Merge tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - optimize DMA sync calls when they are no-ops (Alexander Lobakin)

 - fix swiotlb padding for untrusted devices (Michael Kelley)

 - add documentation for swiotb (Michael Kelley)

* tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping:
  dma: fix DMA sync for drivers not calling dma_set_mask*()
  xsk: use generic DMA sync shortcut instead of a custom one
  page_pool: check for DMA sync shortcut earlier
  page_pool: don't use driver-set flags field directly
  page_pool: make sure frag API fields don't span between cachelines
  iommu/dma: avoid expensive indirect calls for sync operations
  dma: avoid redundant calls for sync operations
  dma: compile-out DMA sync op calls when not used
  iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices
  swiotlb: remove alloc_size argument to swiotlb_tbl_map_single()
  Documentation/core-api: add swiotlb documentation

2 files changed, 52 insertions, 55 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 8bcc7014a61a..f4444b4e39e6 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -173,19 +173,29 @@ static void page_pool_producer_unlock(struct page_pool *pool,
 		spin_unlock_bh(&pool->ring.producer_lock);
 }
 
+static void page_pool_struct_check(void)
+{
+	CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_users);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_page);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_offset);
+	CACHELINE_ASSERT_GROUP_SIZE(struct page_pool, frag, 4 * sizeof(long));
+}
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params,
 			  int cpuid)
 {
 	unsigned int ring_qsize = 1024; /* Default */
 
+	page_pool_struct_check();
+
 	memcpy(&pool->p, &params->fast, sizeof(pool->p));
 	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	pool->cpuid = cpuid;
 
 	/* Validate only known flags were used */
-	if (pool->p.flags & ~(PP_FLAG_ALL))
+	if (pool->slow.flags & ~PP_FLAG_ALL)
 		return -EINVAL;
 
 	if (pool->p.pool_size)
@@ -199,22 +209,26 @@ static int page_pool_init(struct page_pool *pool,
 	 * DMA_BIDIRECTIONAL is for allowing page used for DMA sending,
 	 * which is the XDP_TX use-case.
 	 */
-	if (pool->p.flags & PP_FLAG_DMA_MAP) {
+	if (pool->slow.flags & PP_FLAG_DMA_MAP) {
 		if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
 		    (pool->p.dma_dir != DMA_BIDIRECTIONAL))
 			return -EINVAL;
+
+		pool->dma_map = true;
 	}
 
-	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+	if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) {
 		/* In order to request DMA-sync-for-device the page
 		 * needs to be mapped
 		 */
-		if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+		if (!(pool->slow.flags & PP_FLAG_DMA_MAP))
 			return -EINVAL;
 
 		if (!pool->p.max_len)
 			return -EINVAL;
 
+		pool->dma_sync = true;
+
 		/* pool->p.offset has to be set according to the address
 		 * offset used by the DMA engine to start copying rx data
 		 */
@@ -223,7 +237,7 @@ static int page_pool_init(struct page_pool *pool,
 	pool->has_init_callback = !!pool->slow.init_callback;
 
 #ifdef CONFIG_PAGE_POOL_STATS
-	if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) {
+	if (!(pool->slow.flags & PP_FLAG_SYSTEM_POOL)) {
 		pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
 		if (!pool->recycle_stats)
 			return -ENOMEM;
@@ -233,12 +247,13 @@ static int page_pool_init(struct page_pool *pool,
 		 * (also percpu) page pool instance.
 		 */
 		pool->recycle_stats = &pp_system_recycle_stats;
+		pool->system = true;
 	}
 #endif
 
 	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) {
 #ifdef CONFIG_PAGE_POOL_STATS
-		if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+		if (!pool->system)
 			free_percpu(pool->recycle_stats);
 #endif
 		return -ENOMEM;
@@ -249,7 +264,7 @@ 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->p.flags & PP_FLAG_DMA_MAP)
+	if (pool->dma_map)
 		get_device(pool->p.dev);
 
 	return 0;
@@ -259,11 +274,11 @@ static void page_pool_uninit(struct page_pool *pool)
 {
 	ptr_ring_cleanup(&pool->ring, NULL);
 
-	if (pool->p.flags & PP_FLAG_DMA_MAP)
+	if (pool->dma_map)
 		put_device(pool->p.dev);
 
 #ifdef CONFIG_PAGE_POOL_STATS
-	if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+	if (!pool->system)
 		free_percpu(pool->recycle_stats);
 #endif
 }
@@ -384,16 +399,26 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
 	return page;
 }
 
