1 files changed, 317 insertions, 104 deletions

diff --git a/net/core/xdp.c b/net/core/xdp.c
index 8310714c47fd..844c9d99dc0e 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -11,11 +11,13 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
+#include <linux/bug.h>
 #include <net/page_pool.h>
 
 #include <net/xdp.h>
 #include <net/xdp_priv.h> /* struct xdp_mem_allocator */
 #include <trace/events/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 #define REG_STATE_NEW		0x0
 #define REG_STATE_REGISTERED	0x1
@@ -108,49 +110,36 @@ static void mem_allocator_disconnect(void *allocator)
 	mutex_unlock(&mem_id_lock);
 }
 
-static void mem_id_disconnect(int id)
+void xdp_unreg_mem_model(struct xdp_mem_info *mem)
 {
 	struct xdp_mem_allocator *xa;
+	int type = mem->type;
+	int id = mem->id;
 
-	mutex_lock(&mem_id_lock);
+	/* Reset mem info to defaults */
+	mem->id = 0;
+	mem->type = 0;
 
-	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
-	if (!xa) {
-		mutex_unlock(&mem_id_lock);
-		WARN(1, "Request remove non-existing id(%d), driver bug?", id);
+	if (id == 0)
 		return;
-	}
 
-	trace_mem_disconnect(xa);
-
-	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
-		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
-
-	mutex_unlock(&mem_id_lock);
+	if (type == MEM_TYPE_PAGE_POOL) {
+		rcu_read_lock();
+		xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
+		page_pool_destroy(xa->page_pool);
+		rcu_read_unlock();
+	}
 }
+EXPORT_SYMBOL_GPL(xdp_unreg_mem_model);
 
 void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
 {
-	struct xdp_mem_allocator *xa;
-	int id = xdp_rxq->mem.id;
-
 	if (xdp_rxq->reg_state != REG_STATE_REGISTERED) {
 		WARN(1, "Missing register, driver bug");
 		return;
 	}
 
-	if (id == 0)
-		return;
-
-	if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY)
-		return mem_id_disconnect(id);
-
-	if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) {
-		rcu_read_lock();
-		xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
-		page_pool_destroy(xa->page_pool);
-		rcu_read_unlock();
-	}
+	xdp_unreg_mem_model(&xdp_rxq->mem);
 }
 EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model);
 
@@ -160,16 +149,10 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
 	if (xdp_rxq->reg_state == REG_STATE_UNUSED)
 		return;
 
-	WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG");
-
 	xdp_rxq_info_unreg_mem_model(xdp_rxq);
 
 	xdp_rxq->reg_state = REG_STATE_UNREGISTERED;
 	xdp_rxq->dev = NULL;
-
-	/* Reset mem info to defaults */
-	xdp_rxq->mem.id = 0;
-	xdp_rxq->mem.type = 0;
 }
 EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg);
 
@@ -179,9 +162,15 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
 }
 
 /* Returns 0 on success, negative on failure */
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index)
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		       struct net_device *dev, u32 queue_index,
+		       unsigned int napi_id, u32 frag_size)
 {
+	if (!dev) {
+		WARN(1, "Missing net_device from driver");
+		return -ENODEV;
+	}
+
 	if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
 		WARN(1, "Driver promised not to register this");
 		return -EINVAL;
@@ -192,20 +181,17 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 		xdp_rxq_info_unreg(xdp_rxq);
 	}
 
-	if (!dev) {
-		WARN(1, "Missing net_device from driver");
-		return -ENODEV;
-	}
-
 	/* State either UNREGISTERED or NEW */
 	xdp_rxq_info_init(xdp_rxq);
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
+	xdp_rxq->napi_id = napi_id;
+	xdp_rxq->frag_size = frag_size;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xdp_rxq_info_reg);
+EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg);
 
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq)
 {
@@ -281,28 +267,24 @@ static bool __is_supported_mem_type(enum xdp_mem_type type)
 	return true;
 }
 
