1 files changed, 159 insertions, 116 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ebffa0e4a9c0..5e6fa06f2784 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -380,20 +380,6 @@ void prep_compound_page(struct page *page, unsigned long order)
 	}
 }
 
-static inline void prep_zero_page(struct page *page, unsigned int order,
-							gfp_t gfp_flags)
-{
-	int i;
-
-	/*
-	 * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
-	 * and __GFP_HIGHMEM from hard or soft interrupt context.
-	 */
-	VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt());
-	for (i = 0; i < (1 << order); i++)
-		clear_highpage(page + i);
-}
-
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
 bool _debug_pagealloc_enabled __read_mostly;
@@ -975,7 +961,8 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 	kasan_alloc_pages(page, order);
 
 	if (gfp_flags & __GFP_ZERO)
-		prep_zero_page(page, order, gfp_flags);
+		for (i = 0; i < (1 << order); i++)
+			clear_highpage(page + i);
 
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
@@ -2322,48 +2309,6 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 		show_mem(filter);
 }
 
-static inline int
-should_alloc_retry(gfp_t gfp_mask, unsigned int order,
-				unsigned long did_some_progress,
-				unsigned long pages_reclaimed)
-{
-	/* Do not loop if specifically requested */
-	if (gfp_mask & __GFP_NORETRY)
-		return 0;
-
-	/* Always retry if specifically requested */
-	if (gfp_mask & __GFP_NOFAIL)
-		return 1;
-
-	/*
-	 * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
-	 * making forward progress without invoking OOM. Suspend also disables
-	 * storage devices so kswapd will not help. Bail if we are suspending.
-	 */
-	if (!did_some_progress && pm_suspended_storage())
-		return 0;
-
-	/*
-	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
-	 * means __GFP_NOFAIL, but that may not be true in other
-	 * implementations.
-	 */
-	if (order <= PAGE_ALLOC_COSTLY_ORDER)
-		return 1;
-
-	/*
-	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
-	 * specified, then we retry until we no longer reclaim any pages
-	 * (above), or we've reclaimed an order of pages at least as
-	 * large as the allocation's order. In both cases, if the
-	 * allocation still fails, we stop retrying.
-	 */
-	if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
-		return 1;
-
-	return 0;
-}
-
 static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	const struct alloc_context *ac, unsigned long *did_some_progress)
@@ -2373,10 +2318,10 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	*did_some_progress = 0;
 
 	/*
-	 * Acquire the per-zone oom lock for each zone.  If that
-	 * fails, somebody else is making progress for us.
+	 * Acquire the oom lock.  If that fails, somebody else is
+	 * making progress for us.
 	 */
-	if (!oom_zonelist_trylock(ac->zonelist, gfp_mask)) {
+	if (!mutex_trylock(&oom_lock)) {
 		*did_some_progress = 1;
 		schedule_timeout_uninterruptible(1);
 		return NULL;
@@ -2402,16 +2347,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 		/* The OOM killer does not needlessly kill tasks for lowmem */
 		if (ac->high_zoneidx < ZONE_NORMAL)
 			goto out;
-		/* The OOM killer does not compensate for light reclaim */
+		/* The OOM killer does not compensate for IO-less reclaim */
 		if (!(gfp_mask & __GFP_FS)) {
 			/*
 			 * XXX: Page reclaim didn't yield anything,
 			 * and the OOM killer can't be invoked, but
-			 * keep looping as per should_alloc_retry().
+			 * keep looping as per tradition.
 			 */
 			*did_some_progress = 1;
 			goto out;
 		}
+		if (pm_suspended_storage())
+			goto out;
 		/* The OOM killer may not free memory on a specific node */
 		if (gfp_mask & __GFP_THISNODE)
 			goto out;
@@ -2421,7 +2368,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			|| WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
 		*did_some_progress = 1;
 out:
-	oom_zonelist_unlock(ac->zonelist, gfp_mask);
+	mutex_unlock(&oom_lock);
 	return page;
 }
 
