b77f0f3c1f
In the course of testing jump labels for use with the CFS
bandwidth controller, Paul Turner, discovered that using jump
labels reduced the branch count and the instruction count, but
did not reduce the cycle count or wall time.
I noticed that having the jump_label.o included in the kernel
but not used in any way still caused this increase in cycle
count and wall time. Thus, I moved jump_label.o in the
kernel/Makefile, thus changing the link order, and presumably
moving it out of hot icache areas. This brought down the cycle
count/time as expected.
In addition to Paul's testing, I've tested the patch using a
single 'static_branch()' in the getppid() path, and basically
running tight loops of calls to getppid(). Here are my results
for the branch disabled case:
With jump labels turned on (CONFIG_JUMP_LABEL), branch disabled:
Performance counter stats for 'bash -c /tmp/getppid;true' (50 runs):
3,969,510,217 instructions # 0.864 IPC ( +-0.000% )
4,592,334,954 cycles ( +- 0.046% )
751,634,470 branches ( +- 0.000% )
1.722635797 seconds time elapsed ( +- 0.046% )
Jump labels turned off (CONFIG_JUMP_LABEL not set), branch
disabled:
Performance counter stats for 'bash -c /tmp/getppid;true' (50 runs):
4,009,611,846 instructions # 0.867 IPC ( +-0.000% )
4,622,210,580 cycles ( +- 0.012% )
771,662,904 branches ( +- 0.000% )
1.734341454 seconds time elapsed ( +- 0.022% )
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: rth@redhat.com
Cc: a.p.zijlstra@chello.nl
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/20110805204040.GG2522@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Paul Turner <pjt@google.com>
140 lines
5 KiB
Makefile
140 lines
5 KiB
Makefile
#
|
|
# Makefile for the linux kernel.
|
|
#
|
|
|
|
obj-y = sched.o fork.o exec_domain.o panic.o printk.o \
|
|
cpu.o exit.o itimer.o time.o softirq.o resource.o \
|
|
sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
|
|
signal.o sys.o kmod.o workqueue.o pid.o \
|
|
rcupdate.o extable.o params.o posix-timers.o \
|
|
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
|
|
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
|
|
notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
|
|
async.o range.o
|
|
obj-y += groups.o
|
|
|
|
ifdef CONFIG_FUNCTION_TRACER
|
|
# Do not trace debug files and internal ftrace files
|
|
CFLAGS_REMOVE_lockdep.o = -pg
|
|
CFLAGS_REMOVE_lockdep_proc.o = -pg
|
|
CFLAGS_REMOVE_mutex-debug.o = -pg
|
|
CFLAGS_REMOVE_rtmutex-debug.o = -pg
|
|
CFLAGS_REMOVE_cgroup-debug.o = -pg
|
|
CFLAGS_REMOVE_sched_clock.o = -pg
|
|
CFLAGS_REMOVE_irq_work.o = -pg
|
|
endif
|
|
|
|
obj-$(CONFIG_FREEZER) += freezer.o
|
|
obj-$(CONFIG_PROFILING) += profile.o
|
|
obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
|
|
obj-$(CONFIG_STACKTRACE) += stacktrace.o
|
|
obj-y += time/
|
|
obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
|
|
obj-$(CONFIG_LOCKDEP) += lockdep.o
|
|
ifeq ($(CONFIG_PROC_FS),y)
|
|
obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
|
|
endif
|
|
obj-$(CONFIG_FUTEX) += futex.o
|
|
ifeq ($(CONFIG_COMPAT),y)
|
|
obj-$(CONFIG_FUTEX) += futex_compat.o
|
|
endif
|
|
obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
|
|
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
|
|
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
|
|
obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
|
|
obj-$(CONFIG_SMP) += smp.o
|
|
ifneq ($(CONFIG_SMP),y)
|
|
obj-y += up.o
|
|
endif
|
|
obj-$(CONFIG_SMP) += spinlock.o
|
|
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
|
|
obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
|
|
obj-$(CONFIG_UID16) += uid16.o
|
|
obj-$(CONFIG_MODULES) += module.o
|
|
obj-$(CONFIG_KALLSYMS) += kallsyms.o
|
|
obj-$(CONFIG_PM) += power/
|
|
obj-$(CONFIG_FREEZER) += power/
|
|
