On Wed, 22 May 2019 17:09:37 +0200 Uladzislau Rezki (Sony) wrote:
> /*
> + * Preload this CPU with one extra vmap_area object to ensure
> + * that we have it available when fit type of free area is
> + * NE_FIT_TYPE.
> + *
> + * The preload is done in non-atomic context thus, it allows us
> + * to use more permissive allocation masks, therefore to be more
> + * stable under low memory condition and high memory pressure.
> + *
> + * If success, it returns zero with preemption disabled. In case
> + * of error, (-ENOMEM) is returned with preemption not disabled.
> + * Note it has to be paired with alloc_vmap_area_preload_end().
> + */
> +static void
> +ne_fit_preload(int *preloaded)
> +{
> + preempt_disable();
> +
> + if (!__this_cpu_read(ne_fit_preload_node)) {
> + struct vmap_area *node;
> +
> + preempt_enable();
> + node = kmem_cache_alloc(vmap_area_cachep, GFP_KERNEL);
Alternatively, can you please take another look at the upside to use
the memory node parameter in alloc_vmap_area() for allocating va slab,
given that this preload, unlike adjust_va_to_fit_type() is invoked
with the vmap_area_lock not aquired?
> + if (node == NULL) {
> + *preloaded = 0;
> + return;
> + }
> +
> + preempt_disable();
> +
> + if (__this_cpu_cmpxchg(ne_fit_preload_node, NULL, node))
> + kmem_cache_free(vmap_area_cachep, node);
> + }
> +
> + *preloaded = 1;
> +}
> +
> +static void
> +ne_fit_preload_end(int preloaded)
> +{
> + if (preloaded)
> + preempt_enable();
> +}
> +
> +/*
> * Allocate a region of KVA of the specified size and alignment, within the
> * vstart and vend.
> */
> @@ -1034,6 +1100,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
> struct vmap_area *va;
> unsigned long addr;
> int purged = 0;
> + int preloaded;
>
> BUG_ON(!size);
> BUG_ON(offset_in_page(size));
> @@ -1056,6 +1123,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
> kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
>
> retry:
> + /*
> + * Even if it fails we do not really care about that.
> + * Just proceed as it is. "overflow" path will refill
> + * the cache we allocate from.
> + */
> + ne_fit_preload(&preloaded);
> spin_lock(&vmap_area_lock);
>
> /*
> @@ -1063,6 +1136,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
> * returned. Therefore trigger the overflow path.
> */
> addr = __alloc_vmap_area(size, align, vstart, vend);
> + ne_fit_preload_end(preloaded);
> +
> if (unlikely(addr == vend))
> goto overflow;
>
> --
> 2.11.0
>
Best Regards
Hillf
