse_events_term__clone(struct parse_events_term **new,
struct parse_events_term *term)
{
return new_term(new, term->type_val, term->type_term, term->config,
- term->val.str, term->val.num);
+ term->val.str, term->val.num,
+ term->err_term, term->err_val);
}
void parse_events__free_terms(struct list_head *terms)
@@ -1535,3 +1653,13 @@
list_for_each_entry_safe(term, h, terms, list)
free(term);
}
+
+void parse_events_evlist_error(struct parse_events_evlist *data,
+ int idx, const char *str)
+{
+ struct parse_events_error *err = data->error;
+
+ err->idx = idx;
+ err->str = strdup(str);
+ WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 52a2dda..e236f1b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -12,6 +12,7 @@
struct list_head;
struct perf_evsel;
struct perf_evlist;
+struct parse_events_error;
struct option;
@@ -29,7 +30,8 @@
extern int parse_events_option(const struct option *opt, const char *str,
int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str);
+extern int parse_events(struct perf_evlist *evlist, const char *str,
+ struct parse_events_error *error);
extern int parse_events_terms(struct list_head *terms, const char *str);
extern int parse_filter(const struct option *opt, const char *str, int unset);
@@ -72,12 +74,23 @@
int type_term;
struct list_head list;
bool used;
+
+ /* error string indexes for within parsed string */
+ int err_term;
+ int err_val;
+};
+
+struct parse_events_error {
+ int idx; /* index in the parsed string */
+ char *str; /* string to display at the index */
+ char *help; /* optional help string */
};
struct parse_events_evlist {
- struct list_head list;
- int idx;
- int nr_groups;
+ struct list_head list;
+ int idx;
+ int nr_groups;
+ struct parse_events_error *error;
};
struct parse_events_terms {
@@ -85,10 +98,6 @@
};
int parse_events__is_hardcoded_term(struct parse_events_term *term);
-int parse_events_term__num(struct parse_events_term **_term,
- int type_term, char *config, u64 num);
-int parse_events_term__str(struct parse_events_term **_term,
- int type_term, char *config, char *str);
int parse_events_term__sym_hw(struct parse_events_term **term,
char *config, unsigned idx);
int parse_events_term__clone(struct parse_events_term **new,
@@ -99,21 +108,24 @@
int parse_events_name(struct list_head *list, char *name);
int parse_events_add_tracepoint(struct list_head *list, int *idx,
char *sys, char *event);
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+ struct list_head *list,
u32 type, u64 config,
struct list_head *head_config);
int parse_events_add_cache(struct list_head *list, int *idx,
char *type, char *op_result1, char *op_result2);
int parse_events_add_breakpoint(struct list_head *list, int *idx,
void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct list_head *list, int *idx,
- char *pmu , struct list_head *head_config);
+int parse_events_add_pmu(struct parse_events_evlist *data,
+ struct list_head *list, char *name,
+ struct list_head *head_config);
enum perf_pmu_event_symbol_type
perf_pmu__parse_check(const char *name);
void parse_events__set_leader(char *name, struct list_head *list);
void parse_events_update_lists(struct list_head *list_event,
struct list_head *list_all);
-void parse_events_error(void *data, void *scanner, char const *msg);
+void parse_events_evlist_error(struct parse_events_evlist *data,
+ int idx, const char *str);
void print_events(const char *event_glob, bool name_only);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8895cf3..09e738f 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -3,6 +3,8 @@
%option bison-bridge
%option prefix="parse_events_"
%option stack
+%option bison-locations
+%option yylineno
%{
#include <errno.h>
@@ -51,6 +53,18 @@
return token;
}
+#define REWIND(__alloc) \
+do { \
+ YYSTYPE *__yylval = parse_events_get_lval(yyscanner); \
+ char *text = parse_events_get_text(yyscanner); \
+ \
+ if (__alloc) \
+ __yylval->str = strdup(text); \
+ \
+ yycolumn -= strlen(text); \
+ yyless(0); \
+} while (0)
+
static int pmu_str_check(yyscan_t scanner)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -85,6 +99,13 @@
return PE_TERM;
}
+#define YY_USER_ACTION \
+do { \
+ yylloc->last_column = yylloc->first_column; \
+ yylloc->first_column = yycolumn; \
+ yycolumn += yyleng; \
+} while (0);
+
%}
%x mem
@@ -119,6 +140,12 @@
if (start_token) {
parse_events_set_extra(NULL, yyscanner);
+ /*
+ * The flex parser does not init locations variable
+ * via the scan_string interface, so we need do the
+ * init in here.
+ */
+ yycolumn = 0;
return start_token;
}
}
@@ -127,24 +154,30 @@
<event>{
{group} {
- BEGIN(INITIAL); yyless(0);
+ BEGIN(INITIAL);
+ REWIND(0);
}
{event_pmu} |
{event} {
- str(yyscanner, PE_EVENT_NAME);
- BEGIN(INITIAL); yyless(0);
+ BEGIN(INITIAL);
+ REWIND(1);
return PE_EVENT_NAME;
}
. |
<<EOF>> {
- BEGIN(INITIAL); yyless(0);
+ BEGIN(INITIAL);
+ REWIND(0);
}
}
<config>{
+ /*
+ * Please update formats_error_string any time
+ * new static term is added.
+ */
config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 72def07..3d11e00 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -2,6 +2,7 @@
%parse-param {void *_data}
%parse-param {void *scanner}
%lex-param {void* scanner}
+%locations
%{
@@ -14,8 +15,6 @@
#include "parse-events.h"
#include "parse-events-bison.h"
-extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
-
#define ABORT_ON(val) \
do { \
if (val) \
@@ -208,7 +207,7 @@
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
+ ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
parse_events__free_terms($3);
$$ = list;
}
@@ -219,7 +218,7 @@
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+ ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
$$ = list;
}
|
@@ -232,11 +231,11 @@
ALLOC_LIST(head);
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1));
+ $1, 1, &@1, NULL));
list_add_tail(&term->list, head);
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+ ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
parse_events__free_terms(head);
$$ = list;
}
@@ -252,7 +251,7 @@
ALLOC_LIST(head);
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- &pmu_name, 1));
+ &pmu_name, 1, &@1, NULL));
list_add_tail(&term->list, head);
ALLOC_LIST(list);
@@ -275,8 +274,7 @@
int config = $1 & 255;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx,
- type, config, $3));
+ ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
parse_events__free_terms($3);
$$ = list;
}
@@ -289,8 +287,7 @@
int config = $1 & 255;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx,
- type, config, NULL));
+ ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
$$ = list;
}
@@ -389,7 +386,13 @@
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
+ if (parse_events_add_tracepoint(list, &data->idx, $1, $3)) {
+ struct parse_events_error *error = data->error;
+
+ error->idx = @1.first_column;
+ error->str = strdup("unknown tracepoint");
+ return -1;
+ }
$$ = list;
}
@@ -400,7 +403,7 @@
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
+ ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
$$ = list;
}
@@ -411,8 +414,7 @@
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx,
- PERF_TYPE_RAW, $1, NULL));
+ ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
$$ = list;
}
@@ -450,7 +452,7 @@
struct parse_events_term *term;
ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3));
+ $1, $3, &@1, &@3));
$$ = term;
}
|
@@ -459,7 +461,7 @@
struct parse_events_term *term;
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3));
+ $1, $3, &@1, &@3));
$$ = term;
}
|
@@ -477,7 +479,7 @@
struct parse_events_term *term;
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1));
+ $1, 1, &@1, NULL));
$$ = term;
}
|
@@ -494,7 +496,7 @@
{
struct parse_events_term *term;
- ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
+ ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3));
$$ = term;
}
|
@@ -502,7 +504,7 @@
{
struct parse_events_term *term;
- ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
+ ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
$$ = term;
}
|
@@ -510,7 +512,7 @@
{
struct parse_events_term *term;
- ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
+ ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
$$ = term;
}
@@ -520,7 +522,9 @@
%%
-void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+void parse_events_error(YYLTYPE *loc, void *data,
+ void *scanner __maybe_unused,
char const *msg __maybe_unused)
{
+ parse_events_evlist_error(data, loc->last_column, "parser error");
}
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 59561fd..367d8b8 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -123,6 +123,10 @@
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+ .value = check_vtype(v, const char **), (a), .help = (h), \
+ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 4841167..244c66f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -579,6 +579,38 @@
return -1;
}
+static char *formats_error_string(struct list_head *formats)
+{
+ struct perf_pmu_format *format;
+ char *err, *str;
+ static const char *static_terms = "config,config1,config2,name,period,branch_type\n";
+ unsigned i = 0;
+
+ if (!asprintf(&str, "valid terms:"))
+ return NULL;
+
+ /* sysfs exported terms */
+ list_for_each_entry(format, formats, list) {
+ char c = i++ ? ',' : ' ';
+
+ err = str;
+ if (!asprintf(&str, "%s%c%s", err, c, format->name))
+ goto fail;
+ free(err);
+ }
+
+ /* static terms */
+ err = str;
+ if (!asprintf(&str, "%s,%s", err, static_terms))
+ goto fail;
+
+ free(err);
+ return str;
+fail:
+ free(err);
+ return NULL;
+}
+
/*
* Setup one of config[12] attr members based on the
* user input data - term parameter.
