Merge 'bpf-next 2023-10-16' into loongarch-next

LoongArch architecture changes for 6.7 (BPF CPU v4 support) depend on
the bpf changes to fix conflictions in selftests and work, so merge them
to create a base.

22 files changed, 578 insertions, 130 deletions

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index d0807ad43f93..dd71d3009771 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -240,6 +240,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES		BIT(6)
 /* used to negotiate communicating link speeds in Mbps */
 #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED		BIT(7)
+#define  VIRTCHNL_VF_OFFLOAD_CRC		BIT(10)
 #define VIRTCHNL_VF_OFFLOAD_VLAN_V2		BIT(15)
 #define VIRTCHNL_VF_OFFLOAD_VLAN		BIT(16)
 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING		BIT(17)
@@ -295,7 +296,13 @@ VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info);
 /* VIRTCHNL_OP_CONFIG_RX_QUEUE
  * VF sends this message to set up parameters for one RX queue.
  * External data buffer contains one instance of virtchnl_rxq_info.
- * PF configures requested queue and returns a status code.
+ * PF configures requested queue and returns a status code. The
+ * crc_disable flag disables CRC stripping on the VF. Setting
+ * the crc_disable flag to 1 will disable CRC stripping for each
+ * queue in the VF where the flag is set. The VIRTCHNL_VF_OFFLOAD_CRC
+ * offload must have been set prior to sending this info or the PF
+ * will ignore the request. This flag should be set the same for
+ * all of the queues for a VF.
  */
 
 /* Rx queue config info */
@@ -307,7 +314,7 @@ struct virtchnl_rxq_info {
 	u16 splithdr_enabled; /* deprecated with AVF 1.0 */
 	u32 databuffer_size;
 	u32 max_pkt_size;
-	u8 pad0;
+	u8 crc_disable;
 	u8 rxdid;
 	u8 pad1[2];
 	u64 dma_ring_addr;
diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
index 7b121bd780eb..0985221d5478 100644
--- a/include/linux/bpf-cgroup-defs.h
+++ b/include/linux/bpf-cgroup-defs.h
@@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type {
 	CGROUP_INET6_BIND,
 	CGROUP_INET4_CONNECT,
 	CGROUP_INET6_CONNECT,
+	CGROUP_UNIX_CONNECT,
 	CGROUP_INET4_POST_BIND,
 	CGROUP_INET6_POST_BIND,
 	CGROUP_UDP4_SENDMSG,
 	CGROUP_UDP6_SENDMSG,
+	CGROUP_UNIX_SENDMSG,
 	CGROUP_SYSCTL,
 	CGROUP_UDP4_RECVMSG,
 	CGROUP_UDP6_RECVMSG,
+	CGROUP_UNIX_RECVMSG,
 	CGROUP_GETSOCKOPT,
 	CGROUP_SETSOCKOPT,
 	CGROUP_INET4_GETPEERNAME,
 	CGROUP_INET6_GETPEERNAME,
+	CGROUP_UNIX_GETPEERNAME,
 	CGROUP_INET4_GETSOCKNAME,
 	CGROUP_INET6_GETSOCKNAME,
+	CGROUP_UNIX_GETSOCKNAME,
 	CGROUP_INET_SOCK_RELEASE,
 	CGROUP_LSM_START,
 	CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1,
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 8506690dbb9c..98b8cea904fe 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type)
 	CGROUP_ATYPE(CGROUP_INET6_BIND);
 	CGROUP_ATYPE(CGROUP_INET4_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET6_CONNECT);
+	CGROUP_ATYPE(CGROUP_UNIX_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET4_POST_BIND);
 	CGROUP_ATYPE(CGROUP_INET6_POST_BIND);
 	CGROUP_ATYPE(CGROUP_UDP4_SENDMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_SENDMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_SENDMSG);
 	CGROUP_ATYPE(CGROUP_SYSCTL);
 	CGROUP_ATYPE(CGROUP_UDP4_RECVMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_RECVMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_RECVMSG);
 	CGROUP_ATYPE(CGROUP_GETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_SETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE);
 	default:
 		return CGROUP_BPF_ATTACH_TYPE_INVALID;
@@ -120,6 +125,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 
 int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 				      struct sockaddr *uaddr,
+				      int *uaddrlen,
 				      enum cgroup_bpf_attach_type atype,
 				      void *t_ctx,
 				      u32 *flags);
@@ -230,22 +236,22 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk)				       \
 	BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND)
 