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
|
|
obj-$(CONFIG_KEXEC) += kexec.o
|
|
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
|
|
obj-$(CONFIG_COMPAT) += compat.o
|
|
obj-$(CONFIG_CGROUPS) += cgroup.o
|
|
obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
|
|
obj-$(CONFIG_CPUSETS) += cpuset.o
|
|
obj-$(CONFIG_UTS_NS) += utsname.o
|
|
obj-$(CONFIG_USER_NS) += user_namespace.o
|
|
obj-$(CONFIG_PID_NS) += pid_namespace.o
|
|
obj-$(CONFIG_IKCONFIG) += configs.o
|
|
obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
|
|
obj-$(CONFIG_SMP) += stop_machine.o
|
|
obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
|
|
obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
|
|
obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
|
|
obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o
|
|
obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
|
|
obj-$(CONFIG_GCOV_KERNEL) += gcov/
|
|
obj-$(CONFIG_KPROBES) += kprobes.o
|
|
obj-$(CONFIG_KGDB) += debug/
|
|
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
|
|
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
|
|
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
|
|
obj-$(CONFIG_SECCOMP) += seccomp.o
|
|
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
|
|
obj-$(CONFIG_TREE_RCU) += rcutree.o
|
|
obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
|
|
obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
|
|
obj-$(CONFIG_TINY_RCU) += rcutiny.o
|
|
obj-$(CONFIG_TINY_PREEMPT_RCU) += rcutiny.o
|
|
obj-$(CONFIG_RELAY) += relay.o
|
|
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
|
|
obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
|
|
obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
|
|
obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
|
|
obj-$(CONFIG_LATENCYTOP) += latencytop.o
|
|
obj-$(CONFIG_BINFMT_ELF) += elfcore.o
|
|
obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
|
|
obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
|
|
obj-$(CONFIG_FUNCTION_TRACER) += trace/
|
|
obj-$(CONFIG_TRACING) += trace/
|
|
obj-$(CONFIG_X86_DS) += trace/
|
|
obj-$(CONFIG_RING_BUFFER) += trace/
|
|
obj-$(CONFIG_TRACEPOINTS) += trace/
|
|
obj-$(CONFIG_SMP) += sched_cpupri.o
|
|
obj-$(CONFIG_IRQ_WORK) += irq_work.o
|
|
|
|
obj-$(CONFIG_PERF_EVENTS) += events/
|
|
|
|
obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
|
|
obj-$(CONFIG_PADATA) += padata.o
|
|
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
|
|
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
|
|
|
|
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
|
|
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
|
|
# needed for x86 only. Why this used to be enabled for all architectures is beyond
|
|
# me. I suspect most platforms don't need this, but until we know that for sure
|
|
# I turn this off for IA-64 only. Andreas Schwab says it's also needed on m68k
|
|
# to get a correct value for the wait-channel (WCHAN in ps). --davidm
|
|
CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer
|
|
endif
|
|
|
|
$(obj)/configs.o: $(obj)/config_data.h
|
|
|
|
# config_data.h contains the same information as ikconfig.h but gzipped.
|
|
# Info from config_data can be extracted from /proc/config*
|
|
targets += config_data.gz
|
|
$(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE
|
|
$(call if_changed,gzip)
|
|
|
|
filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;")
|
|
targets += config_data.h
|
|
$(obj)/config_data.h: $(obj)/config_data.gz FORCE
|
|
$(call filechk,ikconfiggz)
|
|
|
|
$(obj)/time.o: $(obj)/timeconst.h
|
|
|
|
quiet_cmd_timeconst = TIMEC $@
|
|
cmd_timeconst = $(PERL) $< $(CONFIG_HZ) > $@
|
|
targets += timeconst.h
|
|
$(obj)/timeconst.h: $(src)/timeconst.pl FORCE
|
|
$(call if_changed,timeconst)
|