@@ -587,7 +619,7 @@
struct perf_event_attr *attr,
struct parse_events_term *term,
struct list_head *head_terms,
- bool zero)
+ bool zero, struct parse_events_error *err)
{
struct perf_pmu_format *format;
__u64 *vp;
@@ -611,6 +643,11 @@
if (!format) {
if (verbose)
printf("Invalid event/parameter '%s'\n", term->config);
+ if (err) {
+ err->idx = term->err_term;
+ err->str = strdup("unknown term");
+ err->help = formats_error_string(formats);
+ }
return -EINVAL;
}
@@ -636,9 +673,14 @@
val = term->val.num;
else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
if (strcmp(term->val.str, "?")) {
- if (verbose)
+ if (verbose) {
pr_info("Invalid sysfs entry %s=%s\n",
term->config, term->val.str);
+ }
+ if (err) {
+ err->idx = term->err_val;
+ err->str = strdup("expected numeric value");
+ }
return -EINVAL;
}
@@ -654,12 +696,13 @@
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
struct list_head *head_terms,
- bool zero)
+ bool zero, struct parse_events_error *err)
{
struct parse_events_term *term;
list_for_each_entry(term, head_terms, list) {
- if (pmu_config_term(formats, attr, term, head_terms, zero))
+ if (pmu_config_term(formats, attr, term, head_terms,
+ zero, err))
return -EINVAL;
}
@@ -672,12 +715,14 @@
* 2) pmu format definitions - specified by pmu parameter
*/
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
- struct list_head *head_terms)
+ struct list_head *head_terms,
+ struct parse_events_error *err)
{
bool zero = !!pmu->default_config;
attr->type = pmu->type;
- return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
+ return perf_pmu__config_terms(&pmu->format, attr, head_terms,
+ zero, err);
}
static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b1249f..7b9c8cf 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -4,6 +4,7 @@
#include <linux/bitmap.h>
#include <linux/perf_event.h>
#include <stdbool.h>
+#include "parse-events.h"
enum {
PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -47,11 +48,12 @@
struct perf_pmu *perf_pmu__find(const char *name);
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
- struct list_head *head_terms);
+ struct list_head *head_terms,
+ struct parse_events_error *error);
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
struct list_head *head_terms,
- bool zero);
+ bool zero, struct parse_events_error *error);
int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
struct perf_pmu_info *info);
struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d05b77c..1faa1e6 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -51,6 +51,7 @@
#define PERFPROBE_GROUP "probe"
bool probe_event_dry_run; /* Dry run flag */
+struct probe_conf probe_conf;
#define semantic_error(msg ...) pr_err("Semantic error :" msg)
@@ -344,15 +345,14 @@
static int get_alternative_probe_event(struct debuginfo *dinfo,
struct perf_probe_event *pev,
- struct perf_probe_point *tmp,
- const char *target)
+ struct perf_probe_point *tmp)
{
int ret;
memcpy(tmp, &pev->point, sizeof(*tmp));
memset(&pev->point, 0, sizeof(pev->point));
ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
- target, pev->uprobes);
+ pev->target, pev->uprobes);
if (ret < 0)
memcpy(&pev->point, tmp, sizeof(*tmp));
@@ -557,8 +557,9 @@
bool uprobe)
{
struct ref_reloc_sym *reloc_sym;
+ u64 etext_addr;
char *tmp;
- int i;
+ int i, skipped = 0;
if (uprobe)
return add_exec_to_probe_trace_events(tevs, ntevs, module);
@@ -572,33 +573,45 @@
pr_warning("Relocated base symbol is not found!\n");
return -EINVAL;
}
+ /* Get the address of _etext for checking non-probable text symbol */
+ etext_addr = kernel_get_symbol_address_by_name("_etext", false);
for (i = 0; i < ntevs; i++) {
if (tevs[i].point.address && !tevs[i].point.retprobe) {
- tmp = strdup(reloc_sym->name);
- if (!tmp)
- return -ENOMEM;
- free(tevs[i].point.symbol);
+ /* If we found a wrong one, mark it by NULL symbol */
+ if (etext_addr < tevs[i].point.address) {
+ pr_warning("%s+%lu is out of .text, skip it.\n",
+ tevs[i].point.symbol, tevs[i].point.offset);
+ tmp = NULL;
+ skipped++;
+ } else {
+ tmp = strdup(reloc_sym->name);
+ if (!tmp)
+ return -ENOMEM;
+ }
+ /* If we have no realname, use symbol for it */
+ if (!tevs[i].point.realname)
+ tevs[i].point.realname = tevs[i].point.symbol;
+ else
+ free(tevs[i].point.symbol);
tevs[i].point.symbol = tmp;
tevs[i].point.offset = tevs[i].point.address -
reloc_sym->unrelocated_addr;
}
}
- return 0;
+ return skipped;
}
/* Try to find perf_probe_event with debuginfo */
static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs, const char *target)
+ struct probe_trace_event **tevs)
{
bool need_dwarf = perf_probe_event_need_dwarf(pev);
struct perf_probe_point tmp;
struct debuginfo *dinfo;
int ntevs, ret = 0;
- dinfo = open_debuginfo(target, !need_dwarf);
-
+ dinfo = open_debuginfo(pev->target, !need_dwarf);
if (!dinfo) {
if (need_dwarf)
return -ENOENT;
@@ -608,13 +621,12 @@
pr_debug("Try to find probe point from debuginfo.\n");
/* Searching trace events corresponding to a probe event */
- ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
+ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
if (ntevs == 0) { /* Not found, retry with an alternative */
- ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+ ret = get_alternative_probe_event(dinfo, pev, &tmp);
if (!ret) {
- ntevs = debuginfo__find_trace_events(dinfo, pev,
- tevs, max_tevs);
+ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
/*
* Write back to the original probe_event for
* setting appropriate (user given) event name
@@ -629,12 +641,15 @@
if (ntevs > 0) { /* Succeeded to find trace events */
pr_debug("Found %d probe_trace_events.\n", ntevs);
ret = post_process_probe_trace_events(*tevs, ntevs,
- target, pev->uprobes);
- if (ret < 0) {
+ pev->target, pev->uprobes);
+ if (ret < 0 || ret == ntevs) {
clear_probe_trace_events(*tevs, ntevs);
zfree(tevs);
}
- return ret < 0 ? ret : ntevs;
+ if (ret != ntevs)
+ return ret < 0 ? ret : ntevs;
+ ntevs = 0;
+ /* Fall through */
}
if (ntevs == 0) { /* No error but failed to find probe point. */
@@ -809,8 +824,7 @@
static int show_available_vars_at(struct debuginfo *dinfo,
struct perf_probe_event *pev,
- int max_vls, struct strfilter *_filter,
- bool externs, const char *target)
+ struct strfilter *_filter)
{
char *buf;
int ret, i, nvars;
@@ -824,13 +838,12 @@
return -EINVAL;
pr_debug("Searching variables at %s\n", buf);
- ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
- max_vls, externs);
+ ret = debuginfo__find_available_vars_at(dinfo, pev, &vls);
if (!ret) { /* Not found, retry with an alternative */
- ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+ ret = get_alternative_probe_event(dinfo, pev, &tmp);
if (!ret) {
ret = debuginfo__find_available_vars_at(dinfo, pev,
- &vls, max_vls, externs);
+ &vls);
/* Release the old probe_point */
clear_perf_probe_point(&tmp);
}
@@ -877,8 +890,7 @@
/* Show available variables on given probe point */
int show_available_vars(struct perf_probe_event *pevs, int npevs,
- int max_vls, const char *module,
- struct strfilter *_filter, bool externs)
+ struct strfilter *_filter)
{
int i, ret = 0;
struct debuginfo *dinfo;
@@ -887,7 +899,7 @@
if (ret < 0)
return ret;
- dinfo = open_debuginfo(module, false);
+ dinfo = open_debuginfo(pevs->target, false);
if (!dinfo) {
ret = -ENOENT;
goto out;
@@ -896,8 +908,7 @@
setup_pager();
for (i = 0; i < npevs && ret >= 0; i++)
- ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
- externs, module);
+ ret = show_available_vars_at(dinfo, &pevs[i], _filter);
debuginfo__delete(dinfo);
out:
@@ -916,9 +927,7 @@
}
static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
- struct probe_trace_event **tevs __maybe_unused,
- int max_tevs __maybe_unused,
- const char *target __maybe_unused)
+ struct probe_trace_event **tevs __maybe_unused)
{
if (perf_probe_event_need_dwarf(pev)) {
pr_warning("Debuginfo-analysis is not supported.\n");
@@ -937,10 +946,8 @@
}
int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
- int npevs __maybe_unused, int max_vls __maybe_unused,
- const char *module __maybe_unused,
- struct strfilter *filter __maybe_unused,
- bool externs __maybe_unused)
+ int npevs __maybe_unused,
+ struct strfilter *filter __maybe_unused)
{
pr_warning("Debuginfo-analysis is not supported.\n");
return -ENOSYS;
@@ -980,6 +987,18 @@
return 0;
}
+/* Check the name is good for event, group or function */
+static bool is_c_func_name(const char *name)
+{
+ if (!isalpha(*name) && *name != '_')
+ return false;
+ while (*++name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return false;
+ }
+ return true;
+}
+
/*
* Stuff 'lr' according to the line range described by 'arg'.
