Use immediate values with lower d-cache hit in optimized version as a condition for scheduler profiling call. Changelog : - Use imv_* instead of immediate_*. - Follow the white rabbit : kvm_main.c which becomes x86.c. Signed-off-by: Mathieu Desnoyers CC: Rusty Russell CC: Adrian Bunk CC: Andi Kleen CC: Christoph Hellwig CC: mingo@elte.hu CC: akpm@osdl.org --- arch/x86/kvm/x86.c | 2 +- include/linux/profile.h | 5 +++-- kernel/ksysfs.c | 4 ++-- kernel/profile.c | 22 +++++++++++----------- kernel/sched_fair.c | 7 ++----- 5 files changed, 19 insertions(+), 21 deletions(-) Index: linux.trees.git/kernel/profile.c =================================================================== --- linux.trees.git.orig/kernel/profile.c 2009-09-24 08:52:55.000000000 -0400 +++ linux.trees.git/kernel/profile.c 2009-09-24 09:03:02.000000000 -0400 @@ -42,8 +42,8 @@ static int (*timer_hook)(struct pt_regs static atomic_t *prof_buffer; static unsigned long prof_len, prof_shift; -int prof_on __read_mostly; -EXPORT_SYMBOL_GPL(prof_on); +DEFINE_IMV(char, prof_on) __read_mostly; +EXPORT_IMV_SYMBOL_GPL(prof_on); static cpumask_var_t prof_cpu_mask; #ifdef CONFIG_SMP @@ -61,7 +61,7 @@ int profile_setup(char *str) if (!strncmp(str, sleepstr, strlen(sleepstr))) { #ifdef CONFIG_SCHEDSTATS - prof_on = SLEEP_PROFILING; + imv_set(prof_on, SLEEP_PROFILING); if (str[strlen(sleepstr)] == ',') str += strlen(sleepstr) + 1; if (get_option(&str, &par)) @@ -74,7 +74,7 @@ int profile_setup(char *str) "kernel sleep profiling requires CONFIG_SCHEDSTATS\n"); #endif /* CONFIG_SCHEDSTATS */ } else if (!strncmp(str, schedstr, strlen(schedstr))) { - prof_on = SCHED_PROFILING; + imv_set(prof_on, SCHED_PROFILING); if (str[strlen(schedstr)] == ',') str += strlen(schedstr) + 1; if (get_option(&str, &par)) @@ -83,7 +83,7 @@ int profile_setup(char *str) "kernel schedule profiling enabled (shift: %ld)\n", prof_shift); } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { - prof_on = KVM_PROFILING; + imv_set(prof_on, KVM_PROFILING); if (str[strlen(kvmstr)] == ',') str += strlen(kvmstr) + 1; if (get_option(&str, &par)) @@ -93,7 +93,7 @@ int profile_setup(char *str) prof_shift); } else if (get_option(&str, &par)) { prof_shift = par; - prof_on = CPU_PROFILING; + imv_set(prof_on, CPU_PROFILING); printk(KERN_INFO "kernel profiling enabled (shift: %ld)\n", prof_shift); } @@ -105,7 +105,7 @@ __setup("profile=", profile_setup); int __ref profile_init(void) { int buffer_bytes; - if (!prof_on) + if (!_imv_read(prof_on)) return 0; /* only text is profiled */ @@ -309,7 +309,7 @@ void profile_hits(int type, void *__pc, int i, j, cpu; struct profile_hit *hits; - if (prof_on != type || !prof_buffer) + if (!prof_buffer) return; pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; @@ -421,7 +421,7 @@ void profile_hits(int type, void *__pc, { unsigned long pc; - if (prof_on != type || !prof_buffer) + if (!prof_buffer) return; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); @@ -585,7 +585,7 @@ static int create_hash_tables(void) } return 0; out_cleanup: - prof_on = 0; + imv_set(prof_on, 0); smp_mb(); on_each_cpu(profile_nop, NULL, 1); for_each_online_cpu(cpu) { @@ -612,7 +612,7 @@ int __ref create_proc_profile(void) /* f { struct proc_dir_entry *entry; - if (!prof_on) + if (!_imv_read(prof_on)) return 0; if (create_hash_tables()) return -ENOMEM; Index: linux.trees.git/include/linux/profile.h =================================================================== --- linux.trees.git.orig/include/linux/profile.h 2008-10-30 20:22:52.000000000 -0400 +++ linux.trees.git/include/linux/profile.h 2009-09-24 09:03:02.000000000 -0400 @@ -5,6 +5,7 @@ #include #include #include +#include #include @@ -38,7 +39,7 @@ enum profile_type { #ifdef CONFIG_PROFILING -extern int prof_on __read_mostly; +DECLARE_IMV(char, prof_on) __read_mostly; /* init basic kernel profiler */ int profile_init(void); @@ -58,7 +59,7 @@ static inline void profile_hit(int type, /* * Speedup for the common (no profiling enabled) case: */ - if (unlikely(prof_on == type)) + if (unlikely(imv_read(prof_on) == type)) profile_hits(type, ip, 1); } Index: linux.trees.git/kernel/sched_fair.c =================================================================== --- linux.trees.git.orig/kernel/sched_fair.c 2009-09-24 08:52:55.000000000 -0400 +++ linux.trees.git/kernel/sched_fair.c 2009-09-24 09:03:56.000000000 -0400 @@ -672,11 +672,8 @@ static void enqueue_sleeper(struct cfs_r * 20 to get a milliseconds-range estimation of the * amount of time that the task spent sleeping: */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - profile_hits(SLEEP_PROFILING, - (void *)get_wchan(tsk), - delta >> 20); - } + profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk), + delta >> 20); account_scheduler_latency(tsk, delta >> 10, 0); } } Index: linux.trees.git/arch/x86/kvm/x86.c =================================================================== --- linux.trees.git.orig/arch/x86/kvm/x86.c 2009-09-24 08:52:42.000000000 -0400 +++ linux.trees.git/arch/x86/kvm/x86.c 2009-09-24 09:03:02.000000000 -0400 @@ -3672,7 +3672,7 @@ static int vcpu_enter_guest(struct kvm_v /* * Profile KVM exit RIPs: */ - if (unlikely(prof_on == KVM_PROFILING)) { + if (unlikely(imv_read(prof_on) == KVM_PROFILING)) { unsigned long rip = kvm_rip_read(vcpu); profile_hit(KVM_PROFILING, (void *)rip); } Index: linux.trees.git/kernel/ksysfs.c =================================================================== --- linux.trees.git.orig/kernel/ksysfs.c 2009-03-06 13:29:01.000000000 -0500 +++ linux.trees.git/kernel/ksysfs.c 2009-09-24 09:03:02.000000000 -0400 @@ -58,7 +58,7 @@ KERNEL_ATTR_RW(uevent_helper); static ssize_t profiling_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", prof_on); + return sprintf(buf, "%d\n", _imv_read(prof_on)); } static ssize_t profiling_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -66,7 +66,7 @@ static ssize_t profiling_store(struct ko { int ret; - if (prof_on) + if (_imv_read(prof_on)) return -EEXIST; /* * This eventually calls into get_option() which -- Mathieu Desnoyers OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68