* Mel Gorman <[email protected]> wrote:
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1289,6 +1289,18 @@ enum perf_event_task_context {
> perf_nr_task_contexts,
> };
>
> +/* Track pages that require TLB flushes */
> +struct tlbflush_unmap_batch {
> + /*
> + * Each bit set is a CPU that potentially has a TLB entry for one of
> + * the PFNs being flushed. See set_tlb_ubc_flush_pending().
> + */
> + struct cpumask cpumask;
> +
> + /* True if any bit in cpumask is set */
> + bool flush_required;
> +};
> +
> struct task_struct {
> volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
> void *stack;
> @@ -1648,6 +1660,10 @@ struct task_struct {
> unsigned long numa_pages_migrated;
> #endif /* CONFIG_NUMA_BALANCING */
>
> +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
> + struct tlbflush_unmap_batch *tlb_ubc;
> +#endif
Please embedd this constant size structure in task_struct directly so that the
whole per task allocation overhead goes away:
> +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
> +/*
> + * Allocate the control structure for batch TLB flushing. An allocation
> + * failure is harmless as the reclaimer will send IPIs where necessary.
> + * A GFP_KERNEL allocation from this context is normally not advised but
> + * we are depending on PF_MEMALLOC (set by direct reclaim or kswapd) to
> + * limit the depth of the call.
> + */
> +static void alloc_tlb_ubc(void)
> +{
> + if (!current->tlb_ubc)
> + current->tlb_ubc = kzalloc(sizeof(struct tlbflush_unmap_batch),
> + GFP_KERNEL | __GFP_NOWARN);
> +}
> +#else
> +static inline void alloc_tlb_ubc(void)
> +{
> +}
> +#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
> +
> /*
> * This is a basic per-zone page freer. Used by both kswapd and direct
> reclaim.
> */
> @@ -2152,6 +2174,8 @@ static void shrink_lruvec(struct lruvec *lruvec, int
> swappiness,
> scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
> sc->priority == DEF_PRIORITY);
>
> + alloc_tlb_ubc();
> +
> blk_start_plug(&plug);
> while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
> nr[LRU_INACTIVE_FILE]) {
the whole patch series will become even simpler.
Thanks,
Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
