1 files changed, 105 insertions, 45 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 7745ad924ae2..05e2e22a8f7c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -153,9 +153,9 @@ u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats)
 EXPORT_SYMBOL(page_pool_ethtool_stats_get);
 
 #else
-#define alloc_stat_inc(pool, __stat)
-#define recycle_stat_inc(pool, __stat)
-#define recycle_stat_add(pool, __stat, val)
+#define alloc_stat_inc(...)	do { } while (0)
+#define recycle_stat_inc(...)	do { } while (0)
+#define recycle_stat_add(...)	do { } while (0)
 #endif
 
 static bool page_pool_producer_lock(struct page_pool *pool)
@@ -276,8 +276,7 @@ static int page_pool_init(struct page_pool *pool,
 	/* Driver calling page_pool_create() also call page_pool_destroy() */
 	refcount_set(&pool->user_cnt, 1);
 
-	if (pool->dma_map)
-		get_device(pool->p.dev);
+	xa_init_flags(&pool->dma_mapped, XA_FLAGS_ALLOC1);
 
 	if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) {
 		netdev_assert_locked(pool->slow.netdev);
@@ -320,9 +319,7 @@ free_ptr_ring:
 static void page_pool_uninit(struct page_pool *pool)
 {
 	ptr_ring_cleanup(&pool->ring, NULL);
-
-	if (pool->dma_map)
-		put_device(pool->p.dev);
+	xa_destroy(&pool->dma_mapped);
 
 #ifdef CONFIG_PAGE_POOL_STATS
 	if (!pool->system)
@@ -374,7 +371,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
 }
 EXPORT_SYMBOL(page_pool_create);
 
-static void page_pool_return_page(struct page_pool *pool, netmem_ref netmem);
+static void page_pool_return_netmem(struct page_pool *pool, netmem_ref netmem);
 
 static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool)
 {
@@ -412,7 +409,7 @@ static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool)
 			 * (2) break out to fallthrough to alloc_pages_node.
 			 * This limit stress on page buddy alloactor.
 			 */
-			page_pool_return_page(pool, netmem);
+			page_pool_return_netmem(pool, netmem);
 			alloc_stat_inc(pool, waive);
 			netmem = 0;
 			break;
@@ -463,13 +460,21 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
 			      netmem_ref netmem,
 			      u32 dma_sync_size)
 {
-	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
-		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
+	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev)) {
+		rcu_read_lock();
+		/* re-check under rcu_read_lock() to sync with page_pool_scrub() */
+		if (pool->dma_sync)
+			__page_pool_dma_sync_for_device(pool, netmem,
+							dma_sync_size);
+		rcu_read_unlock();
+	}
 }
 
-static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
+static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem, gfp_t gfp)
 {
 	dma_addr_t dma;
+	int err;
+	u32 id;
 
 	/* 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
@@ -483,15 +488,30 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
-	if (page_pool_set_dma_addr_netmem(netmem, dma))
+	if (page_pool_set_dma_addr_netmem(netmem, dma)) {
+		WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 		goto unmap_failed;
+	}
 
+	if (in_softirq())
+		err = xa_alloc(&pool->dma_mapped, &id, netmem_to_page(netmem),
+			       PP_DMA_INDEX_LIMIT, gfp);
+	else
+		err = xa_alloc_bh(&pool->dma_mapped, &id, netmem_to_page(netmem),
+				  PP_DMA_INDEX_LIMIT, gfp);
+	if (err) {
+		WARN_ONCE(err != -ENOMEM, "couldn't track DMA mapping, please report to netdev@");
+		goto unset_failed;
+	}
+
+	netmem_set_dma_index(netmem, id);
 	page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len);
 
 	return true;
 
+unset_failed:
+	page_pool_set_dma_addr_netmem(netmem, 0);
 unmap_failed:
-	WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 	dma_unmap_page_attrs(pool->p.dev, dma,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
@@ -508,7 +528,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 	if (unlikely(!page))
 		return NULL;
 
-	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) {
+	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page), gfp))) {
 		put_page(page);
 		return NULL;
 	}
@@ -524,8 +544,8 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 }
 
