X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fhugetlb.c;h=508707704d2cb714968a779e128084d640afc439;hb=e8788c0cce63e0cc8689a123d1ce0af1e28cd583;hp=da8a211414c94950014365f745f86c5e3e67dfc9;hpb=1e8f889b10d8d2223105719e36ce45688fedbd59;p=linux-2.6

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index da8a211414..508707704d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -11,6 +11,9 @@
 #include <linux/highmem.h>
 #include <linux/nodemask.h>
 #include <linux/pagemap.h>
+#include <linux/mempolicy.h>
+#include <linux/cpuset.h>
+
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
@@ -36,18 +39,22 @@ static void enqueue_huge_page(struct page *page)
 	free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(void)
+static struct page *dequeue_huge_page(struct vm_area_struct *vma,
+				unsigned long address)
 {
 	int nid = numa_node_id();
 	struct page *page = NULL;
+	struct zonelist *zonelist = huge_zonelist(vma, address);
+	struct zone **z;
 
-	if (list_empty(&hugepage_freelists[nid])) {
-		for (nid = 0; nid < MAX_NUMNODES; ++nid)
-			if (!list_empty(&hugepage_freelists[nid]))
-				break;
+	for (z = zonelist->zones; *z; z++) {
+		nid = (*z)->zone_pgdat->node_id;
+		if (cpuset_zone_allowed(*z, GFP_HIGHUSER) &&
+		    !list_empty(&hugepage_freelists[nid]))
+			break;
 	}
-	if (nid >= 0 && nid < MAX_NUMNODES &&
-	    !list_empty(&hugepage_freelists[nid])) {
+
+	if (*z) {
 		page = list_entry(hugepage_freelists[nid].next,
 				  struct page, lru);
 		list_del(&page->lru);
@@ -78,29 +85,29 @@ void free_huge_page(struct page *page)
 	BUG_ON(page_count(page));
 
 	INIT_LIST_HEAD(&page->lru);
-	page[1].mapping = NULL;
+	page[1].lru.next = NULL;			/* reset dtor */
 
 	spin_lock(&hugetlb_lock);
 	enqueue_huge_page(page);
 	spin_unlock(&hugetlb_lock);
 }
 
-struct page *alloc_huge_page(void)
+struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *page;
 	int i;
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page();
+	page = dequeue_huge_page(vma, addr);
 	if (!page) {
 		spin_unlock(&hugetlb_lock);
 		return NULL;
 	}
 	spin_unlock(&hugetlb_lock);
 	set_page_count(page, 1);
-	page[1].mapping = (void *)free_huge_page;
+	page[1].lru.next = (void *)free_huge_page;	/* set dtor */
 	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); ++i)
-		clear_highpage(&page[i]);
+		clear_user_highpage(&page[i], addr);
 	return page;
 }
 
@@ -194,7 +201,7 @@ static unsigned long set_max_huge_pages(unsigned long count)
 	spin_lock(&hugetlb_lock);
 	try_to_free_low(count);
 	while (count < nr_huge_pages) {
-		struct page *page = dequeue_huge_page();
+		struct page *page = dequeue_huge_page(NULL, 0);
 		if (!page)
 			break;
 		update_and_free_page(page);
@@ -363,42 +370,6 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	flush_tlb_range(vma, start, end);
 }
 
-static struct page *find_or_alloc_huge_page(struct address_space *mapping,
-				unsigned long idx, int shared)
-{
-	struct page *page;
-	int err;
-
-retry:
-	page = find_lock_page(mapping, idx);
-	if (page)
-		goto out;
-
-	if (hugetlb_get_quota(mapping))
-		goto out;
-	page = alloc_huge_page();
-	if (!page) {
-		hugetlb_put_quota(mapping);
-		goto out;
-	}
-
-	if (shared) {
-		err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
-		if (err) {
-			put_page(page);
-			hugetlb_put_quota(mapping);
-			if (err == -EEXIST)
-				goto retry;
-			page = NULL;
-		}
-	} else {
-		/* Caller expects a locked page */
-		lock_page(page);
-	}
-out:
-	return page;
-}
-
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte)
 {
@@ -416,16 +387,11 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	page_cache_get(old_page);
-	new_page = alloc_huge_page();
+	new_page = alloc_huge_page(vma, address);
 
 	if (!new_page) {
 		page_cache_release(old_page);
-
-		/* Logically this is OOM, not a SIGBUS, but an OOM
-		 * could cause the kernel to go killing other
-		 * processes which won't help the hugepage situation
-		 * at all (?) */
-		return VM_FAULT_SIGBUS;
+		return VM_FAULT_OOM;
 	}
 
 	spin_unlock(&mm->page_table_lock);
@@ -465,12 +431,32 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * Use page lock to guard against racing truncation
 	 * before we get page_table_lock.
 	 */
-	page = find_or_alloc_huge_page(mapping, idx,
-			vma->vm_flags & VM_SHARED);
-	if (!page)
-		goto out;
+retry:
+	page = find_lock_page(mapping, idx);
+	if (!page) {
+		if (hugetlb_get_quota(mapping))
+			goto out;
+		page = alloc_huge_page(vma, address);
+		if (!page) {
+			hugetlb_put_quota(mapping);
+			ret = VM_FAULT_OOM;
+			goto out;
+		}
 
-	BUG_ON(!PageLocked(page));
+		if (vma->vm_flags & VM_SHARED) {
+			int err;
+
+			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+			if (err) {
+				put_page(page);
+				hugetlb_put_quota(mapping);
+				if (err == -EEXIST)
+					goto retry;
+				goto out;
+			}
+		} else
+			lock_page(page);
+	}
 
 	spin_lock(&mm->page_table_lock);
 	size = i_size_read(mapping->host) >> HPAGE_SHIFT;