summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorAdam Litke <agl@us.ibm.com>2007-10-16 01:26:18 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-10-16 09:43:02 -0700
commit7893d1d505d59db9d4f35165c8b6d3c6dff40a32 (patch)
tree6bea3b41e111b1d1774980296a032012a3926e9c /mm
parent6af2acb6619688046039234f716fd003e6ed2b3f (diff)
downloadlinux-stable-7893d1d505d59db9d4f35165c8b6d3c6dff40a32.tar.gz
linux-stable-7893d1d505d59db9d4f35165c8b6d3c6dff40a32.tar.bz2
linux-stable-7893d1d505d59db9d4f35165c8b6d3c6dff40a32.zip
hugetlb: Try to grow hugetlb pool for MAP_PRIVATE mappings
Because we overcommit hugepages for MAP_PRIVATE mappings, it is possible that the hugetlb pool will be exhausted or completely reserved when a hugepage is needed to satisfy a page fault. Before killing the process in this situation, try to allocate a hugepage directly from the buddy allocator. The explicitly configured pool size becomes a low watermark. When dynamically grown, the allocated huge pages are accounted as a surplus over the watermark. As huge pages are freed on a node, surplus pages are released to the buddy allocator so that the pool will shrink back to the watermark. Surplus accounting also allows for friendlier explicit pool resizing. When shrinking a pool that is fully in-use, increase the surplus so pages will be returned to the buddy allocator as soon as they are freed. When growing a pool that has a surplus, consume the surplus first and then allocate new pages. Signed-off-by: Adam Litke <agl@us.ibm.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Dave McCracken <dave.mccracken@oracle.com> Cc: William Irwin <bill.irwin@oracle.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Ken Chen <kenchen@google.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> 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/hugetlb.c139
1 files changed, 125 insertions, 14 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba029d640740..8768e5250323 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -23,10 +23,12 @@
const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
+static unsigned long surplus_huge_pages;
unsigned long max_huge_pages;
static struct list_head hugepage_freelists[MAX_NUMNODES];
static unsigned int nr_huge_pages_node[MAX_NUMNODES];
static unsigned int free_huge_pages_node[MAX_NUMNODES];
+static unsigned int surplus_huge_pages_node[MAX_NUMNODES];
static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;
@@ -109,15 +111,57 @@ static void update_and_free_page(struct page *page)
static void free_huge_page(struct page *page)
{
- BUG_ON(page_count(page));
+ int nid = page_to_nid(page);
+ BUG_ON(page_count(page));
INIT_LIST_HEAD(&page->lru);
spin_lock(&hugetlb_lock);
- enqueue_huge_page(page);
+ if (surplus_huge_pages_node[nid]) {
+ update_and_free_page(page);
+ surplus_huge_pages--;
+ surplus_huge_pages_node[nid]--;
+ } else {
+ enqueue_huge_page(page);
+ }
spin_unlock(&hugetlb_lock);
}
+/*
+ * Increment or decrement surplus_huge_pages. Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(int delta)
+{
+ static int prev_nid;
+ int nid = prev_nid;
+ int ret = 0;
+
+ VM_BUG_ON(delta != -1 && delta != 1);
+ do {
+ nid = next_node(nid, node_online_map);
+ if (nid == MAX_NUMNODES)
+ nid = first_node(node_online_map);
+
+ /* To shrink on this node, there must be a surplus page */
+ if (delta < 0 && !surplus_huge_pages_node[nid])
+ continue;
+ /* Surplus cannot exceed the total number of pages */
+ if (delta > 0 && surplus_huge_pages_node[nid] >=
+ nr_huge_pages_node[nid])
+ continue;
+
+ surplus_huge_pages += delta;