 /* slow path */
-static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool,
-							gfp_t gfp)
+static noinline netmem_ref __page_pool_alloc_netmems_slow(struct page_pool *pool,
+							  gfp_t gfp)
 {
 	const int bulk = PP_ALLOC_CACHE_REFILL;
 	unsigned int pp_order = pool->p.order;
@@ -554,7 +574,7 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool,
 	 */
 	for (i = 0; i < nr_pages; i++) {
 		netmem = pool->alloc.cache[i];
-		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem))) {
+		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem, gfp))) {
 			put_page(netmem_to_page(netmem));
 			continue;
 		}
@@ -595,7 +615,7 @@ netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp)
 	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
 		netmem = pool->mp_ops->alloc_netmems(pool, gfp);
 	else
-		netmem = __page_pool_alloc_pages_slow(pool, gfp);
+		netmem = __page_pool_alloc_netmems_slow(pool, gfp);
 	return netmem;
 }
 EXPORT_SYMBOL(page_pool_alloc_netmems);
@@ -653,9 +673,11 @@ void page_pool_clear_pp_info(netmem_ref netmem)
 	netmem_set_pp(netmem, NULL);
 }
 
-static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
-							 netmem_ref netmem)
+static __always_inline void __page_pool_release_netmem_dma(struct page_pool *pool,
+							   netmem_ref netmem)
 {
+	struct page *old, *page = netmem_to_page(netmem);
+	unsigned long id;
 	dma_addr_t dma;
 
 	if (!pool->dma_map)
@@ -664,6 +686,17 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 		 */
 		return;
 
+	id = netmem_get_dma_index(netmem);
+	if (!id)
+		return;
+
+	if (in_softirq())
+		old = xa_cmpxchg(&pool->dma_mapped, id, page, NULL, 0);
+	else
+		old = xa_cmpxchg_bh(&pool->dma_mapped, id, page, NULL, 0);
+	if (old != page)
+		return;
+
 	dma = page_pool_get_dma_addr_netmem(netmem);
 
 	/* When page is unmapped, it cannot be returned to our pool */
@@ -671,6 +704,7 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr_netmem(netmem, 0);
+	netmem_set_dma_index(netmem, 0);
 }
 
 /* Disconnects a page (from a page_pool).  API users can have a need
@@ -678,7 +712,7 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
  * a regular page (that will eventually be returned to the normal
  * page-allocator via put_page).
  */
-void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
+static void page_pool_return_netmem(struct page_pool *pool, netmem_ref netmem)
 {
 	int count;
 	bool put;
@@ -687,7 +721,7 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
 		put = pool->mp_ops->release_netmem(pool, netmem);
 	else
-		__page_pool_release_page_dma(pool, netmem);
+		__page_pool_release_netmem_dma(pool, netmem);
 
 	/* This may be the last page returned, releasing the pool, so
 	 * it is not safe to reference pool afterwards.
@@ -707,19 +741,16 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 
 static bool page_pool_recycle_in_ring(struct page_pool *pool, netmem_ref netmem)
 {
-	int ret;
-	/* BH protection not needed if current is softirq */
-	if (in_softirq())
-		ret = ptr_ring_produce(&pool->ring, (__force void *)netmem);
-	else
-		ret = ptr_ring_produce_bh(&pool->ring, (__force void *)netmem);
+	bool in_softirq, ret;
 
-	if (!ret) {
+	/* BH protection not needed if current is softirq */
+	in_softirq = page_pool_producer_lock(pool);
+	ret = !__ptr_ring_produce(&pool->ring, (__force void *)netmem);
+	if (ret)
 		recycle_stat_inc(pool, ring);
-		return true;
-	}
+	page_pool_producer_unlock(pool, in_softirq);
 
-	return false;
+	return ret;
 }
 
 /* Only allow direct recycling in special circumstances, into the
@@ -795,7 +826,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem,
 	 * will be invoking put_page.
 	 */
 	recycle_stat_inc(pool, released_refcnt);
-	page_pool_return_page(pool, netmem);
+	page_pool_return_netmem(pool, netmem);
 
 	return 0;
 }
@@ -805,6 +836,10 @@ static bool page_pool_napi_local(const struct page_pool *pool)
 	const struct napi_struct *napi;
 	u32 cpuid;
 
+	/* On PREEMPT_RT the softirq can be preempted by the consumer */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		return false;
+
 	if (unlikely(!in_softirq()))
 		return false;
 
