Re: [RFC][Patch v9 2/6] KVM: Enables the kernel to isolate guest free pages

[Alexander Duyck]

On Wed, Mar 6, 2019 at 7:51 AM Nitesh Narayan Lal <nitesh@xxxxxxxxxx> wrote:
>
> This patch enables the kernel to scan the per cpu array
> which carries head pages from the buddy free list of order
> FREE_PAGE_HINTING_MIN_ORDER (MAX_ORDER - 1) by
> guest_free_page_hinting().
> guest_free_page_hinting() scans the entire per cpu array by
> acquiring a zone lock corresponding to the pages which are
> being scanned. If the page is still free and present in the
> buddy it tries to isolate the page and adds it to a
> dynamically allocated array.
>
> Once this scanning process is complete and if there are any
> isolated pages added to the dynamically allocated array
> guest_free_page_report() is invoked. However, before this the
> per-cpu array index is reset so that it can continue capturing
> the pages from buddy free list.
>
> In this patch guest_free_page_report() simply releases the pages back
> to the buddy by using __free_one_page()
>
> Signed-off-by: Nitesh Narayan Lal <nitesh@xxxxxxxxxx>

I'm pretty sure this code is not thread safe and has a few various issues.

> ---
>  include/linux/page_hinting.h |   5 ++
>  mm/page_alloc.c              |   2 +-
>  virt/kvm/page_hinting.c      | 154 +++++++++++++++++++++++++++++++++++
>  3 files changed, 160 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/page_hinting.h b/include/linux/page_hinting.h
> index 90254c582789..d554a2581826 100644
> --- a/include/linux/page_hinting.h
> +++ b/include/linux/page_hinting.h
> @@ -13,3 +13,8 @@
>
>  void guest_free_page_enqueue(struct page *page, int order);
>  void guest_free_page_try_hinting(void);
> +extern int __isolate_free_page(struct page *page, unsigned int order);
> +extern void __free_one_page(struct page *page, unsigned long pfn,
> +                           struct zone *zone, unsigned int order,
> +                           int migratetype);
> +void release_buddy_pages(void *obj_to_free, int entries);
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 684d047f33ee..d38b7eea207b 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -814,7 +814,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
>   * -- nyc
>   */
>
> -static inline void __free_one_page(struct page *page,
> +inline void __free_one_page(struct page *page,
>                 unsigned long pfn,
>                 struct zone *zone, unsigned int order,
>                 int migratetype)
> diff --git a/virt/kvm/page_hinting.c b/virt/kvm/page_hinting.c
> index 48b4b5e796b0..9885b372b5a9 100644
> --- a/virt/kvm/page_hinting.c
> +++ b/virt/kvm/page_hinting.c
> @@ -1,5 +1,9 @@
>  #include <linux/mm.h>
>  #include <linux/page_hinting.h>
> +#include <linux/page_ref.h>
> +#include <linux/kvm_host.h>
> +#include <linux/kernel.h>
> +#include <linux/sort.h>
>
>  /*
>   * struct guest_free_pages- holds array of guest freed PFN's along with an
> @@ -16,6 +20,54 @@ struct guest_free_pages {
>
>  DEFINE_PER_CPU(struct guest_free_pages, free_pages_obj);
>
> +/*
> + * struct guest_isolated_pages- holds the buddy isolated pages which are
> + * supposed to be freed by the host.
> + * @pfn: page frame number for the isolated page.
> + * @order: order of the isolated page.
> + */
> +struct guest_isolated_pages {
> +       unsigned long pfn;
> +       unsigned int order;
> +};
> +
> +void release_buddy_pages(void *obj_to_free, int entries)
> +{
> +       int i = 0;
> +       int mt = 0;
> +       struct guest_isolated_pages *isolated_pages_obj = obj_to_free;
> +
> +       while (i < entries) {
> +               struct page *page = pfn_to_page(isolated_pages_obj[i].pfn);
> +
> +               mt = get_pageblock_migratetype(page);
> +               __free_one_page(page, page_to_pfn(page), page_zone(page),
> +                               isolated_pages_obj[i].order, mt);
> +               i++;
> +       }
> +       kfree(isolated_pages_obj);
> +}

You shouldn't be accessing __free_one_page without holding the zone
lock for the page. You might consider confining yourself to one zone
worth of hints at a time. Then you can acquire the lock once, and then
return the memory you have freed.

This is one of the reasons why I am thinking maybe a bit in the page
and then spinning on that bit in arch_alloc_page might be a nice way
to get around this. Then you only have to take the zone lock when you
are finding the pages you want to hint on and setting the bit
indicating they are mid hint. Otherwise you have to take the zone lock
to pull pages out, and to put them back in and the likelihood of a
lock collision is much higher.

