Re: [PATCH 2/4] alloc_contig_pages() find appropriate physical memory range

From: Minchan Kim
Date: Mon Nov 22 2010 - 06:20:25 EST


On Fri, Nov 19, 2010 at 5:14 PM, KAMEZAWA Hiroyuki
<kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:
> From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
>
> Unlike memory hotplug, at an allocation of contigous memory range, address
> may not be a problem. IOW, if a requester of memory wants to allocate 100M of
> of contigous memory, placement of allocated memory may not be a problem.
> So, "finding a range of memory which seems to be MOVABLE" is required.
>
> This patch adds a functon to isolate a length of memory within [start, end).
> This function returns a pfn which is 1st page of isolated contigous chunk
> of given length within [start, end).
>
> If no_search=true is passed as argument, start address is always same to
> the specified "base" addresss.
>
> After isolation, free memory within this area will never be allocated.
> But some pages will remain as "Used/LRU" pages. They should be dropped by
> page reclaim or migration.
>
> Changelog: 2010-11-17
>  - fixed some conding style (if-then-else)
>
> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> ---
>  mm/page_isolation.c |  146 ++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 146 insertions(+)
>
> Index: mmotm-1117/mm/page_isolation.c
> ===================================================================
> --- mmotm-1117.orig/mm/page_isolation.c
> +++ mmotm-1117/mm/page_isolation.c
> @@ -7,6 +7,7 @@
>  #include <linux/pageblock-flags.h>
>  #include <linux/memcontrol.h>
>  #include <linux/migrate.h>
> +#include <linux/memory_hotplug.h>
>  #include <linux/mm_inline.h>
>  #include "internal.h"
>
> @@ -250,3 +251,148 @@ int do_migrate_range(unsigned long start
>  out:
>        return ret;
>  }
> +
> +/*
> + * Functions for getting contiguous MOVABLE pages in a zone.
> + */
> +struct page_range {
> +       unsigned long base; /* Base address of searching contigouous block */
> +       unsigned long end;
> +       unsigned long pages;/* Length of contiguous block */

Nitpick.
You used nr_pages in other place.
I hope you use the name consistent.

> +       int align_order;
> +       unsigned long align_mask;

Does we really need this field 'align_mask'?
We can get always from align_order.

> +};
> +
> +int __get_contig_block(unsigned long pfn, unsigned long nr_pages, void *arg)
> +{
> +       struct page_range *blockinfo = arg;
> +       unsigned long end;
> +
> +       end = pfn + nr_pages;
> +       pfn = ALIGN(pfn, 1 << blockinfo->align_order);
> +       end = end & ~(MAX_ORDER_NR_PAGES - 1);
> +
> +       if (end < pfn)
> +               return 0;
> +       if (end - pfn >= blockinfo->pages) {
> +               blockinfo->base = pfn;
> +               blockinfo->end = end;
> +               return 1;
> +       }
> +       return 0;
> +}
> +
> +static void __trim_zone(struct zone *zone, struct page_range *range)
> +{
> +       unsigned long pfn;
> +       /*
> +        * skip pages which dones'nt under the zone.

typo dones'nt -> doesn't :)

> +        * There are some archs which zones are not in linear layout.
> +        */
> +       if (page_zone(pfn_to_page(range->base)) != zone) {
> +               for (pfn = range->base;
> +                       pfn < range->end;
> +                       pfn += MAX_ORDER_NR_PAGES) {
> +                       if (page_zone(pfn_to_page(pfn)) == zone)
> +                               break;
> +               }
> +               range->base = min(pfn, range->end);
> +       }
> +       /* Here, range-> base is in the zone if range->base != range->end */
> +       for (pfn = range->base;
> +            pfn < range->end;
> +            pfn += MAX_ORDER_NR_PAGES) {
> +               if (zone != page_zone(pfn_to_page(pfn))) {
> +                       pfn = pfn - MAX_ORDER_NR_PAGES;
> +                       break;
> +               }
> +       }
> +       range->end = min(pfn, range->end);
> +       return;

