Merge tag 'for-linus-5.10c-rc8-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:
 "A short series fixing a regression introduced in 5.9 for running as
  Xen dom0 on a system with NVMe backed storage"

* tag 'for-linus-5.10c-rc8-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: don't use page->lru for ZONE_DEVICE memory
  xen: add helpers for caching grant mapping pages

Author: torvalds

drivers/block/xen-blkback/blkback.c

@@ -132,73 +132,12 @@ module_param(log_stats, int, 0644);
 
 #define BLKBACK_INVALID_HANDLE (~0)
 
-/* Number of free pages to remove on each call to gnttab_free_pages */
-#define NUM_BATCH_FREE_PAGES 10
-
 static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt)
 {
 	return pgrant_timeout && (jiffies - persistent_gnt->last_used >=
 			HZ * pgrant_timeout);
 }
 
-static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&ring->free_pages_lock, flags);
-	if (list_empty(&ring->free_pages)) {
-		BUG_ON(ring->free_pages_num != 0);
-		spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-		return gnttab_alloc_pages(1, page);
-	}
-	BUG_ON(ring->free_pages_num == 0);
-	page[0] = list_first_entry(&ring->free_pages, struct page, lru);
-	list_del(&page[0]->lru);
-	ring->free_pages_num--;
-	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-
-	return 0;
-}
-
-static inline void put_free_pages(struct xen_blkif_ring *ring, struct page **page,
-                                  int num)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&ring->free_pages_lock, flags);
-	for (i = 0; i < num; i++)
-		list_add(&page[i]->lru, &ring->free_pages);
-	ring->free_pages_num += num;
-	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-}
-
-static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num)
-{
-	/* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */
-	struct page *page[NUM_BATCH_FREE_PAGES];
-	unsigned int num_pages = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ring->free_pages_lock, flags);
-	while (ring->free_pages_num > num) {
-		BUG_ON(list_empty(&ring->free_pages));
-		page[num_pages] = list_first_entry(&ring->free_pages,
-		                                   struct page, lru);
-		list_del(&page[num_pages]->lru);
-		ring->free_pages_num--;
-		if (++num_pages == NUM_BATCH_FREE_PAGES) {
-			spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-			gnttab_free_pages(num_pages, page);
-			spin_lock_irqsave(&ring->free_pages_lock, flags);
-			num_pages = 0;
-		}
-	}
-	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-	if (num_pages != 0)
-		gnttab_free_pages(num_pages, page);
-}
-
 #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))
 
 static int do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags);
@@ -331,7 +270,8 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro
 			unmap_data.count = segs_to_unmap;
 			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
 
-			put_free_pages(ring, pages, segs_to_unmap);
+			gnttab_page_cache_put(&ring->free_pages, pages,
+					      segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 
@@ -371,15 +311,16 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
 			unmap_data.count = segs_to_unmap;
 			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
-			put_free_pages(ring, pages, segs_to_unmap);
+			gnttab_page_cache_put(&ring->free_pages, pages,
+					      segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 		kfree(persistent_gnt);
 	}
 	if (segs_to_unmap > 0) {
 		unmap_data.count = segs_to_unmap;
 		BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
-		put_free_pages(ring, pages, segs_to_unmap);
+		gnttab_page_cache_put(&ring->free_pages, pages, segs_to_unmap);
 	}
 }
 
@@ -664,9 +605,10 @@ int xen_blkif_schedule(void *arg)
 
 		/* Shrink the free pages pool if it is too large. */
 		if (time_before(jiffies, blkif->buffer_squeeze_end))
-			shrink_free_pagepool(ring, 0);
+			gnttab_page_cache_shrink(&ring->free_pages, 0);
 		else
-			shrink_free_pagepool(ring, max_buffer_pages);
+			gnttab_page_cache_shrink(&ring->free_pages,
+						 max_buffer_pages);
 
 		if (log_stats && time_after(jiffies, ring->st_print))
 			print_stats(ring);
@@ -697,7 +639,7 @@ void xen_blkbk_free_caches(struct xen_blkif_ring *ring)
 	ring->persistent_gnt_c = 0;
 