* The line range syntax is described by:
@@ -1048,10 +1067,15 @@
goto err;
}
lr->function = name;
- } else if (strchr(name, '.'))
+ } else if (strchr(name, '/') || strchr(name, '.'))
lr->file = name;
- else
+ else if (is_c_func_name(name))/* We reuse it for checking funcname */
lr->function = name;
+ else { /* Invalid name */
+ semantic_error("'%s' is not a valid function name.\n", name);
+ err = -EINVAL;
+ goto err;
+ }
return 0;
err:
@@ -1059,24 +1083,13 @@
return err;
}
-/* Check the name is good for event/group */
-static bool check_event_name(const char *name)
-{
- if (!isalpha(*name) && *name != '_')
- return false;
- while (*++name != '\0') {
- if (!isalpha(*name) && !isdigit(*name) && *name != '_')
- return false;
- }
- return true;
-}
-
/* Parse probepoint definition. */
static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
{
struct perf_probe_point *pp = &pev->point;
char *ptr, *tmp;
char c, nc = 0;
+ bool file_spec = false;
/*
* <Syntax>
* perf probe [EVENT=]SRC[:LN|;PTN]
@@ -1095,7 +1108,7 @@
semantic_error("Group name is not supported yet.\n");
return -ENOTSUP;
}
- if (!check_event_name(arg)) {
+ if (!is_c_func_name(arg)) {
semantic_error("%s is bad for event name -it must "
"follow C symbol-naming rule.\n", arg);
return -EINVAL;
@@ -1107,6 +1120,23 @@
arg = tmp;
}
+ /*
+ * Check arg is function or file name and copy it.
+ *
+ * We consider arg to be a file spec if and only if it satisfies
+ * all of the below criteria::
+ * - it does not include any of "+@%",
+ * - it includes one of ":;", and
+ * - it has a period '.' in the name.
+ *
+ * Otherwise, we consider arg to be a function specification.
+ */
+ if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+ /* This is a file spec if it includes a '.' before ; or : */
+ if (memchr(arg, '.', ptr - arg))
+ file_spec = true;
+ }
+
ptr = strpbrk(arg, ";:+@%");
if (ptr) {
nc = *ptr;
@@ -1117,10 +1147,9 @@
if (tmp == NULL)
return -ENOMEM;
- /* Check arg is function or file and copy it */
- if (strchr(tmp, '.')) /* File */
+ if (file_spec)
pp->file = tmp;
- else /* Function */
+ else
pp->function = tmp;
/* Parse other options */
@@ -1877,6 +1906,7 @@
free(tev->event);
free(tev->group);
free(tev->point.symbol);
+ free(tev->point.realname);
free(tev->point.module);
for (i = 0; i < tev->nargs; i++) {
free(tev->args[i].name);
@@ -1954,7 +1984,7 @@
if (ret >= 0) {
pr_debug("Opening %s write=%d\n", buf, readwrite);
if (readwrite && !probe_event_dry_run)
- ret = open(buf, O_RDWR, O_APPEND);
+ ret = open(buf, O_RDWR | O_APPEND, 0);
else
ret = open(buf, O_RDONLY, 0);
@@ -2131,7 +2161,23 @@
return ret;
}
-static int __show_perf_probe_events(int fd, bool is_kprobe)
+static bool filter_probe_trace_event(struct probe_trace_event *tev,
+ struct strfilter *filter)
+{
+ char tmp[128];
+
+ /* At first, check the event name itself */
+ if (strfilter__compare(filter, tev->event))
+ return true;
+
+ /* Next, check the combination of name and group */
+ if (e_snprintf(tmp, 128, "%s:%s", tev->group, tev->event) < 0)
+ return false;
+ return strfilter__compare(filter, tmp);
+}
+
+static int __show_perf_probe_events(int fd, bool is_kprobe,
+ struct strfilter *filter)
{
int ret = 0;
struct probe_trace_event tev;
@@ -2149,12 +2195,15 @@
strlist__for_each(ent, rawlist) {
ret = parse_probe_trace_command(ent->s, &tev);
if (ret >= 0) {
+ if (!filter_probe_trace_event(&tev, filter))
+ goto next;
ret = convert_to_perf_probe_event(&tev, &pev,
is_kprobe);
if (ret >= 0)
ret = show_perf_probe_event(&pev,
tev.point.module);
}
+next:
clear_perf_probe_event(&pev);
clear_probe_trace_event(&tev);
if (ret < 0)
@@ -2166,7 +2215,7 @@
}
/* List up current perf-probe events */
-int show_perf_probe_events(void)
+int show_perf_probe_events(struct strfilter *filter)
{
int kp_fd, up_fd, ret;
@@ -2178,7 +2227,7 @@
kp_fd = open_kprobe_events(false);
if (kp_fd >= 0) {
- ret = __show_perf_probe_events(kp_fd, true);
+ ret = __show_perf_probe_events(kp_fd, true, filter);
close(kp_fd);
if (ret < 0)
goto out;
@@ -2192,7 +2241,7 @@
}
if (up_fd >= 0) {
- ret = __show_perf_probe_events(up_fd, false);
+ ret = __show_perf_probe_events(up_fd, false, filter);
close(up_fd);
}
out:
@@ -2267,6 +2316,9 @@
{
int i, ret;
+ if (*base == '.')
+ base++;
+
/* Try no suffix */
ret = e_snprintf(buf, len, "%s", base);
if (ret < 0) {
@@ -2332,6 +2384,7 @@
struct strlist *namelist;
LIST_HEAD(blacklist);
struct kprobe_blacklist_node *node;
+ bool safename;
if (pev->uprobes)
fd = open_uprobe_events(true);
@@ -2347,7 +2400,8 @@
namelist = get_probe_trace_event_names(fd, false);
if (!namelist) {
pr_debug("Failed to get current event list.\n");
- return -EIO;
+ ret = -ENOMEM;
+ goto close_out;
}
/* Get kprobe blacklist if exists */
if (!pev->uprobes) {
@@ -2356,10 +2410,14 @@
pr_debug("No kprobe blacklist support, ignored\n");
}
+ safename = (pev->point.function && !strisglob(pev->point.function));
ret = 0;
pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
for (i = 0; i < ntevs; i++) {
tev = &tevs[i];
+ /* Skip if the symbol is out of .text (marked previously) */
+ if (!tev->point.symbol)
+ continue;
/* Ensure that the address is NOT blacklisted */
node = kprobe_blacklist__find_by_address(&blacklist,
tev->point.address);
@@ -2371,10 +2429,10 @@
if (pev->event)
event = pev->event;
else
- if (pev->point.function)
+ if (safename)
event = pev->point.function;
else
- event = tev->point.symbol;
+ event = tev->point.realname;
if (pev->group)
group = pev->group;
else
@@ -2430,6 +2488,7 @@
kprobe_blacklist__delete(&blacklist);
strlist__delete(namelist);
+close_out:
close(fd);
return ret;
}
@@ -2438,9 +2497,14 @@
{
int found = 0;
struct symbol *sym;
+ struct rb_node *tmp;
- map__for_each_symbol_by_name(map, name, sym) {
- found++;
+ if (map__load(map, NULL) < 0)
+ return 0;
+
+ map__for_each_symbol(map, sym, tmp) {
+ if (strglobmatch(sym->name, name))
+ found++;
}
return found;
@@ -2449,13 +2513,16 @@
#define strdup_or_goto(str, label) \
({ char *__p = strdup(str); if (!__p) goto label; __p; })
+void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
+ struct probe_trace_event *tev __maybe_unused,
+ struct map *map __maybe_unused) { }
+
/*
* Find probe function addresses from map.
