1 files changed, 58 insertions, 6 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 193c18799865..a3e12a61d456 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h> /* for put_page() */
 #include <linux/poison.h>
 #include <linux/ethtool.h>
+#include <linux/netdevice.h>
 
 #include <trace/events/page_pool.h>
 
@@ -133,6 +134,29 @@ EXPORT_SYMBOL(page_pool_ethtool_stats_get);
 #define recycle_stat_add(pool, __stat, val)
 #endif
 
+static bool page_pool_producer_lock(struct page_pool *pool)
+	__acquires(&pool->ring.producer_lock)
+{
+	bool in_softirq = in_softirq();
+
+	if (in_softirq)
+		spin_lock(&pool->ring.producer_lock);
+	else
+		spin_lock_bh(&pool->ring.producer_lock);
+
+	return in_softirq;
+}
+
+static void page_pool_producer_unlock(struct page_pool *pool,
+				      bool in_softirq)
+	__releases(&pool->ring.producer_lock)
+{
+	if (in_softirq)
+		spin_unlock(&pool->ring.producer_lock);
+	else
+		spin_unlock_bh(&pool->ring.producer_lock);
+}
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
@@ -315,7 +339,8 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	 */
 	dma = dma_map_page_attrs(pool->p.dev, page, 0,
 				 (PAGE_SIZE << pool->p.order),
-				 pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
+				 pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC |
+						  DMA_ATTR_WEAK_ORDERING);
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
@@ -483,7 +508,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
 	/* When page is unmapped, it cannot be returned to our pool */
 	dma_unmap_page_attrs(pool->p.dev, dma,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
-			     DMA_ATTR_SKIP_CPU_SYNC);
+			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr(page, 0);
 skip_dma_unmap:
 	page_pool_clear_pp_info(page);
@@ -615,6 +640,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 			     int count)
 {
 	int i, bulk_len = 0;
+	bool in_softirq;
 
 	for (i = 0; i < count; i++) {
 		struct page *page = virt_to_head_page(data[i]);
@@ -633,7 +659,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 		return;
 
 	/* Bulk producer into ptr_ring page_pool cache */
-	page_pool_ring_lock(pool);
+	in_softirq = page_pool_producer_lock(pool);
 	for (i = 0; i < bulk_len; i++) {
 		if (__ptr_ring_produce(&pool->ring, data[i])) {
 			/* ring full */
@@ -642,7 +668,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 		}
 	}
 	recycle_stat_add(pool, ring, i);
-	page_pool_ring_unlock(pool);
+	page_pool_producer_unlock(pool, in_softirq);
 
 	/* Hopefully all pages was return into ptr_ring */
 	if (likely(i == bulk_len))
@@ -837,6 +863,21 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
 	pool->xdp_mem_id = mem->id;
 }
 
+void page_pool_unlink_napi(struct page_pool *pool)
+{
+	if (!pool->p.napi)
+		return;
+
+	/* To avoid races with recycling and additional barriers make sure
+	 * pool and NAPI are unlinked when NAPI is disabled.
+	 */
+	WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state) ||
+		READ_ONCE(pool->p.napi->list_owner) != -1);
+
+	WRITE_ONCE(pool->p.napi, NULL);
+}
+EXPORT_SYMBOL(page_pool_unlink_napi);
+
 void page_pool_destroy(struct page_pool *pool)
 {
 	if (!pool)
@@ -845,6 +886,7 @@ void page_pool_destroy(struct page_pool *pool)
 	if (!page_pool_put(pool))
 		return;
 
+	page_pool_unlink_napi(pool);
 	page_pool_free_frag(pool);
 
 	if (!page_pool_release(pool))
@@ -874,9 +916,11 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 }
 EXPORT_SYMBOL(page_pool_update_nid);
 
-bool page_pool_return_skb_page(struct page *page)
+bool page_pool_return_skb_page(struct page *page, bool napi_safe)
 {
+	struct napi_struct *napi;
 	struct page_pool *pp;
+	bool allow_direct;
 
 	page = compound_head(page);
 
@@ -892,12 +936,20 @@ bool page_pool_return_skb_page(struct page *page)
 
 	pp = page->pp;
 
+	/* Allow direct recycle if we have reasons to believe that we are
+	 * in the same context as the consumer would run, so there's
+	 * no possible race.
+	 */
+	napi = READ_ONCE(pp->p.napi);
+	allow_direct = napi_safe && napi &&
+		READ_ONCE(napi->list_owner) == smp_processor_id();
+
 	/* Driver set this to memory recycling info. Reset it on recycle.
 	 * This will *not* work for NIC using a split-page memory model.
 	 * The page will be returned to the pool here regardless of the
 	 * 'flipped' fragment being in use or not.
 	 */
-	page_pool_put_full_page(pp, page, false);
+	page_pool_put_full_page(pp, page, allow_direct);
 
 	return true;
 }