@@ -2794,40 +2741,40 @@ retry:
 	if (page)
 		goto got_pg;
 
-	/* Check if we should retry the allocation */
+	/* Do not loop if specifically requested */
+	if (gfp_mask & __GFP_NORETRY)
+		goto noretry;
+
+	/* Keep reclaiming pages as long as there is reasonable progress */
 	pages_reclaimed += did_some_progress;
-	if (should_alloc_retry(gfp_mask, order, did_some_progress,
-						pages_reclaimed)) {
-		/*
-		 * If we fail to make progress by freeing individual
-		 * pages, but the allocation wants us to keep going,
-		 * start OOM killing tasks.
-		 */
-		if (!did_some_progress) {
-			page = __alloc_pages_may_oom(gfp_mask, order, ac,
-							&did_some_progress);
-			if (page)
-				goto got_pg;
-			if (!did_some_progress)
-				goto nopage;
-		}
+	if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) ||
+	    ((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) {
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto retry;
-	} else {
-		/*
-		 * High-order allocations do not necessarily loop after
-		 * direct reclaim and reclaim/compaction depends on compaction
-		 * being called after reclaim so call directly if necessary
-		 */
-		page = __alloc_pages_direct_compact(gfp_mask, order,
-					alloc_flags, ac, migration_mode,
-					&contended_compaction,
-					&deferred_compaction);
-		if (page)
-			goto got_pg;
 	}
 
+	/* Reclaim has failed us, start killing things */
+	page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
+	if (page)
+		goto got_pg;
+
+	/* Retry as long as the OOM killer is making progress */
+	if (did_some_progress)
+		goto retry;
+
+noretry:
+	/*
+	 * High-order allocations do not necessarily loop after
+	 * direct reclaim and reclaim/compaction depends on compaction
+	 * being called after reclaim so call directly if necessary
+	 */
+	page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags,
+					    ac, migration_mode,
+					    &contended_compaction,
+					    &deferred_compaction);
+	if (page)
+		goto got_pg;
 nopage:
 	warn_alloc_failed(gfp_mask, order, NULL);
 got_pg:
@@ -2967,6 +2914,104 @@ void free_pages(unsigned long addr, unsigned int order)
 EXPORT_SYMBOL(free_pages);
 
 /*
+ * Page Fragment:
+ *  An arbitrary-length arbitrary-offset area of memory which resides
+ *  within a 0 or higher order page.  Multiple fragments within that page
+ *  are individually refcounted, in the page's reference counter.
+ *
+ * The page_frag functions below provide a simple allocation framework for
+ * page fragments.  This is used by the network stack and network device
+ * drivers to provide a backing region of memory for use as either an
+ * sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
+ */
+static struct page *__page_frag_refill(struct page_frag_cache *nc,
+				       gfp_t gfp_mask)
+{
+	struct page *page = NULL;
+	gfp_t gfp = gfp_mask;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+		    __GFP_NOMEMALLOC;
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
+				PAGE_FRAG_CACHE_MAX_ORDER);
+	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
+#endif
+	if (unlikely(!page))
+		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+	nc->va = page ? page_address(page) : NULL;
+
+	return page;
+}
+
+void *__alloc_page_frag(struct page_frag_cache *nc,
+			unsigned int fragsz, gfp_t gfp_mask)
+{
+	unsigned int size = PAGE_SIZE;
+	struct page *page;
+	int offset;
+
+	if (unlikely(!nc->va)) {
+refill:
+		page = __page_frag_refill(nc, gfp_mask);
+		if (!page)
+			return NULL;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+		/* if size can vary use size else just use PAGE_SIZE */
+		size = nc->size;
+#endif
+		/* Even if we own the page, we do not use atomic_set().
+		 * This would break get_page_unless_zero() users.
+		 */
+		atomic_add(size - 1, &page->_count);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pfmemalloc = page->pfmemalloc;
+		nc->pagecnt_bias = size;
+		nc->offset = size;
+	}
+
+	offset = nc->offset - fragsz;
+	if (unlikely(offset < 0)) {
+		page = virt_to_page(nc->va);
+
+		if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count))
+			goto refill;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+		/* if size can vary use size else just use PAGE_SIZE */
+		size = nc->size;
+#endif
+		/* OK, page count is 0, we can safely set it */
+		atomic_set(&page->_count, size);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = size;
+		offset = size - fragsz;
+	}
+
+	nc->pagecnt_bias--;
+	nc->offset = offset;
+
+	return nc->va + offset;
+}
+EXPORT_SYMBOL(__alloc_page_frag);
+
+/*
+ * Frees a page fragment allocated out of either a compound or order 0 page.
+ */
+void __free_page_frag(void *addr)
+{
+	struct page *page = virt_to_head_page(addr);
+
+	if (unlikely(put_page_testzero(page)))
+		__free_pages_ok(page, compound_order(page));
+}
+EXPORT_SYMBOL(__free_page_frag);
+
+/*
  * alloc_kmem_pages charges newly allocated pages to the kmem resource counter
  * of the current memory cgroup.
  *
@@ -4769,22 +4814,28 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
 						unsigned long *zones_size,
 						unsigned long *zholes_size)
 {
-	unsigned long realtotalpages, totalpages = 0;
+	unsigned long realtotalpages = 0, totalpages = 0;
 	enum zone_type i;
 