-static void page_pool_dma_sync_for_device(const struct page_pool *pool,
-					  const struct page *page,
-					  unsigned int dma_sync_size)
+static void __page_pool_dma_sync_for_device(const struct page_pool *pool,
+					    const struct page *page,
+					    u32 dma_sync_size)
 {
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
 	dma_addr_t dma_addr = page_pool_get_dma_addr(page);
 
 	dma_sync_size = min(dma_sync_size, pool->p.max_len);
-	dma_sync_single_range_for_device(pool->p.dev, dma_addr,
-					 pool->p.offset, dma_sync_size,
-					 pool->p.dma_dir);
+	__dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset,
+				     dma_sync_size, pool->p.dma_dir);
+#endif
+}
+
+static __always_inline void
+page_pool_dma_sync_for_device(const struct page_pool *pool,
+			      const struct page *page,
+			      u32 dma_sync_size)
+{
+	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
+		__page_pool_dma_sync_for_device(pool, page, dma_sync_size);
 }
 
 static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
@@ -415,8 +440,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	if (page_pool_set_dma_addr(page, dma))
 		goto unmap_failed;
 
-	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
-		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+	page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
 
 	return true;
 
@@ -461,8 +485,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 	if (unlikely(!page))
 		return NULL;
 
-	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
-	    unlikely(!page_pool_dma_map(pool, page))) {
+	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page))) {
 		put_page(page);
 		return NULL;
 	}
@@ -482,8 +505,8 @@ 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;
+	bool dma_map = pool->dma_map;
 	struct page *page;
 	int i, nr_pages;
 
@@ -508,8 +531,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	 */
 	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))) {
+		if (dma_map && unlikely(!page_pool_dma_map(pool, page))) {
 			put_page(page);
 			continue;
 		}
@@ -582,7 +604,7 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
 {
 	dma_addr_t dma;
 
-	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+	if (!pool->dma_map)
 		/* Always account for inflight pages, even if we didn't
 		 * map them
 		 */
@@ -665,7 +687,7 @@ static bool __page_pool_page_can_be_recycled(const struct page *page)
 }
 
 /* If the page refcnt == 1, this will try to recycle the page.
- * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for
+ * If pool->dma_sync is set, we'll try to sync the DMA area for
  * the configured size min(dma_sync_size, pool->max_len).
  * If the page refcnt != 1, then the page will be returned to memory
  * subsystem.
@@ -688,9 +710,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	if (likely(__page_pool_page_can_be_recycled(page))) {
 		/* Read barrier done in page_ref_count / READ_ONCE */
 
-		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
-			page_pool_dma_sync_for_device(pool, page,
-						      dma_sync_size);
+		page_pool_dma_sync_for_device(pool, page, dma_sync_size);
 
 		if (allow_direct && page_pool_recycle_in_cache(page, pool))
 			return NULL;
@@ -829,9 +849,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
 		return NULL;
 
 	if (__page_pool_page_can_be_recycled(page)) {
-		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
-			page_pool_dma_sync_for_device(pool, page, -1);
-
+		page_pool_dma_sync_for_device(pool, page, -1);
 		return page;
 	}
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index ce60ecd48a4d..c0e0204b9630 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -338,7 +338,6 @@ static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_devi
 
 	dma_map->netdev = netdev;
 	dma_map->dev = dev;
-	dma_map->dma_need_sync = false;
 	dma_map->dma_pages_cnt = nr_pages;
 	refcount_set(&dma_map->users, 1);
 	list_add(&dma_map->list, &umem->xsk_dma_list);
@@ -424,7 +423,6 @@ static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_
 
 	pool->dev = dma_map->dev;
 	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
-	pool->dma_need_sync = dma_map->dma_need_sync;
 	memcpy(pool->dma_pages, dma_map->dma_pages,
 	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));
 
@@ -460,8 +458,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 			__xp_dma_unmap(dma_map, attrs);
 			return -ENOMEM;
 		}
-		if (dma_need_sync(dev, dma))
-			dma_map->dma_need_sync = true;
 		dma_map->dma_pages[i] = dma;
 	}
 
@@ -557,11 +553,9 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 	xskb->xdp.data_meta = xskb->xdp.data;
 	xskb->xdp.flags = 0;
 
-	if (pool->dma_need_sync) {
-		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
-						 pool->frame_len,
-						 DMA_BIDIRECTIONAL);
-	}
+	if (pool->dev)
+		xp_dma_sync_for_device(pool, xskb->dma, pool->frame_len);
+
 	return &xskb->xdp;
 }
 EXPORT_SYMBOL(xp_alloc);
@@ -633,7 +627,7 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 {
 	u32 nb_entries1 = 0, nb_entries2;
 
-	if (unlikely(pool->dma_need_sync)) {
+	if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) {
 		struct xdp_buff *buff;
 
 		/* Slow path */
@@ -693,18 +687,3 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
 		(addr & ~PAGE_MASK);
 }
 EXPORT_SYMBOL(xp_raw_get_dma);
-
-void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb)
-{
-	dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0,
-				      xskb->pool->frame_len, DMA_BIDIRECTIONAL);
-}
-EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow);
-
-void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
-				 size_t size)
-{
-	dma_sync_single_range_for_device(pool->dev, dma, 0,
-					 size, DMA_BIDIRECTIONAL);
-}
-EXPORT_SYMBOL(xp_dma_sync_for_device_slow);