Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-09-01

The following pull-request contains BPF updates for your *net-next* tree.

There are two small conflicts when pulling, resolve as follows:

1) Merge conflict in tools/lib/bpf/libbpf.c between 88a82120282b ("libbpf: Factor
   out common ELF operations and improve logging") in bpf-next and 1e891e513e16
   ("libbpf: Fix map index used in error message") in net-next. Resolve by taking
   the hunk in bpf-next:

        [...]
        scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx);
        data = elf_sec_data(obj, scn);
        if (!scn || !data) {
                pr_warn("elf: failed to get %s map definitions for %s\n",
                        MAPS_ELF_SEC, obj->path);
                return -EINVAL;
        }
        [...]

2) Merge conflict in drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c between
   9647c57b11e5 ("xsk: i40e: ice: ixgbe: mlx5: Test for dma_need_sync earlier for
   better performance") in bpf-next and e20f0dbf204f ("net/mlx5e: RX, Add a prefetch
   command for small L1_CACHE_BYTES") in net-next. Resolve the two locations by retaining
   net_prefetch() and taking xsk_buff_dma_sync_for_cpu() from bpf-next. Should look like:

        [...]
        xdp_set_data_meta_invalid(xdp);
        xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
        net_prefetch(xdp->data);
        [...]

We've added 133 non-merge commits during the last 14 day(s) which contain
a total of 246 files changed, 13832 insertions(+), 3105 deletions(-).

The main changes are:

1) Initial support for sleepable BPF programs along with bpf_copy_from_user() helper
   for tracing to reliably access user memory, from Alexei Starovoitov.

2) Add BPF infra for writing and parsing TCP header options, from Martin KaFai Lau.

3) bpf_d_path() helper for returning full path for given 'struct path', from Jiri Olsa.

4) AF_XDP support for shared umems between devices and queues, from Magnus Karlsson.

5) Initial prep work for full BPF-to-BPF call support in libbpf, from Andrii Nakryiko.

6) Generalize bpf_sk_storage map & add local storage for inodes, from KP Singh.

7) Implement sockmap/hash updates from BPF context, from Lorenz Bauer.

8) BPF xor verification for scalar types & add BPF link iterator, from Yonghong Song.

9) Use target's prog type for BPF_PROG_TYPE_EXT prog verification, from Udip Pant.

10) Rework BPF tracing samples to use libbpf loader, from Daniel T. Lee.

11) Fix xdpsock sample to really cycle through all buffers, from Weqaar Janjua.

12) Improve type safety for tun/veth XDP frame handling, from Maciej Żenczykowski.

13) Various smaller cleanups and improvements all over the place.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 203 insertions, 90 deletions

diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 5036c94c0503..119f4c9c3a9c 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -3,13 +3,27 @@
 #ifndef _BPF_SK_STORAGE_H
 #define _BPF_SK_STORAGE_H
 
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_local_storage.h>
+
 struct sock;
 
 void bpf_sk_storage_free(struct sock *sk);
 
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+extern const struct bpf_func_proto sk_storage_get_btf_proto;
+extern const struct bpf_func_proto sk_storage_delete_btf_proto;
 
+struct bpf_local_storage_elem;
 struct bpf_sk_storage_diag;
 struct sk_buff;
 struct nlattr;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index aa8893c68c50..c738abeb3265 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -86,6 +86,8 @@ struct inet_connection_sock {
  	struct timer_list	  icsk_retransmit_timer;
  	struct timer_list	  icsk_delack_timer;
 	__u32			  icsk_rto;
+	__u32                     icsk_rto_min;
+	__u32                     icsk_delack_max;
 	__u32			  icsk_pmtu_cookie;
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index b2eb8b4ba697..29e41ff3ec93 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -41,6 +41,13 @@ struct request_sock_ops {
 
 int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
 
+struct saved_syn {
+	u32 mac_hdrlen;
+	u32 network_hdrlen;
+	u32 tcp_hdrlen;
+	u8 data[];
+};
+
 /* struct request_sock - mini sock to represent a connection request
  */
 struct request_sock {
@@ -60,7 +67,7 @@ struct request_sock {
 	struct timer_list		rsk_timer;
 	const struct request_sock_ops	*rsk_ops;
 	struct sock			*sk;
-	u32				*saved_syn;
+	struct saved_syn		*saved_syn;
 	u32				secid;
 	u32				peer_secid;
 };
diff --git a/include/net/sock.h b/include/net/sock.h
index b943731fa879..7dd3051551fb 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -246,7 +246,7 @@ struct sock_common {
 	/* public: */
 };
 
