X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fhugetlb.c;h=a45d1f0691cecb63e088d02fb3ff287f025e4d78;hb=06b32f3ab6df4c7489729f94bdc7093c72681d4b;hp=cb362f761f174b926c1c41b72ec2940c5d45763d;hpb=463e7c7cf9aaf95dd05e97e1a47854fdf5454cdc;p=linux-2.6

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cb362f761f..a45d1f0691 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -140,6 +140,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	return page;
 
 fail:
+	if (vma->vm_flags & VM_MAYSHARE)
+		resv_huge_pages++;
 	spin_unlock(&hugetlb_lock);
 	return NULL;
 }
@@ -172,6 +174,17 @@ static int __init hugetlb_setup(char *s)
 }
 __setup("hugepages=", hugetlb_setup);
 
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+	int node;
+	unsigned int nr = 0;
+
+	for_each_node_mask(node, cpuset_current_mems_allowed)
+		nr += array[node];
+
+	return nr;
+}
+
 #ifdef CONFIG_SYSCTL
 static void update_and_free_page(struct page *page)
 {
@@ -313,9 +326,10 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 	pte_t entry;
 
 	entry = pte_mkwrite(pte_mkdirty(*ptep));
-	ptep_set_access_flags(vma, address, ptep, entry, 1);
-	update_mmu_cache(vma, address, entry);
-	lazy_mmu_prot_update(entry);
+	if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+		update_mmu_cache(vma, address, entry);
+		lazy_mmu_prot_update(entry);
+	}
 }
 
 
@@ -389,6 +403,8 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			continue;
 
 		page = pte_page(pte);
+		if (pte_dirty(pte))
+			set_page_dirty(page);
 		list_add(&page->lru, &page_list);
 	}
 	spin_unlock(&mm->page_table_lock);
@@ -815,6 +831,26 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
 	chg = region_chg(&inode->i_mapping->private_list, from, to);
 	if (chg < 0)
 		return chg;
+	/*
+	 * When cpuset is configured, it breaks the strict hugetlb page
+	 * reservation as the accounting is done on a global variable. Such
+	 * reservation is completely rubbish in the presence of cpuset because
+	 * the reservation is not checked against page availability for the
+	 * current cpuset. Application can still potentially OOM'ed by kernel
+	 * with lack of free htlb page in cpuset that the task is in.
+	 * Attempt to enforce strict accounting with cpuset is almost
+	 * impossible (or too ugly) because cpuset is too fluid that
+	 * task or memory node can be dynamically moved between cpusets.
+	 *
+	 * The change of semantics for shared hugetlb mapping with cpuset is
+	 * undesirable. However, in order to preserve some of the semantics,
+	 * we fall back to check against current free page availability as
+	 * a best attempt and hopefully to minimize the impact of changing
+	 * semantics that cpuset has.
+	 */
+	if (chg > cpuset_mems_nr(free_huge_pages_node))
+		return -ENOMEM;
+
 	ret = hugetlb_acct_memory(chg);
 	if (ret < 0)
 		return ret;