 	/* Since we are shutting down remove all pages from the buffer */
-	shrink_free_pagepool(ring, 0 /* All */);
+	gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */);
 }
 
 static unsigned int xen_blkbk_unmap_prepare(
@@ -736,7 +678,7 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_
 	   but is this the best way to deal with this? */
 	BUG_ON(result);
 
-	put_free_pages(ring, data->pages, data->count);
+	gnttab_page_cache_put(&ring->free_pages, data->pages, data->count);
 	make_response(ring, pending_req->id,
 		      pending_req->operation, pending_req->status);
 	free_req(ring, pending_req);
@@ -803,7 +745,8 @@ static void xen_blkbk_unmap(struct xen_blkif_ring *ring,
 		if (invcount) {
 			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
 			BUG_ON(ret);
-			put_free_pages(ring, unmap_pages, invcount);
+			gnttab_page_cache_put(&ring->free_pages, unmap_pages,
+					      invcount);
 		}
 		pages += batch;
 		num -= batch;
@@ -850,7 +793,8 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 			pages[i]->page = persistent_gnt->page;
 			pages[i]->persistent_gnt = persistent_gnt;
 		} else {
-			if (get_free_page(ring, &pages[i]->page))
+			if (gnttab_page_cache_get(&ring->free_pages,
+						  &pages[i]->page))
 				goto out_of_memory;
 			addr = vaddr(pages[i]->page);
 			pages_to_gnt[segs_to_map] = pages[i]->page;
@@ -883,7 +827,8 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 			BUG_ON(new_map_idx >= segs_to_map);
 			if (unlikely(map[new_map_idx].status != 0)) {
 				pr_debug("invalid buffer -- could not remap it\n");
-				put_free_pages(ring, &pages[seg_idx]->page, 1);
+				gnttab_page_cache_put(&ring->free_pages,
+						      &pages[seg_idx]->page, 1);
 				pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE;
 				ret |= 1;
 				goto next;
@@ -944,7 +889,7 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 
 out_of_memory:
 	pr_alert("%s: out of memory\n", __func__);
-	put_free_pages(ring, pages_to_gnt, segs_to_map);
+	gnttab_page_cache_put(&ring->free_pages, pages_to_gnt, segs_to_map);
 	for (i = last_map; i < num; i++)
 		pages[i]->handle = BLKBACK_INVALID_HANDLE;
 	return -ENOMEM;

drivers/block/xen-blkback/common.h

@@ -288,9 +288,7 @@ struct xen_blkif_ring {
 	struct work_struct	persistent_purge_work;
 
 	/* Buffer of free pages to map grant refs. */
-	spinlock_t		free_pages_lock;
-	int			free_pages_num;
-	struct list_head	free_pages;
+	struct gnttab_page_cache free_pages;
 
 	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */

drivers/block/xen-blkback/xenbus.c

@@ -144,8 +144,7 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif)
 		INIT_LIST_HEAD(&ring->pending_free);
 		INIT_LIST_HEAD(&ring->persistent_purge_list);
 		INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
-		spin_lock_init(&ring->free_pages_lock);
-		INIT_LIST_HEAD(&ring->free_pages);
+		gnttab_page_cache_init(&ring->free_pages);
 
 		spin_lock_init(&ring->pending_free_lock);
 		init_waitqueue_head(&ring->pending_free_wq);
@@ -317,8 +316,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 		BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
 		BUG_ON(!list_empty(&ring->persistent_purge_list));
 		BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
-		BUG_ON(!list_empty(&ring->free_pages));
-		BUG_ON(ring->free_pages_num != 0);
+		BUG_ON(ring->free_pages.num_pages != 0);
 		BUG_ON(ring->persistent_gnt_c != 0);
 		WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
 		ring->active = false;