-int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
-			       enum xdp_mem_type type, void *allocator)
+static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem,
+						     enum xdp_mem_type type,
+						     void *allocator)
 {
 	struct xdp_mem_allocator *xdp_alloc;
 	gfp_t gfp = GFP_KERNEL;
 	int id, errno, ret;
 	void *ptr;
 
-	if (xdp_rxq->reg_state != REG_STATE_REGISTERED) {
-		WARN(1, "Missing register, driver bug");
-		return -EFAULT;
-	}
-
 	if (!__is_supported_mem_type(type))
-		return -EOPNOTSUPP;
+		return ERR_PTR(-EOPNOTSUPP);
 
-	xdp_rxq->mem.type = type;
+	mem->type = type;
 
 	if (!allocator) {
-		if (type == MEM_TYPE_PAGE_POOL || type == MEM_TYPE_ZERO_COPY)
-			return -EINVAL; /* Setup time check page_pool req */
-		return 0;
+		if (type == MEM_TYPE_PAGE_POOL)
+			return ERR_PTR(-EINVAL); /* Setup time check page_pool req */
+		return NULL;
 	}
 
 	/* Delay init of rhashtable to save memory if feature isn't used */
@@ -312,13 +294,13 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 		mutex_unlock(&mem_id_lock);
 		if (ret < 0) {
 			WARN_ON(1);
-			return ret;
+			return ERR_PTR(ret);
 		}
 	}
 
 	xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp);
 	if (!xdp_alloc)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	mutex_lock(&mem_id_lock);
 	id = __mem_id_cyclic_get(gfp);
@@ -326,31 +308,62 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 		errno = id;
 		goto err;
 	}
-	xdp_rxq->mem.id = id;
-	xdp_alloc->mem  = xdp_rxq->mem;
+	mem->id = id;
+	xdp_alloc->mem = *mem;
 	xdp_alloc->allocator = allocator;
 
 	/* Insert allocator into ID lookup table */
 	ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node);
 	if (IS_ERR(ptr)) {
-		ida_simple_remove(&mem_id_pool, xdp_rxq->mem.id);
-		xdp_rxq->mem.id = 0;
+		ida_simple_remove(&mem_id_pool, mem->id);
+		mem->id = 0;
 		errno = PTR_ERR(ptr);
 		goto err;
 	}
 
 	if (type == MEM_TYPE_PAGE_POOL)
-		page_pool_use_xdp_mem(allocator, mem_allocator_disconnect);
+		page_pool_use_xdp_mem(allocator, mem_allocator_disconnect, mem);
 
 	mutex_unlock(&mem_id_lock);
 
-	trace_mem_connect(xdp_alloc, xdp_rxq);
-	return 0;
+	return xdp_alloc;
 err:
 	mutex_unlock(&mem_id_lock);
 	kfree(xdp_alloc);
-	return errno;
+	return ERR_PTR(errno);
+}
+
+int xdp_reg_mem_model(struct xdp_mem_info *mem,
+		      enum xdp_mem_type type, void *allocator)
+{
+	struct xdp_mem_allocator *xdp_alloc;
+
+	xdp_alloc = __xdp_reg_mem_model(mem, type, allocator);
+	if (IS_ERR(xdp_alloc))
+		return PTR_ERR(xdp_alloc);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_reg_mem_model);
+
+int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
+			       enum xdp_mem_type type, void *allocator)
+{
+	struct xdp_mem_allocator *xdp_alloc;
+
+	if (xdp_rxq->reg_state != REG_STATE_REGISTERED) {
+		WARN(1, "Missing register, driver bug");
+		return -EFAULT;
+	}
+
+	xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator);
+	if (IS_ERR(xdp_alloc))
+		return PTR_ERR(xdp_alloc);
+
+	if (trace_mem_connect_enabled() && xdp_alloc)
+		trace_mem_connect(xdp_alloc, xdp_rxq);
+	return 0;
 }
+
 EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
 