* Return an error or the number of found probe_trace_event
*/
static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs, const char *target)
+ struct probe_trace_event **tevs)
{
struct map *map = NULL;
struct ref_reloc_sym *reloc_sym = NULL;
@@ -2466,7 +2533,7 @@
int num_matched_functions;
int ret, i;
- map = get_target_map(target, pev->uprobes);
+ map = get_target_map(pev->target, pev->uprobes);
if (!map) {
ret = -EINVAL;
goto out;
@@ -2479,12 +2546,12 @@
num_matched_functions = find_probe_functions(map, pp->function);
if (num_matched_functions == 0) {
pr_err("Failed to find symbol %s in %s\n", pp->function,
- target ? : "kernel");
+ pev->target ? : "kernel");
ret = -ENOENT;
goto out;
- } else if (num_matched_functions > max_tevs) {
+ } else if (num_matched_functions > probe_conf.max_probes) {
pr_err("Too many functions matched in %s\n",
- target ? : "kernel");
+ pev->target ? : "kernel");
ret = -E2BIG;
goto out;
}
@@ -2532,8 +2599,9 @@
tp->offset = pp->offset;
}
tp->retprobe = pp->retprobe;
- if (target)
- tev->point.module = strdup_or_goto(target, nomem_out);
+ if (pev->target)
+ tev->point.module = strdup_or_goto(pev->target,
+ nomem_out);
tev->uprobes = pev->uprobes;
tev->nargs = pev->nargs;
if (tev->nargs) {
@@ -2555,6 +2623,7 @@
strdup_or_goto(pev->args[i].type,
nomem_out);
}
+ arch__fix_tev_from_maps(pev, tev, map);
}
out:
@@ -2569,27 +2638,34 @@
goto out;
}
+bool __weak arch__prefers_symtab(void) { return false; }
+
static int convert_to_probe_trace_events(struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs, const char *target)
+ struct probe_trace_event **tevs)
{
int ret;
if (pev->uprobes && !pev->group) {
/* Replace group name if not given */
- ret = convert_exec_to_group(target, &pev->group);
+ ret = convert_exec_to_group(pev->target, &pev->group);
if (ret != 0) {
pr_warning("Failed to make a group name.\n");
return ret;
}
}
+ if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
+ ret = find_probe_trace_events_from_map(pev, tevs);
+ if (ret > 0)
+ return ret; /* Found in symbol table */
+ }
+
/* Convert perf_probe_event with debuginfo */
- ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+ ret = try_to_find_probe_trace_events(pev, tevs);
if (ret != 0)
return ret; /* Found in debuginfo or got an error */
- return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
+ return find_probe_trace_events_from_map(pev, tevs);
}
struct __event_package {
@@ -2598,8 +2674,7 @@
int ntevs;
};
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
- int max_tevs, bool force_add)
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
{
int i, j, ret;
struct __event_package *pkgs;
@@ -2621,9 +2696,7 @@
pkgs[i].pev = &pevs[i];
/* Convert with or without debuginfo */
ret = convert_to_probe_trace_events(pkgs[i].pev,
- &pkgs[i].tevs,
- max_tevs,
- pkgs[i].pev->target);
+ &pkgs[i].tevs);
if (ret < 0)
goto end;
pkgs[i].ntevs = ret;
@@ -2632,7 +2705,8 @@
/* Loop 2: add all events */
for (i = 0; i < npevs; i++) {
ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
- pkgs[i].ntevs, force_add);
+ pkgs[i].ntevs,
+ probe_conf.force_add);
if (ret < 0)
break;
}
@@ -2684,40 +2758,39 @@
return ret;
}
-static int del_trace_probe_event(int fd, const char *buf,
- struct strlist *namelist)
+static int del_trace_probe_events(int fd, struct strfilter *filter,
+ struct strlist *namelist)
{
- struct str_node *ent, *n;
- int ret = -1;
+ struct str_node *ent;
+ const char *p;
+ int ret = -ENOENT;
- if (strpbrk(buf, "*?")) { /* Glob-exp */
- strlist__for_each_safe(ent, n, namelist)
- if (strglobmatch(ent->s, buf)) {
- ret = __del_trace_probe_event(fd, ent);
- if (ret < 0)
- break;
- strlist__remove(namelist, ent);
- }
- } else {
- ent = strlist__find(namelist, buf);
- if (ent) {
+ if (!namelist)
+ return -ENOENT;
+
+ strlist__for_each(ent, namelist) {
+ p = strchr(ent->s, ':');
+ if ((p && strfilter__compare(filter, p + 1)) ||
+ strfilter__compare(filter, ent->s)) {
ret = __del_trace_probe_event(fd, ent);
- if (ret >= 0)
- strlist__remove(namelist, ent);
+ if (ret < 0)
+ break;
}
}
return ret;
}
-int del_perf_probe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strfilter *filter)
{
- int ret = -1, ufd = -1, kfd = -1;
- char buf[128];
- const char *group, *event;
- char *p, *str;
- struct str_node *ent;
+ int ret, ret2, ufd = -1, kfd = -1;
struct strlist *namelist = NULL, *unamelist = NULL;
+ char *str = strfilter__string(filter);
+
+ if (!str)
+ return -EINVAL;
+
+ pr_debug("Delete filter: \'%s\'\n", str);
/* Get current event names */
kfd = open_kprobe_events(true);
@@ -2730,48 +2803,21 @@
if (kfd < 0 && ufd < 0) {
print_both_open_warning(kfd, ufd);
+ ret = kfd;
goto error;
}
- if (namelist == NULL && unamelist == NULL)
+ ret = del_trace_probe_events(kfd, filter, namelist);
+ if (ret < 0 && ret != -ENOENT)
goto error;
- strlist__for_each(ent, dellist) {
- str = strdup(ent->s);
- if (str == NULL) {
- ret = -ENOMEM;
- goto error;
- }
- pr_debug("Parsing: %s\n", str);
- p = strchr(str, ':');
- if (p) {
- group = str;
- *p = '\0';
- event = p + 1;
- } else {
- group = "*";
- event = str;
- }
-
- ret = e_snprintf(buf, 128, "%s:%s", group, event);
- if (ret < 0) {
- pr_err("Failed to copy event.");
- free(str);
- goto error;
- }
-
- pr_debug("Group: %s, Event: %s\n", group, event);
-
- if (namelist)
- ret = del_trace_probe_event(kfd, buf, namelist);
-
- if (unamelist && ret != 0)
- ret = del_trace_probe_event(ufd, buf, unamelist);
-
- if (ret != 0)
- pr_info("Info: Event \"%s\" does not exist.\n", buf);
-
- free(str);
+ ret2 = del_trace_probe_events(ufd, filter, unamelist);
+ if (ret2 < 0 && ret2 != -ENOENT)
+ ret = ret2;
+ else if (ret == -ENOENT && ret2 == -ENOENT) {
+ pr_debug("\"%s\" does not hit any event.\n", str);
+ /* Note that this is silently ignored */
+ ret = 0;
}
error:
@@ -2784,6 +2830,7 @@
strlist__delete(unamelist);
close(ufd);
}
+ free(str);
return ret;
}
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index d6b7834..537eb32 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -6,10 +6,20 @@
#include "strlist.h"
#include "strfilter.h"
+/* Probe related configurations */
+struct probe_conf {
+ bool show_ext_vars;
+ bool show_location_range;
+ bool force_add;
+ bool no_inlines;
+ int max_probes;
+};
+extern struct probe_conf probe_conf;
extern bool probe_event_dry_run;
/* kprobe-tracer and uprobe-tracer tracing point */
struct probe_trace_point {
+ char *realname; /* function real name (if needed) */
char *symbol; /* Base symbol */
char *module; /* Module name */
unsigned long offset; /* Offset from symbol */
@@ -124,17 +134,18 @@
/* Internal use: Return kernel/module path */
extern const char *kernel_get_module_path(const char *module);
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
- int max_probe_points, bool force_add);
-extern int del_perf_probe_events(struct strlist *dellist);
-extern int show_perf_probe_events(void);
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int del_perf_probe_events(struct strfilter *filter);
+extern int show_perf_probe_events(struct strfilter *filter);
extern int show_line_range(struct line_range *lr, const char *module,
bool user);
extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
- int max_probe_points, const char *module,
- struct strfilter *filter, bool externs);
+ struct strfilter *filter);
extern int show_available_funcs(const char *module, struct strfilter *filter,
bool user);
+bool arch__prefers_symtab(void);
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+ struct probe_trace_event *tev, struct map *map);
/* Maximum index number of event-name postfix */
#define MAX_EVENT_INDEX 1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2a76e14..c50da39 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -177,7 +177,7 @@
Dwarf_Word offs = 0;
bool ref = false;
const char *regs;
- int ret;
+ int ret, ret2 = 0;
if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
goto static_var;
@@ -187,9 +187,19 @@
return -EINVAL; /* Broken DIE ? */
if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
ret = dwarf_entrypc(sp_die, &tmp);
- if (ret || addr != tmp ||
- dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
- dwarf_highpc(sp_die, &tmp))
+ if (ret)
+ return -ENOENT;
+
+ if (probe_conf.show_location_range &&
+ (dwarf_tag(vr_die) == DW_TAG_variable)) {
+ ret2 = -ERANGE;
+ } else if (addr != tmp ||
+ dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
+ return -ENOENT;
+ }
+
+ ret = dwarf_highpc(sp_die, &tmp);
+ if (ret)
return -ENOENT;
/*
* This is fuzzed by fentry mcount. We try to find the
@@ -210,7 +220,7 @@
if (op->atom == DW_OP_addr) {