+ surplus_huge_pages_node[nid] += delta;
+ ret = 1;
+ break;
+ } while (nid != prev_nid);
+
+ prev_nid = nid;
+ return ret;
+}
+
static int alloc_fresh_huge_page(void)
{
static int prev_nid;
@@ -150,10 +194,30 @@ static int alloc_fresh_huge_page(void)
return 0;
}
+static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
+ unsigned long address)
+{
+ struct page *page;
+
+ page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
+ HUGETLB_PAGE_ORDER);
+ if (page) {
+ set_compound_page_dtor(page, free_huge_page);
+ spin_lock(&hugetlb_lock);
+ nr_huge_pages++;
+ nr_huge_pages_node[page_to_nid(page)]++;
+ surplus_huge_pages++;
+ surplus_huge_pages_node[page_to_nid(page)]++;
+ spin_unlock(&hugetlb_lock);
+ }
+
+ return page;
+}
+
static struct page *alloc_huge_page(struct vm_area_struct *vma,
unsigned long addr)
{
- struct page *page;
+ struct page *page = NULL;
spin_lock(&hugetlb_lock);
if (vma->vm_flags & VM_MAYSHARE)
@@ -173,7 +237,16 @@ fail:
if (vma->vm_flags & VM_MAYSHARE)
resv_huge_pages++;
spin_unlock(&hugetlb_lock);
- return NULL;
+
+ /*
+ * Private mappings do not use reserved huge pages so the allocation
+ * may have failed due to an undersized hugetlb pool. Try to grab a
+ * surplus huge page from the buddy allocator.
+ */
+ if (!(vma->vm_flags & VM_MAYSHARE))
+ page = alloc_buddy_huge_page(vma, addr);
+
+ return page;
}
static int __init hugetlb_init(void)
@@ -241,26 +314,62 @@ static inline void try_to_free_low(unsigned long count)
}
#endif
+#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages)
static unsigned long set_max_huge_pages(unsigned long count)
{
- while (count > nr_huge_pages) {
- if (!alloc_fresh_huge_page())
- return nr_huge_pages;
- }
- if (count >= nr_huge_pages)
- return nr_huge_pages;
+ unsigned long min_count, ret;
+ /*
+ * Increase the pool size
+ * First take pages out of surplus state. Then make up the
+ * remaining difference by allocating fresh huge pages.
+ */
spin_lock(&hugetlb_lock);
- count = max(count, resv_huge_pages);
- try_to_free_low(count);
- while (count < nr_huge_pages) {
+ while (surplus_huge_pages && count > persistent_huge_pages) {
+ if (!adjust_pool_surplus(-1))
+ break;
+ }
+
+ while (count > persistent_huge_pages) {
+ int ret;
+ /*
+ * If this allocation races such that we no longer need the
+ * page, free_huge_page will handle it by freeing the page
+ * and reducing the surplus.
+ */
+ spin_unlock(&hugetlb_lock);
+ ret = alloc_fresh_huge_page();
+ spin_lock(&hugetlb_lock);
+ if (!ret)
+ goto out;
+
+ }
+ if (count >= persistent_huge_pages)
+ goto out;
+
+ /*
+ * Decrease the pool size
+ * First return free pages to the buddy allocator (being careful
+ * to keep enough around to satisfy reservations). Then place
+ * pages into surplus state as needed so the pool will shrink
+ * to the desired size as pages become free.
+ */
+ min_count = max(count, resv_huge_pages);
+ try_to_free_low(min_count);
+ while (min_count < persistent_huge_pages) {
struct page *page = dequeue_huge_page(NULL, 0);
if (!page)
break;
update_and_free_page(page);
}
+ while (count < persistent_huge_pages) {
+ if (!adjust_pool_surplus(1))
+ break;
+ }
+out:
+ ret = persistent_huge_pages;
spin_unlock(&hugetlb_lock);
- return nr_huge_pages;
+ return ret;
}
int hugetlb_sysctl_handler(struct ctl_table *table, int write,
@@ -292,10 +401,12 @@ int hugetlb_report_meminfo(char *buf)
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
"HugePages_Rsvd: %5lu\n"
+ "HugePages_Surp: %5lu\n"
"Hugepagesize: %5lu kB\n",
nr_huge_pages,
free_huge_pages,
resv_huge_pages,
+ surplus_huge_pages,
HPAGE_SIZE/1024);
}