 /* XDP RX runs under NAPI protection, and in different delivery error
@@ -359,21 +372,20 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
  * is used for those calls sites.  Thus, allowing for faster recycling
  * of xdp_frames/pages in those cases.
  */
-static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
-			 unsigned long handle)
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+		  struct xdp_buff *xdp)
 {
-	struct xdp_mem_allocator *xa;
 	struct page *page;
 
 	switch (mem->type) {
 	case MEM_TYPE_PAGE_POOL:
-		rcu_read_lock();
-		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
-		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		napi_direct &= !xdp_return_frame_no_direct();
-		page_pool_put_page(xa->page_pool, page, napi_direct);
-		rcu_read_unlock();
+		if (napi_direct && xdp_return_frame_no_direct())
+			napi_direct = false;
+		/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
+		 * as mem->type knows this a page_pool page
+		 */
+		page_pool_put_full_page(page->pp, page, napi_direct);
 		break;
 	case MEM_TYPE_PAGE_SHARED:
 		page_frag_free(data);
@@ -382,34 +394,138 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		page = virt_to_page(data); /* Assumes order0 page*/
 		put_page(page);
 		break;
-	case MEM_TYPE_ZERO_COPY:
+	case MEM_TYPE_XSK_BUFF_POOL:
 		/* NB! Only valid from an xdp_buff! */
-		rcu_read_lock();
-		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
-		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
-		xa->zc_alloc->free(xa->zc_alloc, handle);
-		rcu_read_unlock();
+		xsk_buff_free(xdp);
+		break;
 	default:
 		/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
+		WARN(1, "Incorrect XDP memory type (%d) usage", mem->type);
 		break;
 	}
 }
 
 void xdp_return_frame(struct xdp_frame *xdpf)
 {
-	__xdp_return(xdpf->data, &xdpf->mem, false, 0);
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp_frame_has_frags(xdpf)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdpf->mem, false, NULL);
+	}
+out:
+	__xdp_return(xdpf->data, &xdpf->mem, false, NULL);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame);
 
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 {
-	__xdp_return(xdpf->data, &xdpf->mem, true, 0);
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp_frame_has_frags(xdpf)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdpf->mem, true, NULL);
+	}
+out:
+	__xdp_return(xdpf->data, &xdpf->mem, true, NULL);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_allocator *xa = bq->xa;
+
+	if (unlikely(!xa || !bq->count))
+		return;
+
+	page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+	/* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+	bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_info *mem = &xdpf->mem;
+	struct xdp_mem_allocator *xa;
+
+	if (mem->type != MEM_TYPE_PAGE_POOL) {
+		xdp_return_frame(xdpf);
+		return;
+	}
+
+	xa = bq->xa;
+	if (unlikely(!xa)) {
+		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+		bq->count = 0;
+		bq->xa = xa;
+	}
+
+	if (bq->count == XDP_BULK_QUEUE_SIZE)
+		xdp_flush_frame_bulk(bq);
+
+	if (unlikely(mem->id != xa->mem.id)) {
+		xdp_flush_frame_bulk(bq);
+		bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+	}
+
+	if (unlikely(xdp_frame_has_frags(xdpf))) {
+		struct skb_shared_info *sinfo;
+		int i;
+
+		sinfo = xdp_get_shared_info_from_frame(xdpf);
+		for (i = 0; i < sinfo->nr_frags; i++) {
+			skb_frag_t *frag = &sinfo->frags[i];
+
+			bq->q[bq->count++] = skb_frag_address(frag);
+			if (bq->count == XDP_BULK_QUEUE_SIZE)
+				xdp_flush_frame_bulk(bq);
+		}
+	}
+	bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
-	__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle);
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdp->rxq->mem, true, xdp);
+	}
+out:
+	__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp);
 }
 EXPORT_SYMBOL_GPL(xdp_return_buff);
 
@@ -428,27 +544,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem)
 }
 EXPORT_SYMBOL_GPL(__xdp_release_frame);
 