-struct bpf_sk_storage;
+struct bpf_local_storage;
 
 /**
   *	struct sock - network layer representation of sockets
@@ -517,7 +517,7 @@ struct sock {
 	void                    (*sk_destruct)(struct sock *sk);
 	struct sock_reuseport __rcu	*sk_reuseport_cb;
 #ifdef CONFIG_BPF_SYSCALL
-	struct bpf_sk_storage __rcu	*sk_bpf_storage;
+	struct bpf_local_storage __rcu	*sk_bpf_storage;
 #endif
 	struct rcu_head		sk_rcu;
 };
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0d11db6436c8..e85d564446c6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -394,7 +394,7 @@ void tcp_metrics_init(void);
 bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
-void tcp_init_transfer(struct sock *sk, int bpf_op);
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
 __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
@@ -455,7 +455,8 @@ enum tcp_synack_type {
 struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct tcp_fastopen_cookie *foc,
-				enum tcp_synack_type synack_type);
+				enum tcp_synack_type synack_type,
+				struct sk_buff *syn_skb);
 int tcp_disconnect(struct sock *sk, int flags);
 
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -699,7 +700,7 @@ static inline void tcp_fast_path_check(struct sock *sk)
 static inline u32 tcp_rto_min(struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
-	u32 rto_min = TCP_RTO_MIN;
+	u32 rto_min = inet_csk(sk)->icsk_rto_min;
 
 	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
 		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
@@ -2025,7 +2026,8 @@ struct tcp_request_sock_ops {
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
-			   enum tcp_synack_type synack_type);
+			   enum tcp_synack_type synack_type,
+			   struct sk_buff *syn_skb);
 };
 
 extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
@@ -2223,6 +2225,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 		      struct msghdr *msg, int len, int flags);
 #endif /* CONFIG_NET_SOCK_MSG */
 
+#ifdef CONFIG_CGROUP_BPF
+/* Copy the listen sk's HDR_OPT_CB flags to its child.
+ *
+ * During 3-Way-HandShake, the synack is usually sent from
+ * the listen sk with the HDR_OPT_CB flags set so that
+ * bpf-prog will be called to write the BPF hdr option.
+ *
+ * In fastopen, the child sk is used to send synack instead
+ * of the listen sk.  Thus, inheriting the HDR_OPT_CB flags
+ * from the listen sk gives the bpf-prog a chance to write
+ * BPF hdr option in the synack pkt during fastopen.
+ *
+ * Both fastopen and non-fastopen child will inherit the
+ * HDR_OPT_CB flags to keep the bpf-prog having a consistent
+ * behavior when deciding to clear this cb flags (or not)
+ * during the PASSIVE_ESTABLISHED_CB.
+ *
+ * In the future, other cb flags could be inherited here also.
+ */
+static inline void bpf_skops_init_child(const struct sock *sk,
+					struct sock *child)
+{
+	tcp_sk(child)->bpf_sock_ops_cb_flags =
+		tcp_sk(sk)->bpf_sock_ops_cb_flags &
+		(BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG |
+		 BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
+		 BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
+}
+
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+				      struct sk_buff *skb,
+				      unsigned int end_offset)
+{
+	skops->skb = skb;
+	skops->skb_data_end = skb->data + end_offset;
+}
+#else
+static inline void bpf_skops_init_child(const struct sock *sk,
+					struct sock *child)
+{
+}
+
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+				      struct sk_buff *skb,
+				      unsigned int end_offset)
+{
+}
+#endif
+
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF
  * program does not support the chosen operation or there is no BPF
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index c9d87cc40c11..1a9559c0cbdd 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -18,25 +18,19 @@ struct xsk_queue;
 struct xdp_buff;
 