> +
> +void guest_free_page_report(struct guest_isolated_pages *isolated_pages_obj,
> +                           int entries)
> +{
> +       release_buddy_pages(isolated_pages_obj, entries);
> +}
> +
> +static int sort_zonenum(const void *a1, const void *b1)
> +{
> +       const unsigned long *a = a1;
> +       const unsigned long *b = b1;
> +
> +       if (page_zonenum(pfn_to_page(a[0])) > page_zonenum(pfn_to_page(b[0])))
> +               return 1;
> +
> +       if (page_zonenum(pfn_to_page(a[0])) < page_zonenum(pfn_to_page(b[0])))
> +               return -1;
> +
> +       return 0;
> +}
> +
>  struct page *get_buddy_page(struct page *page)
>  {
>         unsigned long pfn = page_to_pfn(page);
> @@ -33,9 +85,111 @@ struct page *get_buddy_page(struct page *page)
>  static void guest_free_page_hinting(void)
>  {
>         struct guest_free_pages *hinting_obj = &get_cpu_var(free_pages_obj);
> +       struct guest_isolated_pages *isolated_pages_obj;
> +       int idx = 0, ret = 0;
> +       struct zone *zone_cur, *zone_prev;
> +       unsigned long flags = 0;
> +       int hyp_idx = 0;
> +       int free_pages_idx = hinting_obj->free_pages_idx;
> +
> +       isolated_pages_obj = kmalloc(MAX_FGPT_ENTRIES *
> +                       sizeof(struct guest_isolated_pages), GFP_KERNEL);
> +       if (!isolated_pages_obj) {
> +               hinting_obj->free_pages_idx = 0;
> +               put_cpu_var(hinting_obj);
> +               return;
> +               /* return some logical error here*/
> +       }
> +
> +       sort(hinting_obj->free_page_arr, free_pages_idx,
> +            sizeof(unsigned long), sort_zonenum, NULL);
> +
> +       while (idx < free_pages_idx) {
> +               unsigned long pfn = hinting_obj->free_page_arr[idx];
> +               unsigned long pfn_end = hinting_obj->free_page_arr[idx] +
> +                       (1 << FREE_PAGE_HINTING_MIN_ORDER) - 1;
> +
> +               zone_cur = page_zone(pfn_to_page(pfn));
> +               if (idx == 0) {
> +                       zone_prev = zone_cur;
> +                       spin_lock_irqsave(&zone_cur->lock, flags);
> +               } else if (zone_prev != zone_cur) {
> +                       spin_unlock_irqrestore(&zone_prev->lock, flags);
> +                       spin_lock_irqsave(&zone_cur->lock, flags);
> +                       zone_prev = zone_cur;
> +               }
> +
> +               while (pfn <= pfn_end) {
> +                       struct page *page = pfn_to_page(pfn);
> +                       struct page *buddy_page = NULL;
> +
> +                       if (PageCompound(page)) {
> +                               struct page *head_page = compound_head(page);
> +                               unsigned long head_pfn = page_to_pfn(head_page);
> +                               unsigned int alloc_pages =
> +                                       1 << compound_order(head_page);
> +
> +                               pfn = head_pfn + alloc_pages;
> +                               continue;
> +                       }
> +

I don't think the buddy allocator has compound pages.

> +                       if (page_ref_count(page)) {
> +                               pfn++;
> +                               continue;
> +                       }
> +

A ref count of 0 doesn't mean the page isn't in use. It could be in
use by something such as SLUB for instance.

> +                       if (PageBuddy(page) && page_private(page) >=
> +                           FREE_PAGE_HINTING_MIN_ORDER) {
> +                               int buddy_order = page_private(page);
> +
> +                               ret = __isolate_free_page(page, buddy_order);
> +                               if (ret) {
> +                                       isolated_pages_obj[hyp_idx].pfn = pfn;
> +                                       isolated_pages_obj[hyp_idx].order =
> +                                                               buddy_order;
> +                                       hyp_idx += 1;
> +                               }
> +                               pfn = pfn + (1 << buddy_order);
> +                               continue;
> +                       }
> +

So this is where things start to get ugly. Basically because we were
acquiring the hints when they were freed we end up needing to check
either this page, and the PFN for all of the higher order pages this
page could be a part of. Since we are currently limiting ourselves to
MAX_ORDER - 1 it shouldn't be too expensive. I don't recall if your
get_buddy_page already had that limitation coded in but we should
probably look at doing that there. Then we can just skip the PageBuddy
check up here and have it automatically start walking all pages your
original page could be a part of looking for the highest page order
that might still be free.

> +                       buddy_page = get_buddy_page(page);
> +                       if (buddy_page && page_private(buddy_page) >=
> +                           FREE_PAGE_HINTING_MIN_ORDER) {
> +                               int buddy_order = page_private(buddy_page);
> +
> +                               ret = __isolate_free_page(buddy_page,
> +                                                         buddy_order);
> +                               if (ret) {
> +                                       unsigned long buddy_pfn =
> +                                               page_to_pfn(buddy_page);
> +
> +                                       isolated_pages_obj[hyp_idx].pfn =
> +                                                               buddy_pfn;
> +                                       isolated_pages_obj[hyp_idx].order =
> +                                                               buddy_order;
> +                                       hyp_idx += 1;
> +                               }
> +                               pfn = page_to_pfn(buddy_page) +
> +                                       (1 << buddy_order);
> +                               continue;
> +                       }

This is essentially just a duplicate of the code above. As I mentioned
before it would probably make sense to just combine this block with
that one.

> +                       pfn++;
> +               }
> +               hinting_obj->free_page_arr[idx] = 0;
> +               idx++;
> +               if (idx == free_pages_idx)
> +                       spin_unlock_irqrestore(&zone_cur->lock, flags);
> +       }
>
>         hinting_obj->free_pages_idx = 0;
>         put_cpu_var(hinting_obj);
> +
> +       if (hyp_idx > 0)
> +               guest_free_page_report(isolated_pages_obj, hyp_idx);
> +       else
> +               kfree(isolated_pages_obj);
> +               /* return some logical error here*/
>  }
>
>  int if_exist(struct page *page)
> --
> 2.17.2
>