static_var:
if (!tvar)
- return 0;
+ return ret2;
/* Static variables on memory (not stack), make @varname */
ret = strlen(dwarf_diename(vr_die));
tvar->value = zalloc(ret + 2);
@@ -220,7 +230,7 @@
tvar->ref = alloc_trace_arg_ref((long)offs);
if (tvar->ref == NULL)
return -ENOMEM;
- return 0;
+ return ret2;
}
/* If this is based on frame buffer, set the offset */
@@ -250,14 +260,14 @@
}
if (!tvar)
- return 0;
+ return ret2;
regs = get_arch_regstr(regn);
if (!regs) {
/* This should be a bug in DWARF or this tool */
pr_warning("Mapping for the register number %u "
"missing on this architecture.\n", regn);
- return -ERANGE;
+ return -ENOTSUP;
}
tvar->value = strdup(regs);
@@ -269,7 +279,7 @@
if (tvar->ref == NULL)
return -ENOMEM;
}
- return 0;
+ return ret2;
}
#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long))
@@ -517,10 +527,12 @@
ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
&pf->sp_die, pf->tvar);
- if (ret == -ENOENT || ret == -EINVAL)
- pr_err("Failed to find the location of %s at this address.\n"
- " Perhaps, it has been optimized out.\n", pf->pvar->var);
- else if (ret == -ENOTSUP)
+ if (ret == -ENOENT || ret == -EINVAL) {
+ pr_err("Failed to find the location of the '%s' variable at this address.\n"
+ " Perhaps it has been optimized out.\n"
+ " Use -V with the --range option to show '%s' location range.\n",
+ pf->pvar->var, pf->pvar->var);
+ } else if (ret == -ENOTSUP)
pr_err("Sorry, we don't support this variable location yet.\n");
else if (ret == 0 && pf->pvar->field) {
ret = convert_variable_fields(vr_die, pf->pvar->var,
@@ -662,9 +674,15 @@
/* If not a real subprogram, find a real one */
if (!die_is_func_def(sc_die)) {
if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
- pr_warning("Failed to find probe point in any "
- "functions.\n");
- return -ENOENT;
+ if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+ pr_warning("Ignoring tail call from %s\n",
+ dwarf_diename(&pf->sp_die));
+ return 0;
+ } else {
+ pr_warning("Failed to find probe point in any "
+ "functions.\n");
+ return -ENOENT;
+ }
}
} else
memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
@@ -719,7 +737,7 @@
}
/* If the function name is given, that's what user expects */
if (fsp->function) {
- if (die_compare_name(fn_die, fsp->function)) {
+ if (die_match_name(fn_die, fsp->function)) {
memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
fsp->found = true;
return 1;
@@ -922,13 +940,14 @@
/* Check tag and diename */
if (!die_is_func_def(sp_die) ||
- !die_compare_name(sp_die, pp->function))
+ !die_match_name(sp_die, pp->function))
return DWARF_CB_OK;
/* Check declared file */
if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
return DWARF_CB_OK;
+ pr_debug("Matched function: %s\n", dwarf_diename(sp_die));
pf->fname = dwarf_decl_file(sp_die);
if (pp->line) { /* Function relative line */
dwarf_decl_line(sp_die, &pf->lno);
@@ -945,10 +964,20 @@
/* TODO: Check the address in this function */
param->retval = call_probe_finder(sp_die, pf);
}
- } else
+ } else if (!probe_conf.no_inlines) {
/* Inlined function: search instances */
param->retval = die_walk_instances(sp_die,
probe_point_inline_cb, (void *)pf);
+ /* This could be a non-existed inline definition */
+ if (param->retval == -ENOENT && strisglob(pp->function))
+ param->retval = 0;
+ }
+
+ /* We need to find other candidates */
+ if (strisglob(pp->function) && param->retval >= 0) {
+ param->retval = 0; /* We have to clear the result */
+ return DWARF_CB_OK;
+ }
return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
}
@@ -977,7 +1006,7 @@
if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
return DWARF_CB_OK;
- if (die_compare_name(param->sp_die, param->function)) {
+ if (die_match_name(param->sp_die, param->function)) {
if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
return DWARF_CB_OK;
@@ -1030,7 +1059,7 @@
return -ENOMEM;
/* Fastpath: lookup by function name from .debug_pubnames section */
- if (pp->function) {
+ if (pp->function && !strisglob(pp->function)) {
struct pubname_callback_param pubname_param = {
.function = pp->function,
.file = pp->file,
@@ -1089,6 +1118,7 @@
struct local_vars_finder {
struct probe_finder *pf;
struct perf_probe_arg *args;
+ bool vars;
int max_args;
int nargs;
int ret;
@@ -1103,7 +1133,7 @@
tag = dwarf_tag(die_mem);
if (tag == DW_TAG_formal_parameter ||
- tag == DW_TAG_variable) {
+ (tag == DW_TAG_variable && vf->vars)) {
if (convert_variable_location(die_mem, vf->pf->addr,
vf->pf->fb_ops, &pf->sp_die,
NULL) == 0) {
@@ -1129,26 +1159,28 @@
Dwarf_Die die_mem;
int i;
int n = 0;
- struct local_vars_finder vf = {.pf = pf, .args = args,
+ struct local_vars_finder vf = {.pf = pf, .args = args, .vars = false,
.max_args = MAX_PROBE_ARGS, .ret = 0};
for (i = 0; i < pf->pev->nargs; i++) {
/* var never be NULL */
- if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
- pr_debug("Expanding $vars into:");
- vf.nargs = n;
- /* Special local variables */
- die_find_child(sc_die, copy_variables_cb, (void *)&vf,
- &die_mem);
- pr_debug(" (%d)\n", vf.nargs - n);
- if (vf.ret < 0)
- return vf.ret;
- n = vf.nargs;
- } else {
+ if (strcmp(pf->pev->args[i].var, PROBE_ARG_VARS) == 0)
+ vf.vars = true;
+ else if (strcmp(pf->pev->args[i].var, PROBE_ARG_PARAMS) != 0) {
/* Copy normal argument */
args[n] = pf->pev->args[i];
n++;
+ continue;
}
+ pr_debug("Expanding %s into:", pf->pev->args[i].var);
+ vf.nargs = n;
+ /* Special local variables */
+ die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+ &die_mem);
+ pr_debug(" (%d)\n", vf.nargs - n);
+ if (vf.ret < 0)
+ return vf.ret;
+ n = vf.nargs;
}
return n;
}
@@ -1176,6 +1208,10 @@
if (ret < 0)
return ret;
+ tev->point.realname = strdup(dwarf_diename(sc_die));
+ if (!tev->point.realname)
+ return -ENOMEM;
+
pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
tev->point.offset);
@@ -1213,15 +1249,15 @@
/* Find probe_trace_events specified by perf_probe_event from debuginfo */
int debuginfo__find_trace_events(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct probe_trace_event **tevs, int max_tevs)
+ struct probe_trace_event **tevs)
{
struct trace_event_finder tf = {
.pf = {.pev = pev, .callback = add_probe_trace_event},
- .mod = dbg->mod, .max_tevs = max_tevs};
+ .max_tevs = probe_conf.max_probes, .mod = dbg->mod};
int ret;
/* Allocate result tevs array */
- *tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+ *tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
if (*tevs == NULL)
return -ENOMEM;
@@ -1237,14 +1273,11 @@
return (ret < 0) ? ret : tf.ntevs;
}
-#define MAX_VAR_LEN 64
-
/* Collect available variables in this scope */
static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
{
struct available_var_finder *af = data;
struct variable_list *vl;
- char buf[MAX_VAR_LEN];
int tag, ret;
vl = &af->vls[af->nvls - 1];
@@ -1255,11 +1288,38 @@
ret = convert_variable_location(die_mem, af->pf.addr,
af->pf.fb_ops, &af->pf.sp_die,
NULL);
- if (ret == 0) {
- ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
- pr_debug2("Add new var: %s\n", buf);
- if (ret > 0)
- strlist__add(vl->vars, buf);
+ if (ret == 0 || ret == -ERANGE) {
+ int ret2;
+ bool externs = !af->child;
+ struct strbuf buf;
+
+ strbuf_init(&buf, 64);
+
+ if (probe_conf.show_location_range) {
+ if (!externs) {
+ if (ret)
+ strbuf_addf(&buf, "[INV]\t");
+ else
+ strbuf_addf(&buf, "[VAL]\t");
+ } else
+ strbuf_addf(&buf, "[EXT]\t");
+ }
+
+ ret2 = die_get_varname(die_mem, &buf);
+
+ if (!ret2 && probe_conf.show_location_range &&
+ !externs) {
+ strbuf_addf(&buf, "\t");
+ ret2 = die_get_var_range(&af->pf.sp_die,
+ die_mem, &buf);
+ }
+
+ pr_debug("Add new var: %s\n", buf.buf);
+ if (ret2 == 0) {
+ strlist__add(vl->vars,
+ strbuf_detach(&buf, NULL));
+ }
+ strbuf_release(&buf);
}
}
@@ -1302,9 +1362,9 @@
die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
/* Find external variables */
- if (!af->externs)
+ if (!probe_conf.show_ext_vars)
goto out;
- /* Don't need to search child DIE for externs. */
+ /* Don't need to search child DIE for external vars. */
af->child = false;
die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
@@ -1324,17 +1384,16 @@
*/
int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct variable_list **vls,
- int max_vls, bool externs)
+ struct variable_list **vls)
{
struct available_var_finder af = {
.pf = {.pev = pev, .callback = add_available_vars},
.mod = dbg->mod,
- .max_vls = max_vls, .externs = externs};
+ .max_vls = probe_conf.max_probes};
int ret;
/* Allocate result vls array */
- *vls = zalloc(sizeof(struct variable_list) * max_vls);