 struct xdp_umem {
-	struct xsk_queue *fq;
-	struct xsk_queue *cq;
-	struct xsk_buff_pool *pool;
+	void *addrs;
 	u64 size;
 	u32 headroom;
 	u32 chunk_size;
+	u32 chunks;
+	u32 npgs;
 	struct user_struct *user;
 	refcount_t users;
-	struct work_struct work;
-	struct page **pgs;
-	u32 npgs;
-	u16 queue_id;
-	u8 need_wakeup;
 	u8 flags;
-	int id;
-	struct net_device *dev;
 	bool zc;
-	spinlock_t xsk_tx_list_lock;
-	struct list_head xsk_tx_list;
+	struct page **pgs;
+	int id;
+	struct list_head xsk_dma_list;
 };
 
 struct xsk_map {
@@ -48,10 +42,11 @@ struct xsk_map {
 struct xdp_sock {
 	/* struct sock must be the first member of struct xdp_sock */
 	struct sock sk;
-	struct xsk_queue *rx;
+	struct xsk_queue *rx ____cacheline_aligned_in_smp;
 	struct net_device *dev;
 	struct xdp_umem *umem;
 	struct list_head flush_node;
+	struct xsk_buff_pool *pool;
 	u16 queue_id;
 	bool zc;
 	enum {
@@ -59,10 +54,9 @@ struct xdp_sock {
 		XSK_BOUND,
 		XSK_UNBOUND,
 	} state;
-	/* Protects multiple processes in the control path */
-	struct mutex mutex;
+
 	struct xsk_queue *tx ____cacheline_aligned_in_smp;
-	struct list_head list;
+	struct list_head tx_list;
 	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
 	 * in the SKB destructor callback.
 	 */
@@ -77,6 +71,10 @@ struct xdp_sock {
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;
+	/* Protects multiple processes in the control path */
+	struct mutex mutex;
+	struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
+	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
 };
 
 #ifdef CONFIG_XDP_SOCKETS
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index ccf848f7efa4..5b1ee8a9976d 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -11,47 +11,50 @@
 
 #ifdef CONFIG_XDP_SOCKETS
 
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
-void xsk_umem_consume_tx_done(struct xdp_umem *umem);
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
+void xsk_tx_release(struct xsk_buff_pool *pool);
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+					    u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool);
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool);
 
-static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
 {
-	return XDP_PACKET_HEADROOM + umem->headroom;
+	return XDP_PACKET_HEADROOM + pool->headroom;
 }
 
-static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
 {
-	return umem->chunk_size;
+	return pool->chunk_size;
 }
 
-static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 {
-	return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem);
+	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
 }
 
-static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem,
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
-	xp_set_rxq_info(umem->pool, rxq);
+	xp_set_rxq_info(pool, rxq);
 }
 
-static inline void xsk_buff_dma_unmap(struct xdp_umem *umem,
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {
-	xp_dma_unmap(umem->pool, attrs);
+	xp_dma_unmap(pool, attrs);
 }
 
-static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev,
-				   unsigned long attrs)
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+				   struct device *dev, unsigned long attrs)
 {
-	return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs);
+	struct xdp_umem *umem = pool->umem;
+
+	return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs);
 }
 
 static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
@@ -68,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
 	return xp_get_frame_dma(xskb);
 }
 
-static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem)
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 {
-	return xp_alloc(umem->pool);
+	return xp_alloc(pool);
 }
 
-static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count)
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
-	return xp_can_alloc(umem->pool, count);
+	return xp_can_alloc(pool, count);
 }
 
 static inline void xsk_buff_free(struct xdp_buff *xdp)
@@ -85,100 +88,104 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 	xp_free(xskb);
 }
 
-static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr)
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+					      u64 addr)
 {
-	return xp_raw_get_dma(umem->pool, addr);
+	return xp_raw_get_dma(pool, addr);
 }
 
-static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr)
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 {
-	return xp_raw_get_data(umem->pool, addr);
+	return xp_raw_get_data(pool, addr);
 }
 
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
+	if (!pool->dma_need_sync)
+		return;
+
 	xp_dma_sync_for_cpu(xskb);
 }
 
-static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem,
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
 						    dma_addr_t dma,
 						    size_t size)
 {
-	xp_dma_sync_for_device(umem->pool, dma, size);
+	xp_dma_sync_for_device(pool, dma, size);
 }
 