-#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype)				       \
+#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype)		       \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))					       \
-		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  NULL, NULL);	       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \
+							  atype, NULL, NULL);  \
 	__ret;								       \
 })
 
-#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx)		       \
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx)	       \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))	{				       \
 		lock_sock(sk);						       \
-		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  t_ctx, NULL);	       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \
+							  atype, t_ctx, NULL); \
 		release_sock(sk);					       \
 	}								       \
 	__ret;								       \
@@ -256,14 +262,14 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
  * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check
  * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE).
  */
-#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags)	       \
+#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \
 ({									       \
 	u32 __flags = 0;						       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))	{				       \
 		lock_sock(sk);						       \
-		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  NULL, &__flags);     \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \
+							  atype, NULL, &__flags); \
 		release_sock(sk);					       \
 		if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE)	       \
 			*bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE;	       \
@@ -276,29 +282,38 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 	  cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) &&		       \
 	 (sk)->sk_prot->pre_connect)
 
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT)
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen)			\
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT)
 
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT)
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen)			\
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT)
 
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL)
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL)
 
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL)
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL)
 
-#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx)
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL)
 
-#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx)
+#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx)
 
-#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr)			\
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL)
+#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx)
 
-#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr)			\
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL)
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx)
+
+#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL)
+
+#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL)
+
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL)
 
 /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
  * fullsock and its parent fullsock cannot be traced by
@@ -477,24 +492,27 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 }
 
 #define cgroup_bpf_enabled(atype) (0)
-#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; })
-#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; })
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; })
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 49f8b691496c..d3c51a507508 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -55,8 +55,8 @@ struct cgroup;
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
-extern struct bpf_mem_alloc bpf_global_ma;
-extern bool bpf_global_ma_set;
+extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
+extern bool bpf_global_ma_set, bpf_global_percpu_ma_set;
 
 typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
@@ -180,14 +180,15 @@ enum btf_field_type {
 	BPF_TIMER      = (1 << 1),
 	BPF_KPTR_UNREF = (1 << 2),
 	BPF_KPTR_REF   = (1 << 3),
-	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF,
-	BPF_LIST_HEAD  = (1 << 4),
-	BPF_LIST_NODE  = (1 << 5),
-	BPF_RB_ROOT    = (1 << 6),
-	BPF_RB_NODE    = (1 << 7),
+	BPF_KPTR_PERCPU = (1 << 4),
+	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU,
+	BPF_LIST_HEAD  = (1 << 5),
+	BPF_LIST_NODE  = (1 << 6),
+	BPF_RB_ROOT    = (1 << 7),
+	BPF_RB_NODE    = (1 << 8),
 	BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD |
 				 BPF_RB_NODE | BPF_RB_ROOT,
-	BPF_REFCOUNT   = (1 << 8),
+	BPF_REFCOUNT   = (1 << 9),
 };
 
 typedef void (*btf_dtor_kfunc_t)(void *);
@@ -300,6 +301,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return "kptr";
+	case BPF_KPTR_PERCPU:
+		return "percpu_kptr";
 	case BPF_LIST_HEAD:
 		return "bpf_list_head";
 	case BPF_LIST_NODE:
@@ -325,6 +328,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 		return sizeof(struct bpf_timer);
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
 		return sizeof(u64);
 	case BPF_LIST_HEAD:
 		return sizeof(struct bpf_list_head);
@@ -351,6 +355,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 		return __alignof__(struct bpf_timer);
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
 		return __alignof__(u64);
 	case BPF_LIST_HEAD:
 		return __alignof__(struct bpf_list_head);
@@ -389,6 +394,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
 	case BPF_TIMER:
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1029,6 +1035,11 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_SHARE_IPMODIFY	BIT(6)
 