-int xdp_attachment_query(struct xdp_attachment_info *info,
-			 struct netdev_bpf *bpf)
-{
-	bpf->prog_id = info->prog ? info->prog->aux->id : 0;
-	bpf->prog_flags = info->prog ? info->flags : 0;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xdp_attachment_query);
-
-bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
-			     struct netdev_bpf *bpf)
-{
-	if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) {
-		NL_SET_ERR_MSG(bpf->extack,
-			       "program loaded with different flags");
-		return false;
-	}
-	return true;
-}
-EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok);
-
 void xdp_attachment_setup(struct xdp_attachment_info *info,
 			  struct netdev_bpf *bpf)
 {
@@ -490,9 +585,127 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
 	xdpf->len = totsize - metasize;
 	xdpf->headroom = 0;
 	xdpf->metasize = metasize;
+	xdpf->frame_sz = PAGE_SIZE;
 	xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
 
-	xdp_return_buff(xdp);
+	xsk_buff_free(xdp);
 	return xdpf;
 }
 EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame);
+
+/* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */
+void xdp_warn(const char *msg, const char *func, const int line)
+{
+	WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg);
+};
+EXPORT_SYMBOL_GPL(xdp_warn);
+
+int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp)
+{
+	n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp,
+				      n_skb, skbs);
+	if (unlikely(!n_skb))
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk);
+
+struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					   struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
+	unsigned int headroom, frame_size;
+	void *hard_start;
+	u8 nr_frags;
+
+	/* xdp frags frame */
+	if (unlikely(xdp_frame_has_frags(xdpf)))
+		nr_frags = sinfo->nr_frags;
+
+	/* Part of headroom was reserved to xdpf */
+	headroom = sizeof(*xdpf) + xdpf->headroom;
+
+	/* Memory size backing xdp_frame data already have reserved
+	 * room for build_skb to place skb_shared_info in tailroom.
+	 */
+	frame_size = xdpf->frame_sz;
+
+	hard_start = xdpf->data - headroom;
+	skb = build_skb_around(skb, hard_start, frame_size);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, headroom);
+	__skb_put(skb, xdpf->len);
+	if (xdpf->metasize)
+		skb_metadata_set(skb, xdpf->metasize);
+
+	if (unlikely(xdp_frame_has_frags(xdpf)))
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   sinfo->xdp_frags_size,
+					   nr_frags * xdpf->frame_sz,
+					   xdp_frame_is_frag_pfmemalloc(xdpf));
+
+	/* Essential SKB info: protocol and skb->dev */
+	skb->protocol = eth_type_trans(skb, dev);
+
+	/* Optional SKB info, currently missing:
+	 * - HW checksum info		(skb->ip_summed)
+	 * - HW RX hash			(skb_set_hash)
+	 * - RX ring dev queue index	(skb_record_rx_queue)
+	 */
+
+	/* Until page_pool get SKB return path, release DMA here */
+	xdp_release_frame(xdpf);
+
+	/* Allow SKB to reuse area used by xdp_frame */
+	xdp_scrub_frame(xdpf);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame);
+
+struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					 struct net_device *dev)
+{
+	struct sk_buff *skb;
+
+	skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return NULL;
+
+	memset(skb, 0, offsetof(struct sk_buff, tail));
+
+	return __xdp_build_skb_from_frame(xdpf, skb, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
+
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
+{
+	unsigned int headroom, totalsize;
+	struct xdp_frame *nxdpf;
+	struct page *page;
+	void *addr;
+
+	headroom = xdpf->headroom + sizeof(*xdpf);
+	totalsize = headroom + xdpf->len;
+
+	if (unlikely(totalsize > PAGE_SIZE))
+		return NULL;
+	page = dev_alloc_page();
+	if (!page)
+		return NULL;
+	addr = page_to_virt(page);
+
+	memcpy(addr, xdpf, totalsize);
+
+	nxdpf = addr;
+	nxdpf->data = addr + headroom;
+	nxdpf->frame_sz = PAGE_SIZE;
+	nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+	nxdpf->mem.id = 0;
+
+	return nxdpf;
+}