diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-04-23 09:24:06 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-05-05 23:56:18 +0200 |
commit | dfbf4a1bc319f0f9a31e39b2da1fa5c55e85af89 (patch) | |
tree | 0b9dd19406c53a93452dd345bb05f76aa712a757 /kernel | |
parent | cb4ad1ffc7c0d8ea7dc8cd8ba303d83551716d46 (diff) | |
download | talos-obmc-linux-dfbf4a1bc319f0f9a31e39b2da1fa5c55e85af89.tar.gz talos-obmc-linux-dfbf4a1bc319f0f9a31e39b2da1fa5c55e85af89.zip |
sched: fix cpu clock
David Miller pointed it out that nothing in cpu_clock() sets
prev_cpu_time. This caused __sync_cpu_clock() to be called
all the time - against the intention of this code.
The result was that in practice we hit a global spinlock every
time cpu_clock() is called - which - even though cpu_clock()
is used for tracing and debugging, is suboptimal.
While at it, also:
- move the irq disabling to the outest layer,
this should make cpu_clock() warp-free when called with irqs
enabled.
- use long long instead of cycles_t - for platforms where cycles_t
is 32-bit.
Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/sched.c | 24 |
1 files changed, 15 insertions, 9 deletions
diff --git a/kernel/sched.c b/kernel/sched.c index f98f75f3c708..9457106b18af 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -910,11 +910,14 @@ static DEFINE_PER_CPU(unsigned long long, prev_cpu_time); static DEFINE_SPINLOCK(time_sync_lock); static unsigned long long prev_global_time; -static unsigned long long __sync_cpu_clock(cycles_t time, int cpu) +static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu) { - unsigned long flags; - - spin_lock_irqsave(&time_sync_lock, flags); + /* + * We want this inlined, to not get tracer function calls + * in this critical section: + */ + spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_); + __raw_spin_lock(&time_sync_lock.raw_lock); if (time < prev_global_time) { per_cpu(time_offset, cpu) += prev_global_time - time; @@ -923,7 +926,8 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu) prev_global_time = time; } - spin_unlock_irqrestore(&time_sync_lock, flags); + __raw_spin_unlock(&time_sync_lock.raw_lock); + spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_); return time; } @@ -931,7 +935,6 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu) static unsigned long long __cpu_clock(int cpu) { unsigned long long now; - unsigned long flags; struct rq *rq; /* @@ -941,11 +944,9 @@ static unsigned long long __cpu_clock(int cpu) if (unlikely(!scheduler_running)) return 0; - local_irq_save(flags); rq = cpu_rq(cpu); update_rq_clock(rq); now = rq->clock; - local_irq_restore(flags); return now; } @@ -957,13 +958,18 @@ static unsigned long long __cpu_clock(int cpu) unsigned long long cpu_clock(int cpu) { unsigned long long prev_cpu_time, time, delta_time; + unsigned long flags; + local_irq_save(flags); prev_cpu_time = per_cpu(prev_cpu_time, cpu); time = __cpu_clock(cpu) + per_cpu(time_offset, cpu); delta_time = time-prev_cpu_time; - if (unlikely(delta_time > time_sync_thresh)) + if (unlikely(delta_time > time_sync_thresh)) { time = __sync_cpu_clock(time, cpu); + per_cpu(prev_cpu_time, cpu) = time; + } + local_irq_restore(flags); return time; } |