Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "A few misc subsystems and some of MM.

  175 patches.

  Subsystems affected by this patch series: ia64, kbuild, scripts, sh,
  ocfs2, kfifo, vfs, kernel/watchdog, and mm (slab-generic, slub,
  kmemleak, debug, pagecache, msync, gup, memremap, memcg, pagemap,
  mremap, dma, sparsemem, vmalloc, documentation, kasan, initialization,
  pagealloc, and memory-failure)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (175 commits)
  mm/memory-failure: unnecessary amount of unmapping
  mm/mmzone.h: fix existing kernel-doc comments and link them to core-api
  mm: page_alloc: ignore init_on_free=1 for debug_pagealloc=1
  net: page_pool: use alloc_pages_bulk in refill code path
  net: page_pool: refactor dma_map into own function page_pool_dma_map
  SUNRPC: refresh rq_pages using a bulk page allocator
  SUNRPC: set rq_page_end differently
  mm/page_alloc: inline __rmqueue_pcplist
  mm/page_alloc: optimize code layout for __alloc_pages_bulk
  mm/page_alloc: add an array-based interface to the bulk page allocator
  mm/page_alloc: add a bulk page allocator
  mm/page_alloc: rename alloced to allocated
  mm/page_alloc: duplicate include linux/vmalloc.h
  mm, page_alloc: avoid page_to_pfn() in move_freepages()
  mm/Kconfig: remove default DISCONTIGMEM_MANUAL
  mm: page_alloc: dump migrate-failed pages
  mm/mempolicy: fix mpol_misplaced kernel-doc
  mm/mempolicy: rewrite alloc_pages_vma documentation
  mm/mempolicy: rewrite alloc_pages documentation
  mm/mempolicy: rename alloc_pages_current to alloc_pages
  ...

2 files changed, 92 insertions, 57 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ad8b0707af04..9ec1aa9640ad 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -180,40 +180,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
 					 pool->p.dma_dir);
 }
 
-/* slow path */
-noinline
-static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
-						 gfp_t _gfp)
+static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 {
-	struct page *page;
-	gfp_t gfp = _gfp;
 	dma_addr_t dma;
 
-	/* We could always set __GFP_COMP, and avoid this branch, as
-	 * prep_new_page() can handle order-0 with __GFP_COMP.
-	 */
-	if (pool->p.order)
-		gfp |= __GFP_COMP;
-
-	/* FUTURE development:
-	 *
-	 * Current slow-path essentially falls back to single page
-	 * allocations, which doesn't improve performance.  This code
-	 * need bulk allocation support from the page allocator code.
-	 */
-
-	/* Cache was empty, do real allocation */
-#ifdef CONFIG_NUMA
-	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
-#else
-	page = alloc_pages(gfp, pool->p.order);
-#endif
-	if (!page)
-		return NULL;
-
-	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
-		goto skip_dma_map;
-
 	/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
 	 * since dma_addr_t can be either 32 or 64 bits and does not always fit
 	 * into page private data (i.e 32bit cpu with 64bit DMA caps)
@@ -222,20 +192,87 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	dma = dma_map_page_attrs(pool->p.dev, page, 0,
 				 (PAGE_SIZE << pool->p.order),
 				 pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
-	if (dma_mapping_error(pool->p.dev, dma)) {
-		put_page(page);
-		return NULL;
-	}
+	if (dma_mapping_error(pool->p.dev, dma))
+		return false;
+
 	page->dma_addr = dma;
 
 	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
 		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
 