@@ -829,12 +864,12 @@ void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
 	if (!allow_direct)
 		allow_direct = page_pool_napi_local(pool);
 
-	netmem =
-		__page_pool_put_page(pool, netmem, dma_sync_size, allow_direct);
+	netmem = __page_pool_put_page(pool, netmem, dma_sync_size,
+				      allow_direct);
 	if (netmem && !page_pool_recycle_in_ring(pool, netmem)) {
 		/* Cache full, fallback to free pages */
 		recycle_stat_inc(pool, ring_full);
-		page_pool_return_page(pool, netmem);
+		page_pool_return_netmem(pool, netmem);
 	}
 }
 EXPORT_SYMBOL(page_pool_put_unrefed_netmem);
@@ -877,7 +912,7 @@ static void page_pool_recycle_ring_bulk(struct page_pool *pool,
 	 * since put_page() with refcnt == 1 can be an expensive operation.
 	 */
 	for (; i < bulk_len; i++)
-		page_pool_return_page(pool, bulk[i]);
+		page_pool_return_netmem(pool, bulk[i]);
 }
 
 /**
@@ -960,7 +995,7 @@ static netmem_ref page_pool_drain_frag(struct page_pool *pool,
 		return netmem;
 	}
 
-	page_pool_return_page(pool, netmem);
+	page_pool_return_netmem(pool, netmem);
 	return 0;
 }
 
@@ -974,7 +1009,7 @@ static void page_pool_free_frag(struct page_pool *pool)
 	if (!netmem || page_pool_unref_netmem(netmem, drain_count))
 		return;
 
-	page_pool_return_page(pool, netmem);
+	page_pool_return_netmem(pool, netmem);
 }
 
 netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool,
@@ -1041,7 +1076,7 @@ static void page_pool_empty_ring(struct page_pool *pool)
 			pr_crit("%s() page_pool refcnt %d violation\n",
 				__func__, netmem_ref_count(netmem));
 
-		page_pool_return_page(pool, netmem);
+		page_pool_return_netmem(pool, netmem);
 	}
 }
 
@@ -1074,14 +1109,35 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
 	 */
 	while (pool->alloc.count) {
 		netmem = pool->alloc.cache[--pool->alloc.count];
-		page_pool_return_page(pool, netmem);
+		page_pool_return_netmem(pool, netmem);
 	}
 }
 
 static void page_pool_scrub(struct page_pool *pool)
 {
+	unsigned long id;
+	void *ptr;
+
 	page_pool_empty_alloc_cache_once(pool);
-	pool->destroy_cnt++;
+	if (!pool->destroy_cnt++ && pool->dma_map) {
+		if (pool->dma_sync) {
+			/* Disable page_pool_dma_sync_for_device() */
+			pool->dma_sync = false;
+
+			/* Make sure all concurrent returns that may see the old
+			 * value of dma_sync (and thus perform a sync) have
+			 * finished before doing the unmapping below. Skip the
+			 * wait if the device doesn't actually need syncing, or
+			 * if there are no outstanding mapped pages.
+			 */
+			if (dma_dev_need_sync(pool->p.dev) &&
+			    !xa_empty(&pool->dma_mapped))
+				synchronize_net();
+		}
+
+		xa_for_each(&pool->dma_mapped, id, ptr)
+			__page_pool_release_netmem_dma(pool, page_to_netmem((struct page *)ptr));
+	}
 
 	/* No more consumers should exist, but producers could still
 	 * be in-flight.
@@ -1091,10 +1147,14 @@ static void page_pool_scrub(struct page_pool *pool)
 
 static int page_pool_release(struct page_pool *pool)
 {
+	bool in_softirq;
 	int inflight;
 
 	page_pool_scrub(pool);
 	inflight = page_pool_inflight(pool, true);
+	/* Acquire producer lock to make sure producers have exited. */
+	in_softirq = page_pool_producer_lock(pool);
+	page_pool_producer_unlock(pool, in_softirq);
 	if (!inflight)
 		__page_pool_destroy(pool);
 
@@ -1193,7 +1253,7 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	/* Flush pool alloc cache, as refill will check NUMA node */
 	while (pool->alloc.count) {
 		netmem = pool->alloc.cache[--pool->alloc.count];
-		page_pool_return_page(pool, netmem);
+		page_pool_return_netmem(pool, netmem);
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);