Merge branch 'xdp-a-fistful-of-generic-changes-pt-iii'

Alexander Lobakin says:

====================
xdp: a fistful of generic changes pt. III

XDP for idpf is currently 5.(6) chapters:
* convert Rx to libeth;
* convert Tx and stats to libeth;
* generic XDP and XSk code changes;
* generic XDP and XSk code additions pt. 1;
* generic XDP and XSk code additions pt. 2 (you are here);
* actual XDP for idpf via new libeth_xdp;
* XSk for idpf (via ^).

Part III.3 does the following:
* adds generic functions to build skbs from xdp_buffs (regular and
  XSk) and attach frags to xdp_buffs (regular and XSk);
* adds helper to optimize XSk xmit in drivers.

Everything is prereq for libeth_xdp, but will be useful standalone
as well: less code in drivers, faster XSk XDP_PASS, smaller object
code.
====================

Link: https://patch.msgid.link/20241218174435.1445282-1-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 316 insertions, 65 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 4e885df789ef..e28f1905a4a0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -395,32 +395,6 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 	WARN_ON_ONCE(1);
 }
 
-static int
-i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first,
-		  struct xdp_buff *xdp, const unsigned int size)
-{
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
-
-	if (!xdp_buff_has_frags(first)) {
-		sinfo->nr_frags = 0;
-		sinfo->xdp_frags_size = 0;
-		xdp_buff_set_frags_flag(first);
-	}
-
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		xsk_buff_free(first);
-		return -ENOMEM;
-	}
-
-	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start),
-				   XDP_PACKET_HEADROOM, size);
-	sinfo->xdp_frags_size += size;
-	xsk_buff_add_frag(xdp);
-
-	return 0;
-}
-
 /**
  * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
  * @rx_ring: Rx ring
@@ -486,8 +460,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 
 		if (!first)
 			first = bi;
-		else if (i40e_add_xsk_frag(rx_ring, first, bi, size))
+		else if (!xsk_buff_add_frag(first, bi)) {
+			xsk_buff_free(first);
 			break;
+		}
 
 		if (++next_to_process == count)
 			next_to_process = 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 334ae945d640..8975d2971bc3 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -801,35 +801,6 @@ out_failure:
 	return result;
 }
 
-static int
-ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
-		 struct xdp_buff *xdp, const unsigned int size)
-{
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
-
-	if (!size)
-		return 0;
-
-	if (!xdp_buff_has_frags(first)) {
-		sinfo->nr_frags = 0;
-		sinfo->xdp_frags_size = 0;
-		xdp_buff_set_frags_flag(first);
-	}
-
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		xsk_buff_free(first);
-		return -ENOMEM;
-	}
-
-	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start),
-				   XDP_PACKET_HEADROOM, size);
-	sinfo->xdp_frags_size += size;
-	xsk_buff_add_frag(xdp);
-
-	return 0;
-}
-
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
@@ -895,7 +866,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 
 		if (!first) {
 			first = xdp;
-		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
+		} else if (likely(size) && !xsk_buff_add_frag(first, xdp)) {
+			xsk_buff_free(first);
 			break;
 		}
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b2509cd0b930..bb2b751d274a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -608,11 +608,19 @@ struct skb_shared_info {
 	 * Warning : all fields before dataref are cleared in __alloc_skb()
 	 */
 	atomic_t	dataref;
-	unsigned int	xdp_frags_size;
 
-	/* Intermediate layers must ensure that destructor_arg
-	 * remains valid until skb destructor */
-	void *		destructor_arg;
+	union {
+		struct {
+			u32		xdp_frags_size;
+			u32		xdp_frags_truesize;
+		};
+
+		/*
+		 * Intermediate layers must ensure that destructor_arg
+		 * remains valid until skb destructor.
+		 */
+		void		*destructor_arg;
+	};
 
 	/* must be last field, see pskb_expand_head() */
 	skb_frag_t	frags[MAX_SKB_FRAGS];
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 776a3008ac28..543f54fa3020 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -144,6 +144,15 @@ static inline netmem_ref page_pool_alloc_netmem(struct page_pool *pool,
 	return netmem;
 }
 
+static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool,
+						    unsigned int *offset,
+						    unsigned int *size)
+{
+	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+
+	return page_pool_alloc_netmem(pool, offset, size, gfp);
+}
+
 static inline struct page *page_pool_alloc(struct page_pool *pool,
 					   unsigned int *offset,
 					   unsigned int *size, gfp_t gfp)
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d2089cfecefd..6da0e746cf75 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -167,6 +167,93 @@ out:
 	return len;
 }
 