 #else
 
-static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
 {
 }
 
-static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
-				       struct xdp_desc *desc)
+static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
+				    struct xdp_desc *desc)
 {
 	return false;
 }
 
-static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+static inline void xsk_tx_release(struct xsk_buff_pool *pool)
 {
 }
 
-static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
-						     u16 queue_id)
+static inline struct xsk_buff_pool *
+xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id)
 {
 	return NULL;
 }
 
-static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
 {
 	return false;
 }
 
-static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
 {
 	return 0;
 }
 
-static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
 {
 	return 0;
 }
 
-static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 {
 	return 0;
 }
 
-static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem,
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
 }
 
-static inline void xsk_buff_dma_unmap(struct xdp_umem *umem,
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {
 }
 
-static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev,
-				   unsigned long attrs)
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+				   struct device *dev, unsigned long attrs)
 {
 	return 0;
 }
@@ -193,12 +200,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
 	return 0;
 }
 
-static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem)
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 {
 	return NULL;
 }
 
-static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count)
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	return false;
 }
@@ -207,21 +214,22 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
-static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr)
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+					      u64 addr)
 {
 	return 0;
 }
 
-static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr)
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 {
 	return NULL;
 }
 
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem,
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
 						    dma_addr_t dma,
 						    size_t size)
 {
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 6842990e2712..0140d086dc84 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -13,6 +13,8 @@ struct xsk_buff_pool;
 struct xdp_rxq_info;
 struct xsk_queue;
 struct xdp_desc;
+struct xdp_umem;
+struct xdp_sock;
 struct device;
 struct page;
 
@@ -26,34 +28,68 @@ struct xdp_buff_xsk {
 	struct list_head free_list_node;
 };
 
+struct xsk_dma_map {
+	dma_addr_t *dma_pages;
+	struct device *dev;
+	struct net_device *netdev;
+	refcount_t users;
+	struct list_head list; /* Protected by the RTNL_LOCK */
+	u32 dma_pages_cnt;
+	bool dma_need_sync;
+};
+
 struct xsk_buff_pool {
-	struct xsk_queue *fq;
+	/* Members only used in the control path first. */
+	struct device *dev;
+	struct net_device *netdev;
+	struct list_head xsk_tx_list;
+	/* Protects modifications to the xsk_tx_list */
+	spinlock_t xsk_tx_list_lock;
+	refcount_t users;
+	struct xdp_umem *umem;
+	struct work_struct work;
 	struct list_head free_list;
+	u32 heads_cnt;
+	u16 queue_id;
+
+	/* Data path members as close to free_heads at the end as possible. */
+	struct xsk_queue *fq ____cacheline_aligned_in_smp;
+	struct xsk_queue *cq;
+	/* For performance reasons, each buff pool has its own array of dma_pages
+	 * even when they are identical.
+	 */
 	dma_addr_t *dma_pages;
 	struct xdp_buff_xsk *heads;
 	u64 chunk_mask;
 	u64 addrs_cnt;
 	u32 free_list_cnt;
 	u32 dma_pages_cnt;
-	u32 heads_cnt;
 	u32 free_heads_cnt;
 	u32 headroom;
 	u32 chunk_size;
 	u32 frame_len;
+	u8 cached_need_wakeup;
+	bool uses_need_wakeup;
 	bool dma_need_sync;
 	bool unaligned;
 	void *addrs;
-	struct device *dev;
 	struct xdp_buff_xsk *free_heads[];
 };
 
 /* AF_XDP core. */
-struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
-				u32 chunk_size, u32 headroom, u64 size,
-				bool unaligned);
-void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+						struct xdp_umem *umem);
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+		  u16 queue_id, u16 flags);
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+			 struct net_device *dev, u16 queue_id);
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_release(struct xdp_buff_xsk *xskb);
+void xp_get_pool(struct xsk_buff_pool *pool);
+void xp_put_pool(struct xsk_buff_pool *pool);
+void xp_clear_dev(struct xsk_buff_pool *pool);
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
@@ -80,9 +116,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
 void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
 static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
 {
-	if (!xskb->pool->dma_need_sync)
-		return;
-
 	xp_dma_sync_for_cpu_slow(xskb);
 }