diff mbox series

[3/7] mm/page_alloc: Add a bulk page allocator

Message ID 20210312154331.32229-4-mgorman@techsingularity.net (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series Introduce a bulk order-0 page allocator with two in-tree users | expand

Checks

Context Check Description
netdev/tree_selection success Guessing tree name failed - patch did not apply

Commit Message

Mel Gorman March 12, 2021, 3:43 p.m. UTC
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. They can be freed in bulk using
free_pages_bulk().

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.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/linux/gfp.h |  12 +++++
 mm/page_alloc.c     | 116 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 128 insertions(+)

Comments

Vlastimil Babka March 19, 2021, 6:18 p.m. UTC | #1
On 3/12/21 4:43 PM, Mel Gorman wrote:
> 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. They can be freed in bulk using
> free_pages_bulk().
> 
> 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.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Vlastimil Babka <vbabka@suse.cz>

Although maybe premature, if it changes significantly due to the users'
performance feedback, let's see :)

Some nits below:

...

> @@ -4963,6 +4978,107 @@ static inline bool prepare_alloc_pages(gfp_t gfp, unsigned int order,
>  	return true;
>  }
>  
> +/*
> + * This is a batched version of the page allocator that attempts to
> + * allocate nr_pages quickly from the preferred zone and add them to list.
> + *
> + * Returns the number of pages allocated.
> + */
> +int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
> +			nodemask_t *nodemask, int nr_pages,
> +			struct list_head *alloc_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;
> +	int allocated = 0;
> +
> +	if (WARN_ON_ONCE(nr_pages <= 0))
> +		return 0;
> +
> +	if (nr_pages == 1)
> +		goto failed;
> +
> +	/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
> +	if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac,
> +	&alloc_gfp, &alloc_flags))

Unusual identation here.

> +		return 0;
> +	gfp = alloc_gfp;
> +
> +	/* Find an allowed local zone that meets the high 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 (!zone)
> +		return 0;

Why not also "goto failed;" here?
Mel Gorman March 22, 2021, 8:30 a.m. UTC | #2
On Fri, Mar 19, 2021 at 07:18:32PM +0100, Vlastimil Babka wrote:
> On 3/12/21 4:43 PM, Mel Gorman wrote:
> > 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. They can be freed in bulk using
> > free_pages_bulk().
> > 
> > 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.
> > 
> > Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> 
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> 
> Although maybe premature, if it changes significantly due to the users'
> performance feedback, let's see :)
> 

Indeed. The next version will have no users so that Jesper and Chuck
can check if an array-based or LRU based version is better. There were
also bugs such as broken accounting of stats that had to be fixed which
increases overhead.

> Some nits below:
> 
> ...
> 
> > @@ -4963,6 +4978,107 @@ static inline bool prepare_alloc_pages(gfp_t gfp, unsigned int order,
> >  	return true;
> >  }
> >  
> > +/*
> > + * This is a batched version of the page allocator that attempts to
> > + * allocate nr_pages quickly from the preferred zone and add them to list.
> > + *
> > + * Returns the number of pages allocated.
> > + */
> > +int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
> > +			nodemask_t *nodemask, int nr_pages,
> > +			struct list_head *alloc_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;
> > +	int allocated = 0;
> > +
> > +	if (WARN_ON_ONCE(nr_pages <= 0))
> > +		return 0;
> > +
> > +	if (nr_pages == 1)
> > +		goto failed;
> > +
> > +	/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
> > +	if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac,
> > +	&alloc_gfp, &alloc_flags))
> 
> Unusual identation here.
> 

Fixed

> > +		return 0;
> > +	gfp = alloc_gfp;
> > +
> > +	/* Find an allowed local zone that meets the high 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 (!zone)
> > +		return 0;
> 
> Why not also "goto failed;" here?

Good question. When first written, it was because the zone search for the
normal allocator was almost certainly going to fail to find a zone and
it was expected that callers would prefer to fail fast over blocking.
Now we know that sunrpc can sleep on a failing allocation and it would
be better to enter the single page allocator and reclaim pages instead of
"sleep and hope for the best".
diff mbox series

Patch

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0a88f84b08f4..e2cd98dba72e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -518,6 +518,17 @@  static inline int arch_make_page_accessible(struct page *page)
 struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask);
 
+int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
+				nodemask_t *nodemask, int nr_pages,
+				struct list_head *list);
+
+/* Bulk allocate order-0 pages */
+static inline unsigned long
+alloc_pages_bulk(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
+{
+	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list);
+}
+
 /*
  * Allocate pages, preferring the node given as nid. The node must be valid and
  * online. For more general interface, see alloc_pages_node().
@@ -581,6 +592,7 @@  void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
+extern void free_pages_bulk(struct list_head *list);
 
 struct page_frag_cache;
 extern void __page_frag_cache_drain(struct page *page, unsigned int count);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 880b1d6368bd..f48f94375b66 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4436,6 +4436,21 @@  static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
 	}
 }
 
+/* Drop reference counts and free order-0 pages from a list. */
+void free_pages_bulk(struct list_head *list)
+{
+	struct page *page, *next;
+
+	list_for_each_entry_safe(page, next, list, lru) {
+		trace_mm_page_free_batched(page);
+		if (put_page_testzero(page)) {
+			list_del(&page->lru);
+			__free_pages_ok(page, 0, FPI_NONE);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(free_pages_bulk);
+
 static inline unsigned int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
@@ -4963,6 +4978,107 @@  static inline bool prepare_alloc_pages(gfp_t gfp, unsigned int order,
 	return true;
 }
 
+/*
+ * This is a batched version of the page allocator that attempts to
+ * allocate nr_pages quickly from the preferred zone and add them to list.
+ *
+ * Returns the number of pages allocated.
+ */
+int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
+			nodemask_t *nodemask, int nr_pages,
+			struct list_head *alloc_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;
+	int allocated = 0;
+
+	if (WARN_ON_ONCE(nr_pages <= 0))
+		return 0;
+
+	if (nr_pages == 1)
+		goto failed;
+
+	/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
+	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 high 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 (!zone)
+		return 0;
+
+	/* 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;
+		}
+
+		list_add(&page->lru, alloc_list);
+		allocated++;
+	}
+
+	__count_zid_vm_events(PGALLOC, zone_idx(zone), allocated);
+	zone_statistics(zone, zone);
+
+	local_irq_restore(flags);
+
+	/* Prep page with IRQs enabled to reduce disabled times */
+	list_for_each_entry(page, alloc_list, lru)
+		prep_new_page(page, 0, gfp, 0);
+
+	return allocated;
+
+failed_irq:
+	local_irq_restore(flags);
+
+failed:
+	page = __alloc_pages(gfp, 0, preferred_nid, nodemask);
+	if (page) {
+		list_add(&page->lru, alloc_list);
+		allocated = 1;
+	}
+
+	return allocated;
+}
+EXPORT_SYMBOL_GPL(__alloc_pages_bulk);
+
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */