[linux-yocto] [PATCH 15/23] hugetlb: add support for gigantic page allocation at runtime
Yang Shi
yang.shi at windriver.com
Wed Jul 30 19:16:19 PDT 2014
From: Luiz Capitulino <lcapitulino at redhat.com>
commit 944d9fec8d7aee3f2e16573e9b6a16634b33f403 upstream
HugeTLB is limited to allocating hugepages whose size are less than
MAX_ORDER order. This is so because HugeTLB allocates hugepages via the
buddy allocator. Gigantic pages (that is, pages whose size is greater
than MAX_ORDER order) have to be allocated at boottime.
However, boottime allocation has at least two serious problems. First,
it doesn't support NUMA and second, gigantic pages allocated at boottime
can't be freed.
This commit solves both issues by adding support for allocating gigantic
pages during runtime. It works just like regular sized hugepages,
meaning that the interface in sysfs is the same, it supports NUMA, and
gigantic pages can be freed.
For example, on x86_64 gigantic pages are 1GB big. To allocate two 1G
gigantic pages on node 1, one can do:
# echo 2 > \
/sys/devices/system/node/node1/hugepages/hugepages-1048576kB/nr_hugepages
And to free them all:
# echo 0 > \
/sys/devices/system/node/node1/hugepages/hugepages-1048576kB/nr_hugepages
The one problem with gigantic page allocation at runtime is that it
can't be serviced by the buddy allocator. To overcome that problem,
this commit scans all zones from a node looking for a large enough
contiguous region. When one is found, it's allocated by using CMA, that
is, we call alloc_contig_range() to do the actual allocation. For
example, on x86_64 we scan all zones looking for a 1GB contiguous
region. When one is found, it's allocated by alloc_contig_range().
One expected issue with that approach is that such gigantic contiguous
regions tend to vanish as runtime goes by. The best way to avoid this
for now is to make gigantic page allocations very early during system
boot, say from a init script. Other possible optimization include using
compaction, which is supported by CMA but is not explicitly used by this
commit.
It's also important to note the following:
1. Gigantic pages allocated at boottime by the hugepages= command-line
option can be freed at runtime just fine
2. This commit adds support for gigantic pages only to x86_64. The
reason is that I don't have access to nor experience with other archs.
The code is arch indepedent though, so it should be simple to add
support to different archs
3. I didn't add support for hugepage overcommit, that is allocating
a gigantic page on demand when
/proc/sys/vm/nr_overcommit_hugepages > 0. The reason is that I don't
think it's reasonable to do the hard and long work required for
allocating a gigantic page at fault time. But it should be simple
to add this if wanted
[akpm at linux-foundation.org: coding-style fixes]
Signed-off-by: Luiz Capitulino <lcapitulino at redhat.com>
Reviewed-by: Davidlohr Bueso <davidlohr at hp.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
Reviewed-by: Zhang Yanfei <zhangyanfei at cn.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki at jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange at redhat.com>
Cc: David Rientjes <rientjes at google.com>
Cc: Marcelo Tosatti <mtosatti at redhat.com>
Cc: Naoya Horiguchi <n-horiguchi at ah.jp.nec.com>
Cc: Rik van Riel <riel at redhat.com>
Cc: Yinghai Lu <yinghai at kernel.org>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Yang Shi <yang.shi at windriver.com>
---
mm/hugetlb.c | 166 +++++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 155 insertions(+), 11 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 148ad85..b46f75d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -679,11 +679,150 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
((node = hstate_next_node_to_free(hs, mask)) || 1); \
nr_nodes--)
+#if defined(CONFIG_CMA) && defined(CONFIG_X86_64)
+static void destroy_compound_gigantic_page(struct page *page,
+ unsigned long order)
+{
+ int i;
+ int nr_pages = 1 << order;
+ struct page *p = page + 1;
+
+ for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+ __ClearPageTail(p);
+ set_page_refcounted(p);
+ p->first_page = NULL;
+ }
+
+ set_compound_order(page, 0);
+ __ClearPageHead(page);
+}
+
+static void free_gigantic_page(struct page *page, unsigned order)
+{
+ free_contig_range(page_to_pfn(page), 1 << order);
+}
+
+static int __alloc_gigantic_page(unsigned long start_pfn,
+ unsigned long nr_pages)
+{
+ unsigned long end_pfn = start_pfn + nr_pages;
+ return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+}
+
+static bool pfn_range_valid_gigantic(unsigned long start_pfn,
+ unsigned long nr_pages)
+{
+ unsigned long i, end_pfn = start_pfn + nr_pages;
+ struct page *page;
+
+ for (i = start_pfn; i < end_pfn; i++) {
+ if (!pfn_valid(i))
+ return false;
+
+ page = pfn_to_page(i);
+
+ if (PageReserved(page))
+ return false;
+
+ if (page_count(page) > 0)
+ return false;
+
+ if (PageHuge(page))
+ return false;
+ }
+
+ return true;
+}
+
+static bool zone_spans_last_pfn(const struct zone *zone,
+ unsigned long start_pfn, unsigned long nr_pages)
+{
+ unsigned long last_pfn = start_pfn + nr_pages - 1;
+ return zone_spans_pfn(zone, last_pfn);
+}
+
+static struct page *alloc_gigantic_page(int nid, unsigned order)
+{
+ unsigned long nr_pages = 1 << order;
+ unsigned long ret, pfn, flags;
+ struct zone *z;
+
+ z = NODE_DATA(nid)->node_zones;
+ for (; z - NODE_DATA(nid)->node_zones < MAX_NR_ZONES; z++) {
+ spin_lock_irqsave(&z->lock, flags);
+
+ pfn = ALIGN(z->zone_start_pfn, nr_pages);
+ while (zone_spans_last_pfn(z, pfn, nr_pages)) {
+ if (pfn_range_valid_gigantic(pfn, nr_pages)) {
+ /*
+ * We release the zone lock here because
+ * alloc_contig_range() will also lock the zone
+ * at some point. If there's an allocation
+ * spinning on this lock, it may win the race
+ * and cause alloc_contig_range() to fail...
+ */
+ spin_unlock_irqrestore(&z->lock, flags);
+ ret = __alloc_gigantic_page(pfn, nr_pages);
+ if (!ret)
+ return pfn_to_page(pfn);
+ spin_lock_irqsave(&z->lock, flags);
+ }
+ pfn += nr_pages;
+ }
+
+ spin_unlock_irqrestore(&z->lock, flags);
+ }
+
+ return NULL;
+}
+
+static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
+static void prep_compound_gigantic_page(struct page *page, unsigned long order);
+
+static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid)
+{
+ struct page *page;
+
+ page = alloc_gigantic_page(nid, huge_page_order(h));
+ if (page) {
+ prep_compound_gigantic_page(page, huge_page_order(h));
+ prep_new_huge_page(h, page, nid);
+ }
+
+ return page;
+}
+
+static int alloc_fresh_gigantic_page(struct hstate *h,
+ nodemask_t *nodes_allowed)
+{
+ struct page *page = NULL;
+ int nr_nodes, node;
+
+ for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+ page = alloc_fresh_gigantic_page_node(h, node);
+ if (page)
+ return 1;
+ }
+
+ return 0;
+}
+
+static inline bool gigantic_page_supported(void) { return true; }
+#else
+static inline bool gigantic_page_supported(void) { return false; }
+static inline void free_gigantic_page(struct page *page, unsigned order) { }
+static inline void destroy_compound_gigantic_page(struct page *page,
+ unsigned long order) { }
+static inline int alloc_fresh_gigantic_page(struct hstate *h,
+ nodemask_t *nodes_allowed) { return 0; }
+#endif
+
static void update_and_free_page(struct hstate *h, struct page *page)
{
int i;
- VM_BUG_ON(hstate_is_gigantic(h));
+ if (hstate_is_gigantic(h) && !gigantic_page_supported())
+ return;
h->nr_huge_pages--;
h->nr_huge_pages_node[page_to_nid(page)]--;
@@ -696,8 +835,13 @@ static void update_and_free_page(struct hstate *h, struct page *page)
VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
set_compound_page_dtor(page, NULL);
set_page_refcounted(page);
- arch_release_hugepage(page);
- __free_pages(page, huge_page_order(h));
+ if (hstate_is_gigantic(h)) {
+ destroy_compound_gigantic_page(page, huge_page_order(h));
+ free_gigantic_page(page, huge_page_order(h));
+ } else {
+ arch_release_hugepage(page);
+ __free_pages(page, huge_page_order(h));
+ }
}
struct hstate *size_to_hstate(unsigned long size)
@@ -736,7 +880,7 @@ static void free_huge_page(struct page *page)
if (restore_reserve)
h->resv_huge_pages++;
- if (h->surplus_huge_pages_node[nid] && !hstate_is_gigantic(h)) {
+ if (h->surplus_huge_pages_node[nid]) {
/* remove the page from active list */
list_del(&page->lru);
update_and_free_page(h, page);
@@ -840,9 +984,6 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
struct page *page;
- if (hstate_is_gigantic(h))
- return NULL;
-
page = alloc_pages_exact_node(nid,
htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN,
@@ -1477,7 +1618,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
{
unsigned long min_count, ret;
- if (hstate_is_gigantic(h))
+ if (hstate_is_gigantic(h) && !gigantic_page_supported())
return h->max_huge_pages;
/*
@@ -1504,7 +1645,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
* and reducing the surplus.
*/
spin_unlock(&hugetlb_lock);
- ret = alloc_fresh_huge_page(h, nodes_allowed);
+ if (hstate_is_gigantic(h))
+ ret = alloc_fresh_gigantic_page(h, nodes_allowed);
+ else
+ ret = alloc_fresh_huge_page(h, nodes_allowed);
spin_lock(&hugetlb_lock);
if (!ret)
goto out;
@@ -1604,7 +1748,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
goto out;
h = kobj_to_hstate(kobj, &nid);
- if (hstate_is_gigantic(h)) {
+ if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
err = -EINVAL;
goto out;
}
@@ -2111,7 +2255,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
tmp = h->max_huge_pages;
- if (write && hstate_is_gigantic(h))
+ if (write && hstate_is_gigantic(h) && !gigantic_page_supported())
return -EINVAL;
table->data = &tmp;
--
2.0.2
More information about the linux-yocto
mailing list