drivers/xen/grant-table.c

@@ -813,6 +813,129 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
 
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+static inline void cache_init(struct gnttab_page_cache *cache)
+{
+	cache->pages = NULL;
+}
+
+static inline bool cache_empty(struct gnttab_page_cache *cache)
+{
+	return !cache->pages;
+}
+
+static inline struct page *cache_deq(struct gnttab_page_cache *cache)
+{
+	struct page *page;
+
+	page = cache->pages;
+	cache->pages = page->zone_device_data;
+
+	return page;
+}
+
+static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page)
+{
+	page->zone_device_data = cache->pages;
+	cache->pages = page;
+}
+#else
+static inline void cache_init(struct gnttab_page_cache *cache)
+{
+	INIT_LIST_HEAD(&cache->pages);
+}
+
+static inline bool cache_empty(struct gnttab_page_cache *cache)
+{
+	return list_empty(&cache->pages);
+}
+
+static inline struct page *cache_deq(struct gnttab_page_cache *cache)
+{
+	struct page *page;
+
+	page = list_first_entry(&cache->pages, struct page, lru);
+	list_del(&page->lru);
+
+	return page;
+}
+
+static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page)
+{
+	list_add(&page->lru, &cache->pages);
+}
+#endif
+
+void gnttab_page_cache_init(struct gnttab_page_cache *cache)
+{
+	spin_lock_init(&cache->lock);
+	cache_init(cache);
+	cache->num_pages = 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_init);
+
+int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+
+	if (cache_empty(cache)) {
+		spin_unlock_irqrestore(&cache->lock, flags);
+		return gnttab_alloc_pages(1, page);
+	}
+
+	page[0] = cache_deq(cache);
+	cache->num_pages--;
+
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_get);
+
+void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page,
+			   unsigned int num)
+{
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&cache->lock, flags);
+
+	for (i = 0; i < num; i++)
+		cache_enq(cache, page[i]);
+	cache->num_pages += num;
+
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_put);
+
+void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, unsigned int num)
+{
+	struct page *page[10];
+	unsigned int i = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+
+	while (cache->num_pages > num) {
+		page[i] = cache_deq(cache);
+		cache->num_pages--;
+		if (++i == ARRAY_SIZE(page)) {
+			spin_unlock_irqrestore(&cache->lock, flags);
+			gnttab_free_pages(i, page);
+			i = 0;
+			spin_lock_irqsave(&cache->lock, flags);
+		}
+	}
+
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	if (i != 0)
+		gnttab_free_pages(i, page);
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_shrink);
+
 void gnttab_pages_clear_private(int nr_pages, struct page **pages)
 {
 	int i;

drivers/xen/unpopulated-alloc.c

@@ -12,7 +12,7 @@
 #include <xen/xen.h>
 
 static DEFINE_MUTEX(list_lock);
-static LIST_HEAD(page_list);
+static struct page *page_list;
 static unsigned int list_count;
 
 static int fill_list(unsigned int nr_pages)
@@ -84,7 +84,8 @@ static int fill_list(unsigned int nr_pages)
 		struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i);
 
 		BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i));
-		list_add(&pg->lru, &page_list);
+		pg->zone_device_data = page_list;
+		page_list = pg;
 		list_count++;
 	}
 
@@ -118,12 +119,10 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 	}
 
 	for (i = 0; i < nr_pages; i++) {
-		struct page *pg = list_first_entry_or_null(&page_list,
-							   struct page,
-							   lru);
+		struct page *pg = page_list;
 
 		BUG_ON(!pg);
-		list_del(&pg->lru);
+		page_list = pg->zone_device_data;
 		list_count--;
 		pages[i] = pg;
 
@@ -134,7 +133,8 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 				unsigned int j;
 
 				for (j = 0; j <= i; j++) {
-					list_add(&pages[j]->lru, &page_list);
+					pages[j]->zone_device_data = page_list;
+					page_list = pages[j];
 					list_count++;
 				}
 				goto out;
@@ -160,7 +160,8 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 
 	mutex_lock(&list_lock);
 	for (i = 0; i < nr_pages; i++) {
-		list_add(&pages[i]->lru, &page_list);
+		pages[i]->zone_device_data = page_list;
+		page_list = pages[i];
 		list_count++;
 	}
 	mutex_unlock(&list_lock);
@@ -189,7 +190,8 @@ static int __init init(void)
 			struct page *pg =
 				pfn_to_page(xen_extra_mem[i].start_pfn + j);
 
-			list_add(&pg->lru, &page_list);
+			pg->zone_device_data = page_list;
+			page_list = pg;
 			list_count++;
 		}
 	}