Merge branch 'linux-2.6'

6 files changed, 104 insertions, 27 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index c070ec0c15b..9ef97417a0b 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -112,18 +112,17 @@ config SPARSEMEM_EXTREME
 	def_bool y
 	depends on SPARSEMEM && !SPARSEMEM_STATIC
 
-#
-# SPARSEMEM_VMEMMAP uses a virtually mapped mem_map to optimise pfn_to_page
-# and page_to_pfn.  The most efficient option where kernel virtual space is
-# not under pressure.
-#
 config SPARSEMEM_VMEMMAP_ENABLE
 	def_bool n
 
 config SPARSEMEM_VMEMMAP
-	bool
-	depends on SPARSEMEM
-	default y if (SPARSEMEM_VMEMMAP_ENABLE)
+	bool "Sparse Memory virtual memmap"
+	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
+	default y
+	help
+	 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
+	 pfn_to_page and page_to_pfn operations.  This is the most
+	 efficient option when sufficient kernel resources are available.
 
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
diff --git a/mm/filemap.c b/mm/filemap.c
index 188cf5fd3e8..f4d0cded0e1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -124,6 +124,18 @@ void __remove_from_page_cache(struct page *page)
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	BUG_ON(page_mapped(page));
+
+	/*
+	 * Some filesystems seem to re-dirty the page even after
+	 * the VM has canceled the dirty bit (eg ext3 journaling).
+	 *
+	 * Fix it up by doing a final dirty accounting check after
+	 * having removed the page entirely.
+	 */
+	if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
+		dec_zone_page_state(page, NR_FILE_DIRTY);
+		dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+	}
 }
 
 void remove_from_page_cache(struct page *page)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6121b57bbe9..7224a4f0710 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;
 }
@@ -481,6 +517,12 @@ 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 +551,14 @@ 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);
@@ -907,7 +957,7 @@ 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);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b5a58d476c1..d73bfad1c32 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -847,8 +847,19 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		struct page *page = __rmqueue(zone, order, migratetype);
 		if (unlikely(page == NULL))
 			break;
+
+		/*
+		 * Split buddy pages returned by expand() are received here
+		 * in physical page order. The page is added to the callers and
+		 * list and the list head then moves forward. From the callers
+		 * perspective, the linked list is ordered by page number in
+		 * some conditions. This is useful for IO devices that can
+		 * merge IO requests if the physical pages are ordered
+		 * properly.
+		 */
 		list_add(&page->lru, list);
 		set_page_private(page, migratetype);
+		list = &page->lru;
 	}
 	spin_unlock(&zone->lock);
 	return i;
diff --git a/mm/slub.c b/mm/slub.c
index 9c1d9f3b364..b9f37cb0f2e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1468,9 +1468,6 @@ static void *__slab_alloc(struct kmem_cache *s,
 	void **object;
 	struct page *new;
 
-	/* We handle __GFP_ZERO in the caller */
-	gfpflags &= ~__GFP_ZERO;
-
 	if (!c->page)
 		goto new_slab;
 
diff --git a/mm/sparse.c b/mm/sparse.c
index e06f514fe04..a2183cb5d52 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -83,6 +83,8 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
 		return -EEXIST;
 
 	section = sparse_index_alloc(nid);
+	if (!section)
+		return -ENOMEM;
 	/*
 	 * This lock keeps two different sections from
 	 * reallocating for the same index
@@ -389,9 +391,17 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 	 * no locking for this, because it does its own
 	 * plus, it does a kmalloc
 	 */
-	sparse_index_init(section_nr, pgdat->node_id);
+	ret = sparse_index_init(section_nr, pgdat->node_id);
+	if (ret < 0 && ret != -EEXIST)
+		return ret;
 	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
+	if (!memmap)
+		return -ENOMEM;
 	usemap = __kmalloc_section_usemap();
+	if (!usemap) {
+		__kfree_section_memmap(memmap, nr_pages);
+		return -ENOMEM;
+	}
 
 	pgdat_resize_lock(pgdat, &flags);
 
@@ -401,18 +411,16 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 		goto out;
 	}
 
-	if (!usemap) {
-		ret = -ENOMEM;
-		goto out;
-	}
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 
 	ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
 
 out:
 	pgdat_resize_unlock(pgdat, &flags);
-	if (ret <= 0)
+	if (ret <= 0) {
+		kfree(usemap);
 		__kfree_section_memmap(memmap, nr_pages);
+	}
 	return ret;
 }
 #endif