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
-							 node_start_pfn,
-							 node_end_pfn,
-							 zones_size);
-	pgdat->node_spanned_pages = totalpages;
-
-	realtotalpages = totalpages;
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		realtotalpages -=
-			zone_absent_pages_in_node(pgdat->node_id, i,
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+		unsigned long size, real_size;
+
+		size = zone_spanned_pages_in_node(pgdat->node_id, i,
+						  node_start_pfn,
+						  node_end_pfn,
+						  zones_size);
+		real_size = size - zone_absent_pages_in_node(pgdat->node_id, i,
 						  node_start_pfn, node_end_pfn,
 						  zholes_size);
+		zone->spanned_pages = size;
+		zone->present_pages = real_size;
+
+		totalpages += size;
+		realtotalpages += real_size;
+	}
+
+	pgdat->node_spanned_pages = totalpages;
 	pgdat->node_present_pages = realtotalpages;
 	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
 							realtotalpages);
@@ -4894,8 +4945,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
  * NOTE: pgdat should get zeroed by caller.
  */
 static void __paginginit free_area_init_core(struct pglist_data *pgdat,
-		unsigned long node_start_pfn, unsigned long node_end_pfn,
-		unsigned long *zones_size, unsigned long *zholes_size)
+		unsigned long node_start_pfn, unsigned long node_end_pfn)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
@@ -4916,12 +4966,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, freesize, memmap_pages;
 
-		size = zone_spanned_pages_in_node(nid, j, node_start_pfn,
-						  node_end_pfn, zones_size);
-		realsize = freesize = size - zone_absent_pages_in_node(nid, j,
-								node_start_pfn,
-								node_end_pfn,
-								zholes_size);
+		size = zone->spanned_pages;
+		realsize = freesize = zone->present_pages;
 
 		/*
 		 * Adjust freesize so that it accounts for how much memory
@@ -4956,8 +5002,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			nr_kernel_pages -= memmap_pages;
 		nr_all_pages += freesize;
 
-		zone->spanned_pages = size;
-		zone->present_pages = realsize;
 		/*
 		 * Set an approximate value for lowmem here, it will be adjusted
 		 * when the bootmem allocator frees pages into the buddy system.
@@ -5063,8 +5107,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
-	free_area_init_core(pgdat, start_pfn, end_pfn,
-			    zones_size, zholes_size);
+	free_area_init_core(pgdat, start_pfn, end_pfn);
 }
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -6013,9 +6056,9 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_NUMA
 int hashdist = HASHDIST_DEFAULT;
 
-#ifdef CONFIG_NUMA
 static int __init set_hashdist(char *str)
 {
 	if (!str)