Re: [PATCH 2/2] Add a thread cpu time implementation to vDSO

[Arun Sharma]

On 12/12/11 12:13 PM, Eric Dumazet wrote:

> > +
> > +struct vcpu_data {
> > +	struct vpercpu_data vpercpu[NR_CPUS];
> > +	unsigned int tsc_khz;
> > +	unsigned int tsc_unstable;
> > +};
>
> Thats a showstopper.
>
> Try to compile the thing with NR_CPUS=4096 ?

I get a link time error:

ld: section .data..percpu [0000000001ac2000 -> 0000000001ad48ff] 
overlaps section .vvar [0000000001ac0000 -> 0000000001b0083f]

which I consider better than runtime memory corruption :)

I could add a BUILD_BUG_ON() that tries to catch this earlier in the 
compile process.

Re: Fixing the build for NR_CPUS > 64

How about something along the lines of the following:

From: Arun Sharma <asharma@xxxxxx>
Date: Mon, 12 Dec 2011 13:13:43 -0800
Subject: [PATCH] Handle NR_CPUS > 64

---
arch/x86/kernel/tsc.c          |    8 ++++++--
arch/x86/vdso/vclock_gettime.c |    4 ++--
include/linux/jiffies.h        |    8 ++++++--
kernel/sched.c                 |    2 ++
4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 1dc7205..45f3438 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -571,7 +571,11 @@ int recalibrate_cpu_khz(void)
			cpufreq_scale(cpu_data(0).loops_per_jiffy,
					cpu_khz_old, cpu_khz);
		vcpu_data.tsc_khz = tsc_khz;
-		vcpu_data.tsc_unstable = 0;
+#if CONFIG_NR_CPUS <= 64
+		vcpu_data.thread_cputime_disabled = 0;
+#else
+		vcpu_data.thread_cputime_disabled = 1;
+#endif
		return 0;
	} else
		return -ENODEV;
@@ -790,7 +794,7 @@ void mark_tsc_unstable(char *reason)
		tsc_unstable = 1;
		sched_clock_stable = 0;
		disable_sched_clock_irqtime();
-		vcpu_data.tsc_unstable = 1;
+		vcpu_data.thread_cputime_disabled = 1;
		jump_label_dec(&vcpu_data_enabled);
		printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
		/* Change only the rating, when not registered */
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 61ab74b..e41a7e9 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -185,7 +185,7 @@ notrace static inline unsigned long 
__do_thread_cpu_time(void)
	const struct vcpu_data *vp = &VVAR(vcpu_data);
	int cpu;

-	if (vp->tsc_unstable) {
+	if (vp->thread_cputime_disabled) {
		struct timespec ts;
		vdso_fallback_gettime(CLOCK_THREAD_CPUTIME_ID, &ts);
		return timespec_to_ns(&ts);
@@ -236,7 +236,7 @@ notrace int __vdso_clock_gettime(clockid_t clock, 
struct timespec *ts)
	case CLOCK_MONOTONIC_COARSE:
		return do_monotonic_coarse(ts);
	case CLOCK_THREAD_CPUTIME_ID:
-		if (vp->tsc_unstable)
+		if (vp->thread_cputime_disabled)
			break;
		ns = do_thread_cpu_time();
		if (likely(ns > 0)) {
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index a0fe1f5..aec389f 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -319,9 +319,13 @@ struct vpercpu_data {
} ____cacheline_aligned;

struct vcpu_data {
-	struct vpercpu_data vpercpu[NR_CPUS];
	unsigned int tsc_khz;
-	unsigned int tsc_unstable;
+	unsigned int thread_cputime_disabled;
+#if CONFIG_NR_CPUS <= 64
+	struct vpercpu_data vpercpu[NR_CPUS];
+#else
+	struct vpercpu_data vpercpu[1];
+#endif
};
extern struct vcpu_data vcpu_data;

diff --git a/kernel/sched.c b/kernel/sched.c
index a72545a..e4f38ae 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3216,11 +3216,13 @@ static void finish_task_switch(struct rq *rq, 
struct task_struct *prev)
		put_task_struct(prev);
	}

+#if CONFIG_NR_CPUS <= 64
	if (static_branch(&vcpu_data_enabled)) {
		int cpu = smp_processor_id();
		vcpu_data.vpercpu[cpu].adj_sched_time =
                  current->se.sum_exec_runtime - sched_clock();
	}
+#endif
}

#ifdef CONFIG_SMP
--
1.7.4


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/