+void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp);
+
+/**
+ * __xdp_buff_add_frag - attach frag to &xdp_buff
+ * @xdp: XDP buffer to attach the frag to
+ * @netmem: network memory containing the frag
+ * @offset: offset at which the frag starts
+ * @size: size of the frag
+ * @truesize: total memory size occupied by the frag
+ * @try_coalesce: whether to try coalescing the frags (not valid for XSk)
+ *
+ * Attach frag to the XDP buffer. If it currently has no frags attached,
+ * initialize the related fields, otherwise check that the frag number
+ * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing
+ * the frag with the previous one.
+ * The function doesn't check/update the pfmemalloc bit. Please use the
+ * non-underscored wrapper in drivers.
+ *
+ * Return: true on success, false if there's no space for the frag in
+ * the shared info struct.
+ */
+static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem,
+				       u32 offset, u32 size, u32 truesize,
+				       bool try_coalesce)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	skb_frag_t *prev;
+	u32 nr_frags;
+
+	if (!xdp_buff_has_frags(xdp)) {
+		xdp_buff_set_frags_flag(xdp);
+
+		nr_frags = 0;
+		sinfo->xdp_frags_size = 0;
+		sinfo->xdp_frags_truesize = 0;
+
+		goto fill;
+	}
+
+	nr_frags = sinfo->nr_frags;
+	prev = &sinfo->frags[nr_frags - 1];
+
+	if (try_coalesce && netmem == skb_frag_netmem(prev) &&
+	    offset == skb_frag_off(prev) + skb_frag_size(prev)) {
+		skb_frag_size_add(prev, size);
+		/* Guaranteed to only decrement the refcount */
+		xdp_return_frag(netmem, xdp);
+	} else if (unlikely(nr_frags == MAX_SKB_FRAGS)) {
+		return false;
+	} else {
+fill:
+		__skb_fill_netmem_desc_noacc(sinfo, nr_frags++, netmem,
+					     offset, size);
+	}
+
+	sinfo->nr_frags = nr_frags;
+	sinfo->xdp_frags_size += size;
+	sinfo->xdp_frags_truesize += truesize;
+
+	return true;
+}
+
+/**
+ * xdp_buff_add_frag - attach frag to &xdp_buff
+ * @xdp: XDP buffer to attach the frag to
+ * @netmem: network memory containing the frag
+ * @offset: offset at which the frag starts
+ * @size: size of the frag
+ * @truesize: total memory size occupied by the frag
+ *
+ * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit.
+ *
+ * Return: true on success, false if there's no space for the frag in
+ * the shared info struct.
+ */
+static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem,
+				     u32 offset, u32 size, u32 truesize)
+{
+	if (!__xdp_buff_add_frag(xdp, netmem, offset, size, truesize, true))
+		return false;
+
+	if (unlikely(netmem_is_pfmemalloc(netmem)))
+		xdp_buff_set_frag_pfmemalloc(xdp);
+
+	return true;
+}
+
 struct xdp_frame {
 	void *data;
 	u32 len;
@@ -230,7 +317,14 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
 			   unsigned int size, unsigned int truesize,
 			   bool pfmemalloc)
 {
-	skb_shinfo(skb)->nr_frags = nr_frags;
+	struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+	sinfo->nr_frags = nr_frags;
+	/*
+	 * ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``,
+	 * reset it after that these fields aren't used anymore.
+	 */
+	sinfo->destructor_arg = NULL;
 
 	skb->len += size;
 	skb->data_len += size;
@@ -242,6 +336,8 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
 void xdp_warn(const char *msg, const char *func, const int line);
 #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
 
+struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp);
+struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp);
 struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
 struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index f3175a5d28f7..86620c818965 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -136,11 +136,21 @@ out:
 	xp_free(xskb);
 }
 
-static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+static inline bool xsk_buff_add_frag(struct xdp_buff *head,
+				     struct xdp_buff *xdp)
 {
-	struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
+	const void *data = xdp->data;
+	struct xdp_buff_xsk *frag;
+
+	if (!__xdp_buff_add_frag(head, virt_to_netmem(data),
+				 offset_in_page(data), xdp->data_end - data,
+				 xdp->frame_sz, false))
+		return false;
 
+	frag = container_of(xdp, struct xdp_buff_xsk, xdp);
 	list_add_tail(&frag->list_node, &frag->pool->xskb_list);
+
+	return true;
 }
 
 static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
@@ -357,8 +367,10 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
-static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+static inline bool xsk_buff_add_frag(struct xdp_buff *head,
+				     struct xdp_buff *xdp)
 {
+	return false;
 }
 
 static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index f1165a35411b..67b53fc7191e 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -535,6 +535,17 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf,
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
 
+/**
+ * xdp_return_frag -- free one XDP frag or decrement its refcount
+ * @netmem: network memory reference to release
+ * @xdp: &xdp_buff to release the frag for
+ */
+void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp)
+{
+	__xdp_return(netmem, xdp->rxq->mem.type, true, NULL);
+}
+EXPORT_SYMBOL_GPL(xdp_return_frag);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo;
@@ -618,6 +629,173 @@ int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk);
 
