X-Git-Url: http://git.samba.org/samba.git/?a=blobdiff_plain;f=mm%2Fhugetlb.c;h=1a5642074e342532f4a844ed0d2fdc86bd9b5de9;hb=b370b08274a25cf1e2015fb7ce65c43173c8156f;hp=abe1e9f2a942281df9707530610dc0b3c349ac04;hpb=8cde045c7ee97573be6ce495b8f7c918182a2c7a;p=sfrench%2Fcifs-2.6.git

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index abe1e9f2a942..1a5642074e34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -31,7 +31,7 @@ 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;
-int hugetlb_dynamic_pool;
+unsigned long nr_overcommit_huge_pages;
 static int hugetlb_next_nid;
 
 /*
@@ -227,22 +227,58 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
 						unsigned long address)
 {
 	struct page *page;
+	unsigned int nid;
 
-	/* Check if the dynamic pool is enabled */
-	if (!hugetlb_dynamic_pool)
+	/*
+	 * Assume we will successfully allocate the surplus page to
+	 * prevent racing processes from causing the surplus to exceed
+	 * overcommit
+	 *
+	 * This however introduces a different race, where a process B
+	 * tries to grow the static hugepage pool while alloc_pages() is
+	 * called by process A. B will only examine the per-node
+	 * counters in determining if surplus huge pages can be
+	 * converted to normal huge pages in adjust_pool_surplus(). A
+	 * won't be able to increment the per-node counter, until the
+	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
+	 * no more huge pages can be converted from surplus to normal
+	 * state (and doesn't try to convert again). Thus, we have a
+	 * case where a surplus huge page exists, the pool is grown, and
+	 * the surplus huge page still exists after, even though it
+	 * should just have been converted to a normal huge page. This
+	 * does not leak memory, though, as the hugepage will be freed
+	 * once it is out of use. It also does not allow the counters to
+	 * go out of whack in adjust_pool_surplus() as we don't modify
+	 * the node values until we've gotten the hugepage and only the
+	 * per-node value is checked there.
+	 */
+	spin_lock(&hugetlb_lock);
+	if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+		spin_unlock(&hugetlb_lock);
 		return NULL;
+	} else {
+		nr_huge_pages++;
+		surplus_huge_pages++;
+	}
+	spin_unlock(&hugetlb_lock);
 
 	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
 					HUGETLB_PAGE_ORDER);
+
+	spin_lock(&hugetlb_lock);
 	if (page) {
+		nid = page_to_nid(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);
+		/*
+		 * We incremented the global counters already
+		 */
+		nr_huge_pages_node[nid]++;
+		surplus_huge_pages_node[nid]++;
+	} else {
+		nr_huge_pages--;
+		surplus_huge_pages--;
 	}
+	spin_unlock(&hugetlb_lock);
 
 	return page;
 }
@@ -382,9 +418,14 @@ static struct page *alloc_huge_page_private(struct vm_area_struct *vma,
 	if (free_huge_pages > resv_huge_pages)
 		page = dequeue_huge_page(vma, addr);
 	spin_unlock(&hugetlb_lock);
-	if (!page)
+	if (!page) {
 		page = alloc_buddy_huge_page(vma, addr);
-	return page ? page : ERR_PTR(-VM_FAULT_OOM);
+		if (!page) {
+			hugetlb_put_quota(vma->vm_file->f_mapping, 1);
+			return ERR_PTR(-VM_FAULT_OOM);
+		}
+	}
+	return page;
 }
 
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
@@ -481,6 +522,12 @@ static unsigned long set_max_huge_pages(unsigned long count)
 	 * Increase the pool size
 	 * First take pages out of surplus state.  Then make up the
 	 * remaining difference by allocating fresh huge pages.
+	 *
+	 * We might race with alloc_buddy_huge_page() here and be unable
+	 * to convert a surplus huge page to a normal huge page. That is
+	 * not critical, though, it just means the overall size of the
+	 * pool might be one hugepage larger than it needs to be, but
+	 * within all the constraints specified by the sysctls.
 	 */
 	spin_lock(&hugetlb_lock);
 	while (surplus_huge_pages && count > persistent_huge_pages) {
@@ -509,6 +556,14 @@ static unsigned long set_max_huge_pages(unsigned long count)
 	 * 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.
+	 *
+	 * By placing pages into the surplus state independent of the
+	 * overcommit value, we are allowing the surplus pool size to
+	 * exceed overcommit. There are few sane options here. Since
+	 * alloc_buddy_huge_page() is checking the global counter,
+	 * though, we'll note that we're not allowed to exceed surplus
+	 * and won't grow the pool anywhere else. Not until one of the
+	 * sysctls are changed, or the surplus pages go out of use.
 	 */
 	min_count = resv_huge_pages + nr_huge_pages - free_huge_pages;
 	min_count = max(count, min_count);
@@ -644,6 +699,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		dst_pte = huge_pte_alloc(dst, addr);
 		if (!dst_pte)
 			goto nomem;
+
+		/* If the pagetables are shared don't copy or take references */
+		if (dst_pte == src_pte)
+			continue;
+
 		spin_lock(&dst->page_table_lock);
 		spin_lock(&src->page_table_lock);
 		if (!pte_none(*src_pte)) {
@@ -753,6 +813,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	spin_unlock(&mm->page_table_lock);
 	copy_huge_page(new_page, old_page, address, vma);
+	__SetPageUptodate(new_page);
 	spin_lock(&mm->page_table_lock);
 
 	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
@@ -798,9 +859,11 @@ retry:
 			goto out;
 		}
 		clear_huge_page(page, address);
+		__SetPageUptodate(page);
 
 		if (vma->vm_flags & VM_SHARED) {
 			int err;
+			struct inode *inode = mapping->host;
 
 			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
 			if (err) {
@@ -809,6 +872,10 @@ retry:
 					goto retry;
 				goto out;
 			}
+
+			spin_lock(&inode->i_lock);
+			inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+			spin_unlock(&inode->i_lock);
 		} else
 			lock_page(page);
 	}
@@ -902,7 +969,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
 
-		if (!pte || pte_none(*pte)) {
+		if (!pte || pte_none(*pte) || (write && !pte_write(*pte))) {
 			int ret;
 
 			spin_unlock(&mm->page_table_lock);
@@ -1151,8 +1218,10 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
 	if (hugetlb_get_quota(inode->i_mapping, chg))
 		return -ENOSPC;
 	ret = hugetlb_acct_memory(chg);
-	if (ret < 0)
+	if (ret < 0) {
+		hugetlb_put_quota(inode->i_mapping, chg);
 		return ret;
+	}
 	region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
 }
@@ -1160,6 +1229,11 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+
+	spin_lock(&inode->i_lock);
+	inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed;
+	spin_unlock(&inode->i_lock);
+
 	hugetlb_put_quota(inode->i_mapping, (chg - freed));
 	hugetlb_acct_memory(-(chg - freed));
 }