[PATCH net-next v4 04/20] mm: Make the page_frag_cache allocator use multipage folios

[David Howells]

Change the page_frag_cache allocator to use multipage folios rather than
groups of pages.  This reduces page_frag_free to just a folio_put() or
put_page().

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
cc: Eric Dumazet <edumazet@xxxxxxxxxx>
cc: Jakub Kicinski <kuba@xxxxxxxxxx>
cc: Paolo Abeni <pabeni@xxxxxxxxxx>
cc: Jens Axboe <axboe@xxxxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: netdev@xxxxxxxxxxxxxxx
---
 drivers/net/ethernet/mediatek/mtk_wed_wo.c |  15 +--
 drivers/nvme/host/tcp.c                    |   7 +-
 drivers/nvme/target/tcp.c                  |   5 +-
 include/linux/gfp.h                        |   1 +
 include/linux/mm_types.h                   |  13 +--
 mm/page_frag_alloc.c                       | 101 +++++++++++----------
 6 files changed, 63 insertions(+), 79 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
index 69fba29055e9..6ce532217777 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
@@ -286,7 +286,6 @@ mtk_wed_wo_queue_free(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q)
 static void
 mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q)
 {
-	struct page *page;
 	int i;
 
 	for (i = 0; i < q->n_desc; i++) {
@@ -298,12 +297,7 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q)
 		entry->buf = NULL;
 	}
 
-	if (!q->cache.va)
-		return;
-
-	page = virt_to_page(q->cache.va);
-	__page_frag_cache_drain(page, q->cache.pagecnt_bias);
-	memset(&q->cache, 0, sizeof(q->cache));
+	page_frag_cache_clear(&q->cache);
 }
 
 static void
@@ -320,12 +314,7 @@ mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q)
 		skb_free_frag(buf);
 	}
 
-	if (!q->cache.va)
-		return;
-
-	page = virt_to_page(q->cache.va);
-	__page_frag_cache_drain(page, q->cache.pagecnt_bias);
-	memset(&q->cache, 0, sizeof(q->cache));
+	page_frag_cache_clear(&q->cache);
 }
 
 static void
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 42c0598c31f2..76f12ac714b0 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1323,12 +1323,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 	if (queue->hdr_digest || queue->data_digest)
 		nvme_tcp_free_crypto(queue);
 
-	if (queue->pf_cache.va) {
-		page = virt_to_head_page(queue->pf_cache.va);
-		__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
-		queue->pf_cache.va = NULL;
-	}
-
+	page_frag_cache_clear(&queue->pf_cache);
 	noreclaim_flag = memalloc_noreclaim_save();
 	sock_release(queue->sock);
 	memalloc_noreclaim_restore(noreclaim_flag);
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 66e8f9fd0ca7..ae871c31cf00 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1438,7 +1438,6 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue)
 
 static void nvmet_tcp_release_queue_work(struct work_struct *w)
 {
-	struct page *page;
 	struct nvmet_tcp_queue *queue =
 		container_of(w, struct nvmet_tcp_queue, release_work);
 
@@ -1460,9 +1459,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
 	if (queue->hdr_digest || queue->data_digest)
 		nvmet_tcp_free_crypto(queue);
 	ida_free(&nvmet_tcp_queue_ida, queue->idx);
-
-	page = virt_to_head_page(queue->pf_cache.va);
-	__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
+	page_frag_cache_clear(&queue->pf_cache);
 	kfree(queue);
 }
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 65a78773dcca..5e15384798eb 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -313,6 +313,7 @@ static inline void *page_frag_alloc(struct page_frag_cache *nc,
 {
 	return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
 }
+void page_frag_cache_clear(struct page_frag_cache *nc);
 
 extern void page_frag_free(void *addr);
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0722859c3647..49a70b3f44a9 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -420,18 +420,13 @@ static inline void *folio_get_private(struct folio *folio)
 }
 
 struct page_frag_cache {
-	void * va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	__u16 offset;
-	__u16 size;
-#else
-	__u32 offset;
-#endif
+	struct folio	*folio;
+	unsigned int	offset;
 	/* we maintain a pagecount bias, so that we dont dirty cache line
 	 * containing page->_refcount every time we allocate a fragment.
 	 */
-	unsigned int		pagecnt_bias;
-	bool pfmemalloc;
+	unsigned int	pagecnt_bias;
+	bool		pfmemalloc;
 };
 
