Re: [PATCH v3 2/4] sched_clock: Optimize cache line usage

[Stephen Boyd <sboyd@codeaurora.org>]

On 01/30, Daniel Thompson wrote:
> diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
> index 3d21a8719444..cb69a47dfee4 100644
> --- a/kernel/time/sched_clock.c
> +++ b/kernel/time/sched_clock.c
> @@ -18,28 +18,44 @@
>  #include <linux/seqlock.h>
>  #include <linux/bitops.h>
>  
> -struct clock_data {
> -	ktime_t wrap_kt;
> +/**
> + * struct clock_read_data - data required to read from sched_clock
> + *

Nitpick: Won't kernel-doc complain that members aren't
documented?

> + * Care must be taken when updating this structure; it is read by
> + * some very hot code paths. It occupies <=48 bytes and, when combined
> + * with the seqcount used to synchronize access, comfortably fits into
> + * a 64 byte cache line.
> + */
> +struct clock_read_data {
>  	u64 epoch_ns;
>  	u64 epoch_cyc;
> -	seqcount_t seq;
> -	unsigned long rate;
> +	u64 sched_clock_mask;
> +	u64 (*read_sched_clock)(void);
>  	u32 mult;
>  	u32 shift;
>  	bool suspended;
>  };
>  
> +/**
> + * struct clock_data - all data needed for sched_clock (including
> + *                     registration of a new clock source)
> + *

Same comment.

> + * The ordering of this structure has been chosen to optimize cache
> + * performance. In particular seq and read_data (combined) should fit
> + * into a single 64 byte cache line.
> + */
> +struct clock_data {
> +	seqcount_t seq;
> +	struct clock_read_data read_data;
> +	ktime_t wrap_kt;
> +	unsigned long rate;
> +};
> @@ -60,15 +79,16 @@ unsigned long long notrace sched_clock(void)
>  {
>  	u64 cyc, res;
>  	unsigned long seq;
> +	struct clock_read_data *rd = &cd.read_data;
>  
>  	do {
>  		seq = raw_read_seqcount_begin(&cd.seq);
>  
> -		res = cd.epoch_ns;
> -		if (!cd.suspended) {
> -			cyc = read_sched_clock();
> -			cyc = (cyc - cd.epoch_cyc) & sched_clock_mask;
> -			res += cyc_to_ns(cyc, cd.mult, cd.shift);
> +		res = rd->epoch_ns;
> +		if (!rd->suspended) {

Should this have likely() treatment? It would be really nice if
we could use static branches here to avoid any branch penalty at
all. I guess that would need some sort of special cased
stop_machine() though. Or I wonder if we could replace
rd->read_sched_clock() with a dumb function that returns
cd.epoch_cyc so that the math turns out to be 0?

> +			cyc = rd->read_sched_clock();
> +			cyc = (cyc - rd->epoch_cyc) & rd->sched_clock_mask;
> +			res += cyc_to_ns(cyc, rd->mult, rd->shift);
>  		}
>  	} while (read_seqcount_retry(&cd.seq, seq));
>  

-- 
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project