+ *vls = zalloc(sizeof(struct variable_list) * af.max_vls);
if (*vls == NULL)
return -ENOMEM;
@@ -1535,7 +1594,7 @@
return DWARF_CB_OK;
if (die_is_func_def(sp_die) &&
- die_compare_name(sp_die, lr->function)) {
+ die_match_name(sp_die, lr->function)) {
lf->fname = dwarf_decl_file(sp_die);
dwarf_decl_line(sp_die, &lr->offset);
pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ebf8c8c..bed8271 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -10,6 +10,9 @@
#define MAX_PROBES 128
#define MAX_PROBE_ARGS 128
+#define PROBE_ARG_VARS "$vars"
+#define PROBE_ARG_PARAMS "$params"
+
static inline int is_c_varname(const char *name)
{
/* TODO */
@@ -37,8 +40,7 @@
/* Find probe_trace_events specified by perf_probe_event from debuginfo */
extern int debuginfo__find_trace_events(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs);
+ struct probe_trace_event **tevs);
/* Find a perf_probe_point from debuginfo */
extern int debuginfo__find_probe_point(struct debuginfo *dbg,
@@ -52,8 +54,7 @@
/* Find available variables */
extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct variable_list **vls,
- int max_points, bool externs);
+ struct variable_list **vls);
/* Find a src file from a DWARF tag path */
int get_real_path(const char *raw_path, const char *comp_dir,
@@ -96,7 +97,6 @@
struct variable_list *vls; /* Found variable lists */
int nvls; /* Number of variable lists */
int max_vls; /* Max no. of variable lists */
- bool externs; /* Find external vars too */
bool child; /* Search child scopes */
};
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index a126e6c..b234a6e 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -74,3 +74,10 @@
pstack->entries[pstack->top] = NULL;
return ret;
}
+
+void *pstack__peek(struct pstack *pstack)
+{
+ if (pstack->top == 0)
+ return NULL;
+ return pstack->entries[pstack->top - 1];
+}
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
index c3cb658..ded7f2e 100644
--- a/tools/perf/util/pstack.h
+++ b/tools/perf/util/pstack.h
@@ -10,5 +10,6 @@
void pstack__remove(struct pstack *pstack, void *key);
void pstack__push(struct pstack *pstack, void *key);
void *pstack__pop(struct pstack *pstack);
+void *pstack__peek(struct pstack *pstack);
#endif /* _PERF_PSTACK_ */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 8acd0df..d457c52 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -20,7 +20,7 @@
if (!evlist)
return -ENOMEM;
- if (parse_events(evlist, str))
+ if (parse_events(evlist, str, NULL))
goto out_delete;
evsel = perf_evlist__first(evlist);
@@ -119,7 +119,16 @@
evsel->attr.comm_exec = 1;
}
- if (evlist->nr_entries > 1) {
+ if (opts->full_auxtrace) {
+ /*
+ * Need to be able to synthesize and parse selected events with
+ * arbitrary sample types, which requires always being able to
+ * match the id.
+ */
+ use_sample_identifier = perf_can_sample_identifier();
+ evlist__for_each(evlist, evsel)
+ perf_evsel__set_sample_id(evsel, use_sample_identifier);
+ } else if (evlist->nr_entries > 1) {
struct perf_evsel *first = perf_evlist__first(evlist);
evlist__for_each(evlist, evsel) {
@@ -207,7 +216,7 @@
if (!temp_evlist)
return false;
- err = parse_events(temp_evlist, str);
+ err = parse_events(temp_evlist, str, NULL);
if (err)
goto out_delete;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0c74012..e722107 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,12 +15,13 @@
#include "cpumap.h"
#include "perf_regs.h"
#include "asm/bug.h"
+#include "auxtrace.h"
-static int machines__deliver_event(struct machines *machines,
- struct perf_evlist *evlist,
- union perf_event *event,
- struct perf_sample *sample,
- struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset);
static int perf_session__open(struct perf_session *session)
{
@@ -105,8 +106,8 @@
return ret;
}
- return machines__deliver_event(&session->machines, session->evlist, event->event,
- &sample, session->tool, event->file_offset);
+ return perf_session__deliver_event(session, event->event, &sample,
+ session->tool, event->file_offset);
}
struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -119,6 +120,7 @@
session->repipe = repipe;
session->tool = tool;
+ INIT_LIST_HEAD(&session->auxtrace_index);
machines__init(&session->machines);
ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
@@ -185,6 +187,8 @@
void perf_session__delete(struct perf_session *session)
{
+ auxtrace__free(session);
+ auxtrace_index__free(&session->auxtrace_index);
perf_session__destroy_kernel_maps(session);
perf_session__delete_threads(session);
perf_session_env__delete(&session->header.env);
@@ -262,6 +266,49 @@
return 0;
}
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+ char buf[4096];
+ ssize_t ret;
+
+ while (n > 0) {
+ ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+ if (ret <= 0)
+ return ret;
+ n -= ret;
+ }
+
+ return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ if (perf_data_file__is_pipe(session->file))
+ skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+ return event->auxtrace.size;
+}
+
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
@@ -278,6 +325,10 @@
tool->exit = process_event_stub;
if (tool->lost == NULL)
tool->lost = perf_event__process_lost;
+ if (tool->aux == NULL)
+ tool->aux = perf_event__process_aux;
+ if (tool->itrace_start == NULL)
+ tool->itrace_start = perf_event__process_itrace_start;
if (tool->read == NULL)
tool->read = process_event_sample_stub;
if (tool->throttle == NULL)
@@ -298,6 +349,12 @@
}
if (tool->id_index == NULL)
tool->id_index = process_id_index_stub;
+ if (tool->auxtrace_info == NULL)
+ tool->auxtrace_info = process_event_auxtrace_info_stub;
+ if (tool->auxtrace == NULL)
+ tool->auxtrace = process_event_auxtrace_stub;
+ if (tool->auxtrace_error == NULL)
+ tool->auxtrace_error = process_event_auxtrace_error_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
@@ -390,6 +447,26 @@
swap_sample_id_all(event, &event->read + 1);
}
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+ event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+ event->aux.aux_size = bswap_64(event->aux.aux_size);
+ event->aux.flags = bswap_64(event->aux.flags);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->aux + 1);
+}
+
+static void perf_event__itrace_start_swap(union perf_event *event,
+ bool sample_id_all)
+{
+ event->itrace_start.pid = bswap_32(event->itrace_start.pid);
+ event->itrace_start.tid = bswap_32(event->itrace_start.tid);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
static void perf_event__throttle_swap(union perf_event *event,
bool sample_id_all)
{
@@ -449,6 +526,7 @@
attr->branch_sample_type = bswap_64(attr->branch_sample_type);
attr->sample_regs_user = bswap_64(attr->sample_regs_user);
attr->sample_stack_user = bswap_32(attr->sample_stack_user);
+ attr->aux_watermark = bswap_32(attr->aux_watermark);
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
@@ -478,6 +556,40 @@
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ size_t size;
+
+ event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+ size = event->header.size;
+ size -= (void *)&event->auxtrace_info.priv - (void *)event;
+ mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace.size = bswap_64(event->auxtrace.size);
+ event->auxtrace.offset = bswap_64(event->auxtrace.offset);
+ event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+ event->auxtrace.idx = bswap_32(event->auxtrace.idx);
+ event->auxtrace.tid = bswap_32(event->auxtrace.tid);
+ event->auxtrace.cpu = bswap_32(event->auxtrace.cpu);
+}
+
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+ event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+ event->auxtrace_error.cpu = bswap_32(event->auxtrace_error.cpu);
+ event->auxtrace_error.pid = bswap_32(event->auxtrace_error.pid);
+ event->auxtrace_error.tid = bswap_32(event->auxtrace_error.tid);
+ event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip);
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
@@ -492,11 +604,16 @@
[PERF_RECORD_THROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_SAMPLE] = perf_event__all64_swap,
+ [PERF_RECORD_AUX] = perf_event__aux_swap,
+ [PERF_RECORD_ITRACE_START] = perf_event__itrace_start_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
[PERF_RECORD_HEADER_BUILD_ID] = NULL,
[PERF_RECORD_ID_INDEX] = perf_event__all64_swap,
+ [PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
+ [PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
+ [PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -938,12 +1055,34 @@
return tool->throttle(tool, event, sample, machine);
case PERF_RECORD_UNTHROTTLE:
return tool->unthrottle(tool, event, sample, machine);
+ case PERF_RECORD_AUX:
+ return tool->aux(tool, event, sample, machine);
+ case PERF_RECORD_ITRACE_START:
+ return tool->itrace_start(tool, event, sample, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
}
}
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset)
+{
+ int ret;
+
+ ret = auxtrace__process_event(session, event, sample, tool);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ return 0;
+
+ return machines__deliver_event(&session->machines, session->evlist,
+ event, sample, tool, file_offset);
+}
+
static s64 perf_session__process_user_event(struct perf_session *session,
union perf_event *event,
u64 file_offset)
@@ -980,6 +1119,15 @@
return tool->finished_round(tool, event, oe);
case PERF_RECORD_ID_INDEX:
return tool->id_index(tool, event, session);
+ case PERF_RECORD_AUXTRACE_INFO:
+ return tool->auxtrace_info(tool, event, session);
+ case PERF_RECORD_AUXTRACE:
+ /* setup for reading amidst mmap */
+ lseek(fd, file_offset + event->header.size, SEEK_SET);
+ return tool->auxtrace(tool, event, session);
+ case PERF_RECORD_AUXTRACE_ERROR:
+ perf_session__auxtrace_error_inc(session, event);
+ return tool->auxtrace_error(tool, event, session);
default:
return -EINVAL;
}
@@ -1096,8 +1244,8 @@
return ret;
}
- return machines__deliver_event(&session->machines, evlist, event,
- &sample, tool, file_offset);
+ return perf_session__deliver_event(session, event, &sample, tool,
+ file_offset);
}
void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1168,6 +1316,8 @@
if (oe->nr_unordered_events != 0)
ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+ events_stats__auxtrace_error_warn(stats);
}
volatile int session_done;
@@ -1256,10 +1406,14 @@
done:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
out_err:
free(buf);
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
return err;
}
@@ -1402,10 +1556,14 @@
out:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
out_err:
ui_progress__finish();
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
session->one_mmap = false;
return err;
}
@@ -1488,7 +1646,13 @@
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
{
- size_t ret = fprintf(fp, "Aggregated stats:\n");
+ size_t ret;
+ const char *msg = "";
+
+ if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+ ret = fprintf(fp, "Aggregated stats:%s\n", msg);
ret += events_stats__fprintf(&session->evlist->stats, fp);
return ret;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index d5fa7b791..b44afc7 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -15,10 +15,16 @@
struct ip_callchain;
struct thread;
+struct auxtrace;
+struct itrace_synth_opts;
+
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
+ struct auxtrace *auxtrace;
+ struct itrace_synth_opts *itrace_synth_opts;
+ struct list_head auxtrace_index;
struct trace_event tevent;
bool repipe;
bool one_mmap;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4593f36..09d4696 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -89,14 +89,14 @@
sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
{
/* Compare the addr that should be unique among comm */
- return comm__str(right->comm) - comm__str(left->comm);
+ return strcmp(comm__str(right->comm), comm__str(left->comm));
}
static int64_t
sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
{
/* Compare the addr that should be unique among comm */
- return comm__str(right->comm) - comm__str(left->comm);
+ return strcmp(comm__str(right->comm), comm__str(left->comm));
}
static int64_t
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 846036a..e97cd47 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -58,15 +58,16 @@
struct hist_entry_diff {
bool computed;
+ union {
+ /* PERF_HPP__DELTA */
+ double period_ratio_delta;
- /* PERF_HPP__DELTA */
- double period_ratio_delta;
+ /* PERF_HPP__RATIO */
+ double period_ratio;
- /* PERF_HPP__RATIO */
- double period_ratio;
-
- /* HISTC_WEIGHTED_DIFF */
- s64 wdiff;
+ /* HISTC_WEIGHTED_DIFF */
+ s64 wdiff;
+ };
};
/**
@@ -92,21 +93,28 @@
s32 cpu;
u8 cpumode;
- struct hist_entry_diff diff;
-
/* We are added by hists__add_dummy_entry. */
bool dummy;
- /* XXX These two should move to some tree widget lib */
- u16 row_offset;
- u16 nr_rows;
-
- bool init_have_children;
char level;
u8 filtered;
+ union {
+ /*
+ * Since perf diff only supports the stdio output, TUI
+ * fields are only accessed from perf report (or perf
+ * top). So make it an union to reduce memory usage.
+ */
+ struct hist_entry_diff diff;
+ struct /* for TUI */ {
+ u16 row_offset;
+ u16 nr_rows;
+ bool init_have_children;
+ bool unfolded;
+ bool has_children;
+ };
+ };
char *srcline;
struct symbol *parent;
- unsigned long position;
struct rb_root sorted_chain;
struct branch_info *branch_info;
struct hists *hists;
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 79a757a..bcae659 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -170,6 +170,46 @@
return filter;
}
+static int strfilter__append(struct strfilter *filter, bool _or,
+ const char *rules, const char **err)
+{
+ struct strfilter_node *right, *root;
+ const char *ep = NULL;
+
+ if (!filter || !rules)
+ return -EINVAL;
+
+ right = strfilter_node__new(rules, &ep);
+ if (!right || *ep != '\0') {
+ if (err)
+ *err = ep;
+ goto error;
+ }
+ root = strfilter_node__alloc(_or ? OP_or : OP_and, filter->root, right);
+ if (!root) {
+ ep = NULL;
+ goto error;
+ }
+
+ filter->root = root;
+ return 0;
+
+error:
+ strfilter_node__delete(right);
+ return ep ? -EINVAL : -ENOMEM;
+}
+
+int strfilter__or(struct strfilter *filter, const char *rules, const char **err)
+{
+ return strfilter__append(filter, true, rules, err);
+}
+
+int strfilter__and(struct strfilter *filter, const char *rules,
+ const char **err)
+{
+ return strfilter__append(filter, false, rules, err);
+}
+
static bool strfilter_node__compare(struct strfilter_node *node,
const char *str)
{
@@ -197,3 +237,70 @@
return false;
return strfilter_node__compare(filter->root, str);
}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf);
+
+/* sprint node in parenthesis if needed */
+static int strfilter_node__sprint_pt(struct strfilter_node *node, char *buf)
+{
+ int len;
+ int pt = node->r ? 2 : 0; /* don't need to check node->l */
+
+ if (buf && pt)
+ *buf++ = '(';
+ len = strfilter_node__sprint(node, buf);
+ if (len < 0)
+ return len;
+ if (buf && pt)
+ *(buf + len) = ')';
+ return len + pt;
+}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
+{
+ int len = 0, rlen;
+
+ if (!node || !node->p)
+ return -EINVAL;
+
+ switch (*node->p) {
+ case '|':
+ case '&':
+ len = strfilter_node__sprint_pt(node->l, buf);
+ if (len < 0)
+ return len;
+ case '!':
+ if (buf) {
+ *(buf + len++) = *node->p;
+ buf += len;
+ } else
+ len++;
+ rlen = strfilter_node__sprint_pt(node->r, buf);
+ if (rlen < 0)
+ return rlen;
+ len += rlen;
+ break;
+ default:
+ len = strlen(node->p);
+ if (buf)
+ strcpy(buf, node->p);
+ }
+
+ return len;
+}
+
+char *strfilter__string(struct strfilter *filter)
+{
+ int len;
+ char *ret = NULL;
+
+ len = strfilter_node__sprint(filter->root, NULL);
+ if (len < 0)
+ return NULL;
+
+ ret = malloc(len + 1);
+ if (ret)
+ strfilter_node__sprint(filter->root, ret);
+
+ return ret;
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
index fe611f3..cff5eda 100644
--- a/tools/perf/util/strfilter.h
+++ b/tools/perf/util/strfilter.h
@@ -29,6 +29,32 @@
struct strfilter *strfilter__new(const char *rules, const char **err);
/**
+ * strfilter__or - Append an additional rule by logical-or
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ * @filter by using logical-or.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-or.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__or(struct strfilter *filter,
+ const char *rules, const char **err);
+
+/**
+ * strfilter__add - Append an additional rule by logical-and
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ * @filter by using logical-and.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-and.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__and(struct strfilter *filter,
+ const char *rules, const char **err);
+
+/**
* strfilter__compare - compare given string and a string filter
* @filter: String filter
* @str: target string
@@ -45,4 +71,13 @@
*/
void strfilter__delete(struct strfilter *filter);
+/**
+ * strfilter__string - Reconstruct a rule string from filter
+ * @filter: String filter to reconstruct
+ *
+ * Reconstruct a rule string from @filter. This will be good for
+ * debug messages. Note that returning string must be freed afterward.