Remove return

> +}
> +
> +/*
> + * This function is for finding a contiguous memory block which has length
> + * of pages and MOVABLE. If it finds, make the range of pages as ISOLATED
> + * and return the first page's pfn.
> + * This checks all pages in the returned range is free of Pg_LRU. To reduce
> + * the risk of false-positive testing, lru_add_drain_all() should be called
> + * before this function to reduce pages on pagevec for zones.
> + */
> +
> +static unsigned long find_contig_block(unsigned long base,
> +               unsigned long end, unsigned long pages,
> +               int align_order, struct zone *zone)
> +{
> +       unsigned long pfn, pos;
> +       struct page_range blockinfo;
> +       int ret;
> +
> +       VM_BUG_ON(pages & (MAX_ORDER_NR_PAGES - 1));
> +       VM_BUG_ON(base & ((1 << align_order) - 1));
> +retry:
> +       blockinfo.base = base;
> +       blockinfo.end = end;
> +       blockinfo.pages = pages;
> +       blockinfo.align_order = align_order;
> +       blockinfo.align_mask = (1 << align_order) - 1;

We don't need this.

> +       /*
> +        * At first, check physical page layout and skip memory holes.
> +        */
> +       ret = walk_system_ram_range(base, end - base, &blockinfo,
> +               __get_contig_block);
> +       if (!ret)
> +               return 0;
> +       /* check contiguous pages in a zone */
> +       __trim_zone(zone, &blockinfo);
> +
> +       /*
> +        * Ok, we found contiguous memory chunk of size. Isolate it.
> +        * We just search MAX_ORDER aligned range.
> +        */
> +       for (pfn = blockinfo.base; pfn + pages <= blockinfo.end;
> +            pfn += (1 << align_order)) {
> +               struct zone *z = page_zone(pfn_to_page(pfn));
> +               if (z != zone)
> +                       continue;

Could we make sure pass __trim_zone is to satisfy whole pfn in zone
what we want.
Repeated the zone check is rather annoying.
I mean let's __get_contig_block or __trim_zone already does check zone
so that we remove the zone check in here.

> +
> +               spin_lock_irq(&z->lock);
> +               pos = pfn;
> +               /*
> +                * Check the range only contains free pages or LRU pages.
> +                */
> +               while (pos < pfn + pages) {
> +                       struct page *p;
> +
> +                       if (!pfn_valid_within(pos))
> +                               break;
> +                       p = pfn_to_page(pos);
> +                       if (PageReserved(p))
> +                               break;
> +                       if (!page_count(p)) {
> +                               if (!PageBuddy(p))
> +                                       pos++;
> +                               else
> +                                       pos += (1 << page_order(p));
> +                       } else if (PageLRU(p)) {

Could we check get_pageblock_migratetype(page) == MIGRATE_MOVABLE in
here and early bail out?

> +                               pos++;
> +                       } else
> +                               break;
> +               }
> +               spin_unlock_irq(&z->lock);
> +               if ((pos == pfn + pages)) {
> +                       if (!start_isolate_page_range(pfn, pfn + pages))
> +                               return pfn;
> +               } else/* the chunk including "pos" should be skipped */
> +                       pfn = pos & ~((1 << align_order) - 1);
> +               cond_resched();
> +       }
> +
> +       /* failed */
> +       if (blockinfo.end + pages <= end) {
> +               /* Move base address and find the next block of RAM. */
> +               base = blockinfo.end;
> +               goto retry;
> +       }
> +       return 0;

If the base is 0, isn't it impossible return pfn 0?
x86 in FLAT isn't impossible but I think some architecture might be possible.
Just guessing.

How about returning negative value and return first page pfn and last
page pfn as out parameter base, end?

> +}
>
>



--
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/