Re: [PATCH v3 1/2] mm: Make alloc_contig_range handle free hugetlb pages

From: Mike Kravetz
Date: Thu Feb 25 2021 - 15:05:14 EST


On 2/22/21 5:51 AM, Oscar Salvador wrote:
> alloc_contig_range will fail if it ever sees a HugeTLB page within the
> range we are trying to allocate, even when that page is free and can be
> easily reallocated.
> This has proved to be problematic for some users of alloc_contic_range,
> e.g: CMA and virtio-mem, where those would fail the call even when those
> pages lay in ZONE_MOVABLE and are free.
>
> We can do better by trying to replace such page.
>
> Free hugepages are tricky to handle so as to no userspace application
> notices disruption, we need to replace the current free hugepage with
> a new one.
>
> In order to do that, a new function called alloc_and_dissolve_huge_page
> is introduced.
> This function will first try to get a new fresh hugepage, and if it
> succeeds, it will replace the old one in the free hugepage pool.
>
> All operations are being handled under hugetlb_lock, so no races are
> possible. The only exception is when page's refcount is 0, but it still
> has not been flagged as PageHugeFreed.
> In this case we retry as the window race is quite small and we have high
> chances to succeed next time.
>
> With regard to the allocation, we restrict it to the node the page belongs
> to with __GFP_THISNODE, meaning we do not fallback on other node's zones.
>
> Note that gigantic hugetlb pages are fenced off since there is a cyclic
> dependency between them and alloc_contig_range.
>
> Signed-off-by: Oscar Salvador <osalvador@xxxxxxx>

Thanks Oscar,

I spent a bunch of time looking for possible race issues. Thankfully,
the recent code from Muchun dealing with free lists helps. In addition,
all the hugetlb acounting looks good.

Reviewed-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>

> ---
> include/linux/hugetlb.h | 6 +++
> mm/compaction.c | 12 ++++++
> mm/hugetlb.c | 111 +++++++++++++++++++++++++++++++++++++++++++++++-
> 3 files changed, 127 insertions(+), 2 deletions(-)
--
Mike Kravetz