+ */
+char *strfilter__string(struct strfilter *filter);
+
#endif
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a7ab606..9d526a5 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -630,6 +630,11 @@
close(ss->fd);
}
+bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+ return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+}
+
int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
enum dso_binary_type type)
{
@@ -678,6 +683,7 @@
}
if (!dso__build_id_equal(dso, build_id)) {
+ pr_debug("%s: build id mismatch for %s.\n", __func__, name);
dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
goto out_elf_end;
}
@@ -711,8 +717,7 @@
".gnu.prelink_undo",
NULL) != NULL);
} else {
- ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
- ehdr.e_type == ET_REL;
+ ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
}
ss->name = strdup(name);
@@ -771,6 +776,8 @@
return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
}
+void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+
int dso__load_sym(struct dso *dso, struct map *map,
struct symsrc *syms_ss, struct symsrc *runtime_ss,
symbol_filter_t filter, int kmodule)
@@ -935,6 +942,8 @@
(sym.st_value & 1))
--sym.st_value;
+ arch__elf_sym_adjust(&sym);
+
if (dso->kernel || kmodule) {
char dso_name[PATH_MAX];
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 201f6c4c..82a31fd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -85,8 +85,17 @@
return tail - str;
}
-#define SYMBOL_A 0
-#define SYMBOL_B 1
+int __weak arch__choose_best_symbol(struct symbol *syma,
+ struct symbol *symb __maybe_unused)
+{
+ /* Avoid "SyS" kernel syscall aliases */
+ if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
+ return SYMBOL_B;
+ if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+ return SYMBOL_B;
+
+ return SYMBOL_A;
+}
static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
{
@@ -134,13 +143,7 @@
else if (na < nb)
return SYMBOL_B;
- /* Avoid "SyS" kernel syscall aliases */
- if (na >= 3 && !strncmp(syma->name, "SyS", 3))
- return SYMBOL_B;
- if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
- return SYMBOL_B;
-
- return SYMBOL_A;
+ return arch__choose_best_symbol(syma, symb);
}
void symbols__fixup_duplicate(struct rb_root *symbols)
@@ -408,7 +411,7 @@
int cmp;
s = rb_entry(n, struct symbol_name_rb_node, rb_node);
- cmp = strcmp(name, s->sym.name);
+ cmp = arch__compare_symbol_names(name, s->sym.name);
if (cmp < 0)
n = n->rb_left;
@@ -426,7 +429,7 @@
struct symbol_name_rb_node *tmp;
tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
- if (strcmp(tmp->sym.name, s->sym.name))
+ if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
break;
s = tmp;
@@ -1380,12 +1383,22 @@
struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
bool kmod;
- dso__set_loaded(dso, map->type);
+ pthread_mutex_lock(&dso->lock);
- if (dso->kernel == DSO_TYPE_KERNEL)
- return dso__load_kernel_sym(dso, map, filter);
- else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
- return dso__load_guest_kernel_sym(dso, map, filter);
+ /* check again under the dso->lock */
+ if (dso__loaded(dso, map->type)) {
+ ret = 1;
+ goto out;
+ }
+
+ if (dso->kernel) {
+ if (dso->kernel == DSO_TYPE_KERNEL)
+ ret = dso__load_kernel_sym(dso, map, filter);
+ else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+ ret = dso__load_guest_kernel_sym(dso, map, filter);
+
+ goto out;
+ }
if (map->groups && map->groups->machine)
machine = map->groups->machine;
@@ -1398,18 +1411,18 @@
struct stat st;
if (lstat(dso->name, &st) < 0)
- return -1;
+ goto out;
if (st.st_uid && (st.st_uid != geteuid())) {
pr_warning("File %s not owned by current user or root, "
"ignoring it.\n", dso->name);
- return -1;
+ goto out;
}
ret = dso__load_perf_map(dso, map, filter);
dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
DSO_BINARY_TYPE__NOT_FOUND;
- return ret;
+ goto out;
}
if (machine)
@@ -1417,7 +1430,7 @@
name = malloc(PATH_MAX);
if (!name)
- return -1;
+ goto out;
kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
@@ -1498,7 +1511,11 @@
out_free:
free(name);
if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
- return 0;
+ ret = 0;
+out:
+ dso__set_loaded(dso, map->type);
+ pthread_mutex_unlock(&dso->lock);
+
return ret;
}
@@ -1802,6 +1819,7 @@
{
while (--vmlinux_path__nr_entries >= 0)
zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+ vmlinux_path__nr_entries = 0;
zfree(&vmlinux_path);
}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 0956150..bef47ead 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -158,8 +158,6 @@
struct map_symbol {
struct map *map;
struct symbol *sym;
- bool unfolded;
- bool has_children;
};
struct addr_map_symbol {
@@ -303,4 +301,14 @@
int setup_intlist(struct intlist **list, const char *list_str,
const char *list_name);
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+void arch__elf_sym_adjust(GElf_Sym *sym);
+#endif
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+
#endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1c8fbc9..16c28a3 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -18,7 +18,7 @@
if (pid == thread->tid || pid == -1) {
thread->mg = map_groups__new(machine);
} else {
- leader = machine__findnew_thread(machine, pid, pid);
+ leader = __machine__findnew_thread(machine, pid, pid);
if (leader)
thread->mg = map_groups__get(leader->mg);
}
@@ -53,7 +53,9 @@
goto err_thread;
list_add(&comm->list, &thread->comm_list);
-
+ atomic_set(&thread->refcnt, 0);
+ INIT_LIST_HEAD(&thread->node);
+ RB_CLEAR_NODE(&thread->rb_node);
}
return thread;
@@ -67,6 +69,9 @@
{
struct comm *comm, *tmp;
+ BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
+ BUG_ON(!list_empty(&thread->node));
+
thread_stack__free(thread);
if (thread->mg) {
@@ -84,13 +89,14 @@
struct thread *thread__get(struct thread *thread)
{
- ++thread->refcnt;
+ if (thread)
+ atomic_inc(&thread->refcnt);
return thread;
}
void thread__put(struct thread *thread)
{
- if (thread && --thread->refcnt == 0) {
+ if (thread && atomic_dec_and_test(&thread->refcnt)) {
list_del_init(&thread->node);
thread__delete(thread);
}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b8a54d..a0ac031 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,6 +1,7 @@
#ifndef __PERF_THREAD_H
#define __PERF_THREAD_H
+#include <linux/atomic.h>
#include <linux/rbtree.h>
#include <linux/list.h>
#include <unistd.h>
@@ -21,12 +22,12 @@
pid_t tid;
pid_t ppid;
int cpu;
- int refcnt;
+ atomic_t refcnt;
char shortname[3];
bool comm_set;
+ int comm_len;
bool dead; /* if set thread has exited */
struct list_head comm_list;
- int comm_len;
u64 db_id;
void *priv;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 51d9e56..7f282ad 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -3,6 +3,8 @@
#include <stdbool.h>
+#include <linux/types.h>
+
struct perf_session;
union perf_event;
struct perf_evlist;
@@ -29,6 +31,9 @@
typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
struct ordered_events *oe);
+typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
+ struct perf_session *session);
+
struct perf_tool {
event_sample sample,
read;
@@ -38,13 +43,18 @@
fork,
exit,
lost,
+ aux,
+ itrace_start,
throttle,
unthrottle;
event_attr_op attr;
event_op2 tracing_data;
event_oe finished_round;
event_op2 build_id,
- id_index;
+ id_index,
+ auxtrace_info,
+ auxtrace_error;
+ event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
};
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 4ee6d0d..0c264bc 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -72,6 +72,49 @@
return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
}
+int rm_rf(char *path)
+{
+ DIR *dir;
+ int ret = 0;
+ struct dirent *d;
+ char namebuf[PATH_MAX];
+
+ dir = opendir(path);
+ if (dir == NULL)
+ return 0;
+
+ while ((d = readdir(dir)) != NULL && !ret) {
+ struct stat statbuf;
+
+ if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+ continue;
+
+ scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+ path, d->d_name);
+
+ ret = stat(namebuf, &statbuf);
+ if (ret < 0) {
+ pr_debug("stat failed: %s\n", namebuf);
+ break;
+ }
+
+ if (S_ISREG(statbuf.st_mode))
+ ret = unlink(namebuf);
+ else if (S_ISDIR(statbuf.st_mode))
+ ret = rm_rf(namebuf);
+ else {
+ pr_debug("unknown file: %s\n", namebuf);
+ ret = -1;
+ }
+ }
+ closedir(dir);
+
+ if (ret < 0)
+ return ret;
+
+ return rmdir(path);
+}
+
static int slow_copyfile(const char *from, const char *to, mode_t mode)
{
int err = -1;
@@ -102,11 +145,38 @@
return err;
}
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+ void *ptr;
+ loff_t pgoff;
+
+ pgoff = off_in & ~(page_size - 1);
+ off_in -= pgoff;
+
+ ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+ if (ptr == MAP_FAILED)
+ return -1;
+
+ while (size) {
+ ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+ if (ret < 0 && errno == EINTR)
+ continue;
+ if (ret <= 0)
+ break;
+
+ size -= ret;
+ off_in += ret;
+ off_out -= ret;
+ }
+ munmap(ptr, off_in + size);
+
+ return size ? -1 : 0;
+}
+
int copyfile_mode(const char *from, const char *to, mode_t mode)
{
int fromfd, tofd;
struct stat st;
- void *addr;
int err = -1;
if (stat(from, &st))
@@ -123,15 +193,8 @@
if (tofd < 0)
goto out_close_from;
- addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
- if (addr == MAP_FAILED)
- goto out_close_to;
+ err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
- if (write(tofd, addr, st.st_size) == st.st_size)
- err = 0;
-
- munmap(addr, st.st_size);
-out_close_to:
close(tofd);
if (err)
unlink(to);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1ff23e0..8bce58b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -249,14 +249,20 @@
}
int mkdir_p(char *path, mode_t mode);
+int rm_rf(char *path);
int copyfile(const char *from, const char *to);
int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
s64 perf_atoll(const char *str);
char **argv_split(const char *str, int *argcp);
void argv_free(char **argv);
bool strglobmatch(const char *str, const char *pat);
bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+ return strpbrk(str, "*?[") != NULL;
+}
int strtailcmp(const char *s1, const char *s2);
char *strxfrchar(char *s, char from, char to);
unsigned long convert_unit(unsigned long value, char *unit);