+/* Indicate that current trampoline is in a tail call context. Then, it has to
+ * cache and restore tail_call_cnt to avoid infinite tail call loop.
+ */
+#define BPF_TRAMP_F_TAIL_CALL_CTX	BIT(7)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */
@@ -1378,6 +1389,7 @@ struct bpf_prog_aux {
 	u32 stack_depth;
 	u32 id;
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
+	u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
 	u32 ctx_arg_info_size;
@@ -1398,6 +1410,8 @@ struct bpf_prog_aux {
 	bool sleepable;
 	bool tail_call_reachable;
 	bool xdp_has_frags;
+	bool exception_cb;
+	bool exception_boundary;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
@@ -1420,6 +1434,7 @@ struct bpf_prog_aux {
 	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
+	unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp);
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
@@ -2149,12 +2164,12 @@ static inline bool bpf_allow_uninit_stack(void)
 
 static inline bool bpf_bypass_spec_v1(void)
 {
-	return perfmon_capable();
+	return cpu_mitigations_off() || perfmon_capable();
 }
 
 static inline bool bpf_bypass_spec_v4(void)
 {
-	return perfmon_capable();
+	return cpu_mitigations_off() || perfmon_capable();
 }
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
@@ -2407,9 +2422,11 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg);
+			  struct bpf_reg_state *reg, bool is_ex_cb);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+				    int comp_idx, const char *tag_key);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
 struct bpf_link *bpf_link_by_id(u32 id);
@@ -2905,6 +2922,22 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
+static __always_inline void
+bpf_prog_inc_misses_counters(const struct bpf_prog_array *array)
+{
+	const struct bpf_prog_array_item *item;
+	struct bpf_prog *prog;
+
+	if (unlikely(!array))
+		return;
+
+	item = &array->items[0];
+	while ((prog = READ_ONCE(item->prog))) {
+		bpf_prog_inc_misses_counter(prog);
+		item++;
+	}
+}
+
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
 void bpf_sk_reuseport_detach(struct sock *sk);
 int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
@@ -3183,4 +3216,9 @@ static inline gfp_t bpf_memcg_flags(gfp_t flags)
 	return flags;
 }
 
+static inline bool bpf_is_subprog(const struct bpf_prog *prog)
+{
+	return prog->aux->func_idx != 0;
+}
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b6e58dab8e27..94ec766432f5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -300,6 +300,7 @@ struct bpf_func_state {
 	bool in_callback_fn;
 	struct tnum callback_ret_range;
 	bool in_async_callback_fn;
+	bool in_exception_callback_fn;
 
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
@@ -480,6 +481,7 @@ struct bpf_insn_aux_data {
 	bool zext_dst; /* this insn zero extends dst reg */
 	bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
 	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
+	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
 	u8 alu_state; /* used in combination with alu_limit */
 
 	/* below fields are initialized once */
@@ -540,7 +542,9 @@ struct bpf_subprog_info {
 	bool has_tail_call;
 	bool tail_call_reachable;
 	bool has_ld_abs;
+	bool is_cb;
 	bool is_async_cb;
+	bool is_exception_cb;
 };
 
 struct bpf_verifier_env;
@@ -587,6 +591,8 @@ struct bpf_verifier_env {
 	u32 used_map_cnt;		/* number of used maps */
 	u32 used_btf_cnt;		/* number of used BTF objects */
 	u32 id_gen;			/* used to generate unique reg IDs */
+	u32 hidden_subprog_cnt;		/* number of hidden subprogs */
+	int exception_callback_subprog;
 	bool explore_alu_limits;
 	bool allow_ptr_leaks;
 	bool allow_uninit_stack;
@@ -594,10 +600,11 @@ struct bpf_verifier_env {
 	bool bypass_spec_v1;
 	bool bypass_spec_v4;
 	bool seen_direct_write;
+	bool seen_exception;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
-	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
+	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */
 	union {
 		struct bpf_idmap idmap_scratch;
 		struct bpf_idset idset_scratch;
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index b658961156a0..7a9a40163c0f 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -19,7 +19,7 @@ struct ceph_monmap {
 	struct ceph_fsid fsid;
 	u32 epoch;
 	u32 num_mon;
-	struct ceph_entity_inst mon_inst[];
+	struct ceph_entity_inst mon_inst[] __counted_by(num_mon);
 };
 