 typedef unsigned long vm_flags_t;
diff --git a/mm/page_frag_alloc.c b/mm/page_frag_alloc.c
index bee95824ef8f..9b138cb0e3a4 100644
--- a/mm/page_frag_alloc.c
+++ b/mm/page_frag_alloc.c
@@ -16,88 +16,95 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
-static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
-					     gfp_t gfp_mask)
+/*
+ * Allocate a new folio for the frag cache.
+ */
+static struct folio *page_frag_cache_refill(struct page_frag_cache *nc,
+					    gfp_t gfp_mask)
 {
-	struct page *page = NULL;
+	struct folio *folio = 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;
+	gfp_mask |= __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
+	folio = folio_alloc(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER);
 #endif
-	if (unlikely(!page))
-		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
-
-	nc->va = page ? page_address(page) : NULL;
+	if (unlikely(!folio))
+		folio = folio_alloc(gfp, 0);
 
-	return page;
+	if (folio)
+		nc->folio = folio;
+	return folio;
 }
 
 void __page_frag_cache_drain(struct page *page, unsigned int count)
 {
-	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+	struct folio *folio = page_folio(page);
 
-	if (page_ref_sub_and_test(page, count - 1))
-		__free_pages(page, compound_order(page));
+	VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
+
+	folio_put_refs(folio, count);
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
+void page_frag_cache_clear(struct page_frag_cache *nc)
+{
+	struct folio *folio = nc->folio;
+
+	if (folio) {
+		VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
+		folio_put_refs(folio, nc->pagecnt_bias);
+		nc->folio = NULL;
+	}
+
+}
+EXPORT_SYMBOL(page_frag_cache_clear);
+
 void *page_frag_alloc_align(struct page_frag_cache *nc,
 		      unsigned int fragsz, gfp_t gfp_mask,
 		      unsigned int align_mask)
 {
-	unsigned int size = PAGE_SIZE;
-	struct page *page;
-	int offset;
+	struct folio *folio = nc->folio;
+	size_t offset;
 
-	if (unlikely(!nc->va)) {
+	if (unlikely(!folio)) {
 refill:
-		page = __page_frag_cache_refill(nc, gfp_mask);
-		if (!page)
+		folio = page_frag_cache_refill(nc, gfp_mask);
+		if (!folio)
 			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.
 		 */
-		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
+		folio_ref_add(folio, PAGE_FRAG_CACHE_MAX_SIZE);
 
 		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page_is_pfmemalloc(page);
+		nc->pfmemalloc = folio_is_pfmemalloc(folio);
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		nc->offset = size;
+		nc->offset = folio_size(folio);
 	}
 
-	offset = nc->offset - fragsz;
-	if (unlikely(offset < 0)) {
-		page = virt_to_page(nc->va);
-
-		if (page_ref_count(page) != nc->pagecnt_bias)
+	offset = nc->offset;
+	if (unlikely(fragsz > offset)) {
+		/* Reuse the folio if everyone we gave it to has finished with it. */
+		if (!folio_ref_sub_and_test(folio, nc->pagecnt_bias)) {
+			nc->folio = NULL;
 			goto refill;
+		}
+
 		if (unlikely(nc->pfmemalloc)) {
-			page_ref_sub(page, nc->pagecnt_bias - 1);
-			__free_pages(page, compound_order(page));
+			__folio_put(folio);
+			nc->folio = NULL;
 			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 */
-		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
+		folio_set_count(folio, PAGE_FRAG_CACHE_MAX_SIZE + 1);
 
 		/* reset page count bias and offset to start of new frag */
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		offset = size - fragsz;
-		if (unlikely(offset < 0)) {
+		offset = folio_size(folio);
+		if (unlikely(fragsz > offset)) {
 			/*
 			 * The caller is trying to allocate a fragment
 			 * with fragsz > PAGE_SIZE but the cache isn't big
@@ -107,15 +114,17 @@ void *page_frag_alloc_align(struct page_frag_cache *nc,
 			 * it could make memory pressure worse
 			 * so we simply return NULL here.
 			 */
+			nc->offset = offset;
 			return NULL;
 		}
 	}
 
 	nc->pagecnt_bias--;
+	offset -= fragsz;
 	offset &= align_mask;
 	nc->offset = offset;
 
-	return nc->va + offset;
+	return folio_address(folio) + offset;
 }
 EXPORT_SYMBOL(page_frag_alloc_align);
 
@@ -124,8 +133,6 @@ EXPORT_SYMBOL(page_frag_alloc_align);
  */
 void page_frag_free(void *addr)
 {
-	struct page *page = virt_to_head_page(addr);
-
-	__free_pages(page, compound_order(page));
+	folio_put(virt_to_folio(addr));
 }
 EXPORT_SYMBOL(page_frag_free);