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

Alexander Lobakin says:

====================
xdp: a fistful of generic changes pt. II (part)

XDP for idpf is currently 5.5 chapters:
* convert Rx to libeth;
* convert Tx and stats to libeth;
* generic XDP and XSk code changes;
* generic XDP and XSk code additions (you are here);
* actual XDP for idpf via new libeth_xdp;
* XSk for idpf (via ^).

Part III.2.1 does the following:
* allows mixing pages from several Page Pools within one XDP frame;
* optimizes &xdp_frame structure and removes no-more-used field;

Everything is prereq for libeth_xdp, but will be useful standalone
as well: faster xdp_return_frame_bulk() and xdp_frame fields access.
====================

Link: https://patch.msgid.link/20241211172649.761483-1-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 48 insertions, 21 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 69624b394cd9..b2509cd0b930 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3674,7 +3674,7 @@ static inline void skb_frag_page_copy(skb_frag_t *fragto,
 bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio);
 
 /**
- * skb_frag_dma_map - maps a paged fragment via the DMA API
+ * __skb_frag_dma_map - maps a paged fragment via the DMA API
  * @dev: the device to map the fragment to
  * @frag: the paged fragment to map
  * @offset: the offset within the fragment (starting at the
@@ -3684,15 +3684,36 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio);
  *
  * Maps the page associated with @frag to @device.
  */
-static inline dma_addr_t skb_frag_dma_map(struct device *dev,
-					  const skb_frag_t *frag,
-					  size_t offset, size_t size,
-					  enum dma_data_direction dir)
+static inline dma_addr_t __skb_frag_dma_map(struct device *dev,
+					    const skb_frag_t *frag,
+					    size_t offset, size_t size,
+					    enum dma_data_direction dir)
 {
 	return dma_map_page(dev, skb_frag_page(frag),
 			    skb_frag_off(frag) + offset, size, dir);
 }
 
+#define skb_frag_dma_map(dev, frag, ...)				\
+	CONCATENATE(_skb_frag_dma_map,					\
+		    COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__)
+
+#define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({		\
+	const skb_frag_t *uf = (frag);					\
+	size_t uo = (offset);						\
+									\
+	__skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo,		\
+			   DMA_TO_DEVICE);				\
+})
+#define _skb_frag_dma_map1(dev, frag, offset)				\
+	__skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_),	\
+			    __UNIQUE_ID(offset_))
+#define _skb_frag_dma_map0(dev, frag)					\
+	_skb_frag_dma_map1(dev, frag, 0)
+#define _skb_frag_dma_map2(dev, frag, offset, size)			\
+	__skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE)
+#define _skb_frag_dma_map3(dev, frag, offset, size, dir)		\
+	__skb_frag_dma_map(dev, frag, offset, size, dir)
+
 static inline struct sk_buff *pskb_copy(struct sk_buff *skb,
 					gfp_t gfp_mask)
 {
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 1ea16b0e9c79..05a864031271 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -259,8 +259,7 @@ void page_pool_disable_direct_recycling(struct page_pool *pool);
 void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
 			   const struct xdp_mem_info *mem);
-void page_pool_put_netmem_bulk(struct page_pool *pool, netmem_ref *data,
-			       u32 count);
+void page_pool_put_netmem_bulk(netmem_ref *data, u32 count);
 #else
 static inline void page_pool_destroy(struct page_pool *pool)
 {
@@ -272,8 +271,7 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 {
 }
 
-static inline void page_pool_put_netmem_bulk(struct page_pool *pool,
-					     netmem_ref *data, u32 count)
+static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count)
 {
 }
 #endif
diff --git a/include/net/xdp.h b/include/net/xdp.h
index f4020b29122f..d2089cfecefd 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -11,6 +11,8 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h> /* skb_shared_info */
 
+#include <net/page_pool/types.h>
+
 /**
  * DOC: XDP RX-queue information
  *
@@ -167,13 +169,13 @@ out:
 
 struct xdp_frame {
 	void *data;
-	u16 len;
-	u16 headroom;
+	u32 len;
+	u32 headroom;
 	u32 metasize; /* uses lower 8-bits */
 	/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
-	 * while mem info is valid on remote CPU.
+	 * while mem_type is valid on remote CPU.
 	 */
-	struct xdp_mem_info mem;
+	enum xdp_mem_type mem_type:32;
 	struct net_device *dev_rx; /* used by cpumap */
 	u32 frame_sz;
 	u32 flags; /* supported values defined in xdp_buff_flags */
@@ -193,14 +195,12 @@ xdp_frame_is_frag_pfmemalloc(const struct xdp_frame *frame)
 #define XDP_BULK_QUEUE_SIZE	16
 struct xdp_frame_bulk {
 	int count;
-	void *xa;
 	netmem_ref q[XDP_BULK_QUEUE_SIZE];
 };
 
 static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq)
 {
-	/* bq->count will be zero'ed when bq->xa gets updated */
-	bq->xa = NULL;
+	bq->count = 0;
 }
 
 static inline struct skb_shared_info *
@@ -306,21 +306,29 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
 	if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0))
 		return NULL;
 
-	/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
-	xdp_frame->mem = xdp->rxq->mem;
+	/* rxq only valid until napi_schedule ends, convert to xdp_mem_type */
+	xdp_frame->mem_type = xdp->rxq->mem.type;
 
 	return xdp_frame;
 }
 
-void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
-		  struct xdp_buff *xdp);
+void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type,
+		  bool napi_direct, struct xdp_buff *xdp);
 void xdp_return_frame(struct xdp_frame *xdpf);
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
 void xdp_return_buff(struct xdp_buff *xdp);
-void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
 void xdp_return_frame_bulk(struct xdp_frame *xdpf,
 			   struct xdp_frame_bulk *bq);
 
+static inline void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+	if (unlikely(!bq->count))
+		return;
+
+	page_pool_put_netmem_bulk(bq->q, bq->count);
+	bq->count = 0;
+}
+
 static __always_inline unsigned int
 xdp_get_frame_len(const struct xdp_frame *xdpf)
 {