 struct ceph_mon_client;
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
new file mode 100644
index 000000000000..bbc480cd2932
--- /dev/null
+++ b/include/linux/dpll.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (c) 2023 Meta Platforms, Inc. and affiliates
+ *  Copyright (c) 2023 Intel and affiliates
+ */
+
+#ifndef __DPLL_H__
+#define __DPLL_H__
+
+#include <uapi/linux/dpll.h>
+#include <linux/device.h>
+#include <linux/netlink.h>
+
+struct dpll_device;
+struct dpll_pin;
+
+struct dpll_device_ops {
+	int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv,
+			enum dpll_mode *mode, struct netlink_ext_ack *extack);
+	bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv,
+			       const enum dpll_mode mode,
+			       struct netlink_ext_ack *extack);
+	int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv,
+			       enum dpll_lock_status *status,
+			       struct netlink_ext_ack *extack);
+	int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv,
+			s32 *temp, struct netlink_ext_ack *extack);
+};
+
+struct dpll_pin_ops {
+	int (*frequency_set)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     const u64 frequency,
+			     struct netlink_ext_ack *extack);
+	int (*frequency_get)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     u64 *frequency, struct netlink_ext_ack *extack);
+	int (*direction_set)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     const enum dpll_pin_direction direction,
+			     struct netlink_ext_ack *extack);
+	int (*direction_get)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     enum dpll_pin_direction *direction,
+			     struct netlink_ext_ack *extack);
+	int (*state_on_pin_get)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_pin *parent_pin,
+				void *parent_pin_priv,
+				enum dpll_pin_state *state,
+				struct netlink_ext_ack *extack);
+	int (*state_on_dpll_get)(const struct dpll_pin *pin, void *pin_priv,
+				 const struct dpll_device *dpll,
+				 void *dpll_priv, enum dpll_pin_state *state,
+				 struct netlink_ext_ack *extack);
+	int (*state_on_pin_set)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_pin *parent_pin,
+				void *parent_pin_priv,
+				const enum dpll_pin_state state,
+				struct netlink_ext_ack *extack);
+	int (*state_on_dpll_set)(const struct dpll_pin *pin, void *pin_priv,
+				 const struct dpll_device *dpll,
+				 void *dpll_priv,
+				 const enum dpll_pin_state state,
+				 struct netlink_ext_ack *extack);
+	int (*prio_get)(const struct dpll_pin *pin,  void *pin_priv,
+			const struct dpll_device *dpll,  void *dpll_priv,
+			u32 *prio, struct netlink_ext_ack *extack);
+	int (*prio_set)(const struct dpll_pin *pin, void *pin_priv,
+			const struct dpll_device *dpll, void *dpll_priv,
+			const u32 prio, struct netlink_ext_ack *extack);
+};
+
+struct dpll_pin_frequency {
+	u64 min;
+	u64 max;
+};
+
+#define DPLL_PIN_FREQUENCY_RANGE(_min, _max)	\
+	{					\
+		.min = _min,			\
+		.max = _max,			\
+	}
+
+#define DPLL_PIN_FREQUENCY(_val) DPLL_PIN_FREQUENCY_RANGE(_val, _val)
+#define DPLL_PIN_FREQUENCY_1PPS \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_1_HZ)
+#define DPLL_PIN_FREQUENCY_10MHZ \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_MHZ)
+#define DPLL_PIN_FREQUENCY_IRIG_B \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_KHZ)
+#define DPLL_PIN_FREQUENCY_DCF77 \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_77_5_KHZ)
+
+struct dpll_pin_properties {
+	const char *board_label;
+	const char *panel_label;
+	const char *package_label;
+	enum dpll_pin_type type;
+	unsigned long capabilities;
+	u32 freq_supported_num;
+	struct dpll_pin_frequency *freq_supported;
+};
+
+#if IS_ENABLED(CONFIG_DPLL)
+size_t dpll_msg_pin_handle_size(struct dpll_pin *pin);
+int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin);
+#else
+static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin)
+{
+	return 0;
+}
+
+static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
+{
+	return 0;
+}
+#endif
+
+struct dpll_device *
+dpll_device_get(u64 clock_id, u32 dev_driver_id, struct module *module);
+
+void dpll_device_put(struct dpll_device *dpll);
+
+int dpll_device_register(struct dpll_device *dpll, enum dpll_type type,
+			 const struct dpll_device_ops *ops, void *priv);
+
+void dpll_device_unregister(struct dpll_device *dpll,
+			    const struct dpll_device_ops *ops, void *priv);
+
+struct dpll_pin *
+dpll_pin_get(u64 clock_id, u32 dev_driver_id, struct module *module,
+	     const struct dpll_pin_properties *prop);
+
+int dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
+		      const struct dpll_pin_ops *ops, void *priv);
+
+void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin,
+			 const struct dpll_pin_ops *ops, void *priv);
+
+void dpll_pin_put(struct dpll_pin *pin);
+
+int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
+			     const struct dpll_pin_ops *ops, void *priv);
+
+void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin,
+				const struct dpll_pin_ops *ops, void *priv);
+
+int dpll_device_change_ntf(struct dpll_device *dpll);
+
+int dpll_pin_change_ntf(struct dpll_pin *pin);
+
+#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 761af6b3cf2b..bcd2bc15ff56 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -117,21 +117,25 @@ struct ctl_table_header;
 