-skip_dma_map:
+	return true;
+}
+
+static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
+						 gfp_t gfp)
+{
+	struct page *page;
+
+	gfp |= __GFP_COMP;
+	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
+	if (unlikely(!page))
+		return NULL;
+
+	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
+	    unlikely(!page_pool_dma_map(pool, page))) {
+		put_page(page);
+		return NULL;
+	}
+
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
-
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
+	return page;
+}
+
+/* slow path */
+noinline
+static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
+						 gfp_t gfp)
+{
+	const int bulk = PP_ALLOC_CACHE_REFILL;
+	unsigned int pp_flags = pool->p.flags;
+	unsigned int pp_order = pool->p.order;
+	struct page *page;
+	int i, nr_pages;
+
+	/* Don't support bulk alloc for high-order pages */
+	if (unlikely(pp_order))
+		return __page_pool_alloc_page_order(pool, gfp);
+
+	/* Unnecessary as alloc cache is empty, but guarantees zero count */
+	if (unlikely(pool->alloc.count > 0))
+		return pool->alloc.cache[--pool->alloc.count];
+
+	/* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */
+	memset(&pool->alloc.cache, 0, sizeof(void *) * bulk);
+
+	nr_pages = alloc_pages_bulk_array(gfp, bulk, pool->alloc.cache);
+	if (unlikely(!nr_pages))
+		return NULL;
+
+	/* Pages have been filled into alloc.cache array, but count is zero and
+	 * page element have not been (possibly) DMA mapped.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		page = pool->alloc.cache[i];
+		if ((pp_flags & PP_FLAG_DMA_MAP) &&
+		    unlikely(!page_pool_dma_map(pool, page))) {
+			put_page(page);
+			continue;
+		}
+		pool->alloc.cache[pool->alloc.count++] = page;
+		/* Track how many pages are held 'in-flight' */
+		pool->pages_state_hold_cnt++;
+		trace_page_pool_state_hold(pool, page,
+					   pool->pages_state_hold_cnt);
+	}
+
+	/* Return last page */
+	if (likely(pool->alloc.count > 0))
+		page = pool->alloc.cache[--pool->alloc.count];
+	else
+		page = NULL;
 
 	/* When page just alloc'ed is should/must have refcnt 1. */
 	return page;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 42565f0c7d5a..d66a8e44a1ae 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -661,36 +661,34 @@ static void svc_check_conn_limits(struct svc_serv *serv)
 static int svc_alloc_arg(struct svc_rqst *rqstp)
 {
 	struct svc_serv *serv = rqstp->rq_server;
-	struct xdr_buf *arg;
-	int pages;
-	int i;
+	struct xdr_buf *arg = &rqstp->rq_arg;
+	unsigned long pages, filled;
 
-	/* now allocate needed pages.  If we get a failure, sleep briefly */
 	pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
 	if (pages > RPCSVC_MAXPAGES) {
-		pr_warn_once("svc: warning: pages=%u > RPCSVC_MAXPAGES=%lu\n",
+		pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n",
 			     pages, RPCSVC_MAXPAGES);
 		/* use as many pages as possible */
 		pages = RPCSVC_MAXPAGES;
 	}
-	for (i = 0; i < pages ; i++)
-		while (rqstp->rq_pages[i] == NULL) {
-			struct page *p = alloc_page(GFP_KERNEL);
-			if (!p) {
-				set_current_state(TASK_INTERRUPTIBLE);
-				if (signalled() || kthread_should_stop()) {
-					set_current_state(TASK_RUNNING);
-					return -EINTR;
-				}
-				schedule_timeout(msecs_to_jiffies(500));
-			}
-			rqstp->rq_pages[i] = p;
+
+	for (;;) {
+		filled = alloc_pages_bulk_array(GFP_KERNEL, pages,
+						rqstp->rq_pages);
+		if (filled == pages)
+			break;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (signalled() || kthread_should_stop()) {
+			set_current_state(TASK_RUNNING);
+			return -EINTR;
 		}
-	rqstp->rq_page_end = &rqstp->rq_pages[i];
-	rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
+		schedule_timeout(msecs_to_jiffies(500));
+	}
+	rqstp->rq_page_end = &rqstp->rq_pages[pages];
+	rqstp->rq_pages[pages] = NULL; /* this might be seen in nfsd_splice_actor() */
 
 	/* Make arg->head point to first page and arg->pages point to rest */
-	arg = &rqstp->rq_arg;
 	arg->head[0].iov_base = page_address(rqstp->rq_pages[0]);
 	arg->head[0].iov_len = PAGE_SIZE;
 	arg->pages = rqstp->rq_pages + 1;