+/**
+ * xdp_build_skb_from_buff - create an skb from &xdp_buff
+ * @xdp: &xdp_buff to convert to an skb
+ *
+ * Perform common operations to create a new skb to pass up the stack from
+ * &xdp_buff: allocate an skb head from the NAPI percpu cache, initialize
+ * skb data pointers and offsets, set the recycle bit if the buff is
+ * PP-backed, Rx queue index, protocol and update frags info.
+ *
+ * Return: new &sk_buff on success, %NULL on error.
+ */
+struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp)
+{
+	const struct xdp_rxq_info *rxq = xdp->rxq;
+	const struct skb_shared_info *sinfo;
+	struct sk_buff *skb;
+	u32 nr_frags = 0;
+	int metalen;
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
+
+	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	__skb_put(skb, xdp->data_end - xdp->data);
+
+	metalen = xdp->data - xdp->data_meta;
+	if (metalen > 0)
+		skb_metadata_set(skb, metalen);
+
+	if (rxq->mem.type == MEM_TYPE_PAGE_POOL)
+		skb_mark_for_recycle(skb);
+
+	skb_record_rx_queue(skb, rxq->queue_index);
+
+	if (unlikely(nr_frags)) {
+		u32 tsize;
+
+		tsize = sinfo->xdp_frags_truesize ? : nr_frags * xdp->frame_sz;
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   sinfo->xdp_frags_size, tsize,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
+	}
+
+	skb->protocol = eth_type_trans(skb, rxq->dev);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(xdp_build_skb_from_buff);
+
+/**
+ * xdp_copy_frags_from_zc - copy frags from XSk buff to skb
+ * @skb: skb to copy frags to
+ * @xdp: XSk &xdp_buff from which the frags will be copied
+ * @pp: &page_pool backing page allocation, if available
+ *
+ * Copy all frags from XSk &xdp_buff to the skb to pass it up the stack.
+ * Allocate a new buffer for each frag, copy it and attach to the skb.
+ *
+ * Return: true on success, false on netmem allocation fail.
+ */
+static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb,
+					    const struct xdp_buff *xdp,
+					    struct page_pool *pp)
+{
+	struct skb_shared_info *sinfo = skb_shinfo(skb);
+	const struct skb_shared_info *xinfo;
+	u32 nr_frags, tsize = 0;
+	bool pfmemalloc = false;
+
+	xinfo = xdp_get_shared_info_from_buff(xdp);
+	nr_frags = xinfo->nr_frags;
+
+	for (u32 i = 0; i < nr_frags; i++) {
+		u32 len = skb_frag_size(&xinfo->frags[i]);
+		u32 offset, truesize = len;
+		netmem_ref netmem;
+
+		netmem = page_pool_dev_alloc_netmem(pp, &offset, &truesize);
+		if (unlikely(!netmem)) {
+			sinfo->nr_frags = i;
+			return false;
+		}
+
+		memcpy(__netmem_address(netmem),
+		       __netmem_address(xinfo->frags[i].netmem),
+		       LARGEST_ALIGN(len));
+		__skb_fill_netmem_desc_noacc(sinfo, i, netmem, offset, len);
+
+		tsize += truesize;
+		pfmemalloc |= netmem_is_pfmemalloc(netmem);
+	}
+
+	xdp_update_skb_shared_info(skb, nr_frags, xinfo->xdp_frags_size,
+				   tsize, pfmemalloc);
+
+	return true;
+}
+
+/**
+ * xdp_build_skb_from_zc - create an skb from XSk &xdp_buff
+ * @xdp: source XSk buff
+ *
+ * Similar to xdp_build_skb_from_buff(), but for XSk frames. Allocate an skb
+ * head, new buffer for the head, copy the data and initialize the skb fields.
+ * If there are frags, allocate new buffers for them and copy.
+ * Buffers are allocated from the system percpu pools to try recycling them.
+ * If new skb was built successfully, @xdp is returned to XSk pool's freelist.
+ * On error, it remains untouched and the caller must take care of this.
+ *
+ * Return: new &sk_buff on success, %NULL on error.
+ */
+struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
+{
+	struct page_pool *pp = this_cpu_read(system_page_pool);
+	const struct xdp_rxq_info *rxq = xdp->rxq;
+	u32 len = xdp->data_end - xdp->data_meta;
+	u32 truesize = xdp->frame_sz;
+	struct sk_buff *skb;
+	int metalen;
+	void *data;
+
+	if (!IS_ENABLED(CONFIG_PAGE_POOL))
+		return NULL;
+
+	data = page_pool_dev_alloc_va(pp, &truesize);
+	if (unlikely(!data))
+		return NULL;
+
+	skb = napi_build_skb(data, truesize);
+	if (unlikely(!skb)) {
+		page_pool_free_va(pp, data, true);
+		return NULL;
+	}
+
+	skb_mark_for_recycle(skb);
+	skb_reserve(skb, xdp->data_meta - xdp->data_hard_start);
+
+	memcpy(__skb_put(skb, len), xdp->data_meta, LARGEST_ALIGN(len));
+
+	metalen = xdp->data - xdp->data_meta;
+	if (metalen > 0) {
+		skb_metadata_set(skb, metalen);
+		__skb_pull(skb, metalen);
+	}
+
+	skb_record_rx_queue(skb, rxq->queue_index);
+
+	if (unlikely(xdp_buff_has_frags(xdp)) &&
+	    unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) {
+		napi_consume_skb(skb, true);
+		return NULL;
+	}
+
+	xsk_buff_free(xdp);
+
+	skb->protocol = eth_type_trans(skb, rxq->dev);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(xdp_build_skb_from_zc);
+
 struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev)