On Mon, May 27, 2019 at 11:38:40AM +0200, Uladzislau Rezki (Sony) wrote:
> Refactor the NE_FIT_TYPE split case when it comes to an
> allocation of one extra object. We need it in order to
> build a remaining space.
>
> Introduce ne_fit_preload()/ne_fit_preload_end() functions
> for preloading one extra vmap_area object to ensure that
> we have it available when fit type is NE_FIT_TYPE.
>
> The preload is done per CPU in non-atomic context thus with
> GFP_KERNEL allocation masks. More permissive parameters can
> be beneficial for systems which are suffer from high memory
> pressure or low memory condition.
>
> Signed-off-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
> ---
> mm/vmalloc.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
> 1 file changed, 76 insertions(+), 3 deletions(-)
Hi Uladzislau!
This patch generally looks good to me (see some nits below),
but it would be really great to add some motivation, e.g. numbers.
Thanks!
>
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index ea1b65fac599..b553047aa05b 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -364,6 +364,13 @@ static LIST_HEAD(free_vmap_area_list);
> */
> static struct rb_root free_vmap_area_root = RB_ROOT;
>
> +/*
> + * Preload a CPU with one object for "no edge" split case. The
> + * aim is to get rid of allocations from the atomic context, thus
> + * to use more permissive allocation masks.
> + */
> +static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);
> +
> static __always_inline unsigned long
> va_size(struct vmap_area *va)
> {
> @@ -950,9 +957,24 @@ adjust_va_to_fit_type(struct vmap_area *va,
> * L V NVA V R
> * |---|-------|---|
> */
> - lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
> - if (unlikely(!lva))
> - return -1;
> + lva = __this_cpu_xchg(ne_fit_preload_node, NULL);
> + if (unlikely(!lva)) {
> + /*
> + * For percpu allocator we do not do any pre-allocation
> + * and leave it as it is. The reason is it most likely
> + * never ends up with NE_FIT_TYPE splitting. In case of
> + * percpu allocations offsets and sizes are aligned to
> + * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE
> + * are its main fitting cases.
> + *
> + * There are a few exceptions though, as an example it is
> + * a first allocation (early boot up) when we have "one"
> + * big free space that has to be split.
> + */
> + lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
> + if (!lva)
> + return -1;
> + }
>
> /*
> * Build the remainder.
> @@ -1023,6 +1045,48 @@ __alloc_vmap_area(unsigned long size, unsigned long align,
> }
>
> /*
> + * 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 to be more stable under
> + * low memory condition and high memory pressure.
> + *
> + * If success it returns 1 with preemption disabled. In case
> + * of error 0 is returned with preemption not disabled. Note it
> + * has to be paired with ne_fit_preload_end().
> + */
> +static int
Cosmetic nit: you don't need a new line here.
> +ne_fit_preload(int nid)
> +{
> + preempt_disable();
> +
> + if (!__this_cpu_read(ne_fit_preload_node)) {
> + struct vmap_area *node;
> +
> + preempt_enable();
> + node = kmem_cache_alloc_node(vmap_area_cachep, GFP_KERNEL, nid);
> + if (node == NULL)
> + return 0;
> +
> + preempt_disable();
> +
> + if (__this_cpu_cmpxchg(ne_fit_preload_node, NULL, node))
> + kmem_cache_free(vmap_area_cachep, node);
> + }
> +
> + return 1;
> +}
> +
> +static void
Here too.
> +ne_fit_preload_end(int preloaded)
> +{
> + if (preloaded)
> + preempt_enable();
> +}
I'd open code it. It's used only once, but hiding preempt_disable()
behind a helper makes it harder to understand and easier to mess.
Then ne_fit_preload() might require disabled preemption (which it can
temporarily re-enable), so that preempt_enable()/disable() logic
will be in one place.
> +
> +/*
> * Allocate a region of KVA of the specified size and alignment, within the
> * vstart and vend.
> */
> @@ -1034,6 +1098,7 @@ 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 +1121,12 @@ 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.
> + */
> + preloaded = ne_fit_preload(node);
> spin_lock(&vmap_area_lock);
>
> /*
> @@ -1063,6 +1134,8 @@ 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
>
