diff options
author | Mel Gorman <mgorman@techsingularity.net> | 2021-04-30 09:01:45 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-04-30 21:20:43 +0300 |
commit | 387ba26fb1cb9be9e35dc14a6d97188e916eda05 (patch) | |
tree | 179d9525438b16f795ba865b02a7052151219990 /mm | |
parent | cb66bede617581309883432e9a633e8cade2a36e (diff) | |
download | linux-387ba26fb1cb9be9e35dc14a6d97188e916eda05.tar.xz |
mm/page_alloc: add a bulk page allocator
This patch adds a new page allocator interface via alloc_pages_bulk, and
__alloc_pages_bulk_nodemask. A caller requests a number of pages to be
allocated and added to a list.
The API is not guaranteed to return the requested number of pages and
may fail if the preferred allocation zone has limited free memory, the
cpuset changes during the allocation or page debugging decides to fail
an allocation. It's up to the caller to request more pages in batch if
necessary.
Note that this implementation is not very efficient and could be
improved but it would require refactoring. The intent is to make it
available early to determine what semantics are required by different
callers. Once the full semantics are nailed down, it can be refactored.
[mgorman@techsingularity.net: fix alloc_pages_bulk() return type, per Matthew]
Link: https://lkml.kernel.org/r/20210325123713.GQ3697@techsingularity.net
[mgorman@techsingularity.net: fix uninit var warning]
Link: https://lkml.kernel.org/r/20210330114847.GX3697@techsingularity.net
[mgorman@techsingularity.net: fix comment, per Vlastimil]
Link: https://lkml.kernel.org/r/20210412110255.GV3697@techsingularity.net
Link: https://lkml.kernel.org/r/20210325114228.27719-3-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Alexander Lobakin <alobakin@pm.me>
Tested-by: Colin Ian King <colin.king@canonical.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/page_alloc.c | 118 |
1 files changed, 118 insertions, 0 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fd283d9b6a4d..d8209d48a543 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5007,6 +5007,124 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, } /* + * __alloc_pages_bulk - Allocate a number of order-0 pages to a list + * @gfp: GFP flags for the allocation + * @preferred_nid: The preferred NUMA node ID to allocate from + * @nodemask: Set of nodes to allocate from, may be NULL + * @nr_pages: The number of pages desired on the list + * @page_list: List to store the allocated pages + * + * This is a batched version of the page allocator that attempts to + * allocate nr_pages quickly and add them to a list. + * + * Returns the number of pages on the list. + */ +unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, + nodemask_t *nodemask, int nr_pages, + struct list_head *page_list) +{ + struct page *page; + unsigned long flags; + struct zone *zone; + struct zoneref *z; + struct per_cpu_pages *pcp; + struct list_head *pcp_list; + struct alloc_context ac; + gfp_t alloc_gfp; + unsigned int alloc_flags = ALLOC_WMARK_LOW; + int allocated = 0; + + if (WARN_ON_ONCE(nr_pages <= 0)) + return 0; + + /* Use the single page allocator for one page. */ + if (nr_pages == 1) + goto failed; + + /* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */ + gfp &= gfp_allowed_mask; + alloc_gfp = gfp; + if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) + return 0; + gfp = alloc_gfp; + + /* Find an allowed local zone that meets the low watermark. */ + for_each_zone_zonelist_nodemask(zone, z, ac.zonelist, ac.highest_zoneidx, ac.nodemask) { + unsigned long mark; + + if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp)) { + continue; + } + + if (nr_online_nodes > 1 && zone != ac.preferred_zoneref->zone && + zone_to_nid(zone) != zone_to_nid(ac.preferred_zoneref->zone)) { + goto failed; + } + + mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages; + if (zone_watermark_fast(zone, 0, mark, + zonelist_zone_idx(ac.preferred_zoneref), + alloc_flags, gfp)) { + break; + } + } + + /* + * If there are no allowed local zones that meets the watermarks then + * try to allocate a single page and reclaim if necessary. + */ + if (!zone) + goto failed; + + /* Attempt the batch allocation */ + local_irq_save(flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + pcp_list = &pcp->lists[ac.migratetype]; + + while (allocated < nr_pages) { + page = __rmqueue_pcplist(zone, ac.migratetype, alloc_flags, + pcp, pcp_list); + if (!page) { + /* Try and get at least one page */ + if (!allocated) + goto failed_irq; + break; + } + + /* + * Ideally this would be batched but the best way to do + * that cheaply is to first convert zone_statistics to + * be inaccurate per-cpu counter like vm_events to avoid + * a RMW cycle then do the accounting with IRQs enabled. + */ + __count_zid_vm_events(PGALLOC, zone_idx(zone), 1); + zone_statistics(ac.preferred_zoneref->zone, zone); + + prep_new_page(page, 0, gfp, 0); + list_add(&page->lru, page_list); + allocated++; + } + + local_irq_restore(flags); + + return allocated; + +failed_irq: + local_irq_restore(flags); + +failed: + page = __alloc_pages(gfp, 0, preferred_nid, nodemask); + if (page) { + list_add(&page->lru, page_list); + allocated = 1; + } + + return allocated; +} +EXPORT_SYMBOL_GPL(__alloc_pages_bulk); + +/* * This is the 'heart' of the zoned buddy allocator. */ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, |