 /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
 
-#define BPF_ALU64_IMM(OP, DST, IMM)				\
+#define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
 		.dst_reg = DST,					\
 		.src_reg = 0,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = IMM })
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	BPF_ALU64_IMM_OFF(OP, DST, IMM, 0)
 
-#define BPF_ALU32_IMM(OP, DST, IMM)				\
+#define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
 		.dst_reg = DST,					\
 		.src_reg = 0,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = IMM })
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	BPF_ALU32_IMM_OFF(OP, DST, IMM, 0)
 
 /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
 
@@ -143,6 +147,16 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = LEN })
 
+/* Byte Swap, bswap16/32/64 */
+
+#define BPF_BSWAP(DST, LEN)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE),	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = LEN })
+
 /* Short form of mov, dst_reg = src_reg */
 
 #define BPF_MOV64_REG(DST, SRC)					\
@@ -179,6 +193,24 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = IMM })
 
+/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */
+
+#define BPF_MOVSX64_REG(DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+#define BPF_MOVSX32_REG(DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Special form of mov32, used for doing explicit zero extension on dst. */
 #define BPF_ZEXT_REG(DST)					\
 	((struct bpf_insn) {					\
@@ -263,6 +295,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Memory load, dst_reg = *(signed size *) (src_reg + off16) */
+
+#define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = src_reg */
 
 #define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
@@ -694,7 +736,7 @@ static inline void bpf_compute_and_save_data_end(
 	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
-/* Restore data saved by bpf_compute_data_pointers(). */
+/* Restore data saved by bpf_compute_and_save_data_end(). */
 static inline void bpf_restore_data_end(
 	struct sk_buff *skb, void *saved_data_end)
 {
@@ -912,6 +954,8 @@ bool bpf_jit_needs_zext(void);
 bool bpf_jit_supports_subprog_tailcalls(void);
 bool bpf_jit_supports_kfunc_call(void);
 bool bpf_jit_supports_far_kfunc_call(void);
+bool bpf_jit_supports_exceptions(void);
+void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
 bool bpf_helper_changes_pkt_data(void *func);
 
 static inline bool bpf_dump_raw_ok(const struct cred *cred)
@@ -1127,6 +1171,7 @@ const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
 bool is_bpf_text_address(unsigned long addr);
 int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		    char *sym);
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr);
 
 static inline const char *
 bpf_address_lookup(unsigned long addr, unsigned long *size,
@@ -1194,6 +1239,11 @@ static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value,
 	return -ERANGE;
 }
 
+static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+{
+	return NULL;
+}
+
 static inline const char *
 bpf_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym)
@@ -1285,6 +1335,7 @@ struct bpf_sock_addr_kern {
 	 */
 	u64 tmp_reg;
 	void *t_ctx;	/* Attach type specific context. */
+	u32 uaddrlen;
 };
 
 struct bpf_sock_ops_kern {
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index af8a771a053c..e400ff757f13 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -213,28 +213,9 @@ struct ipv6_pinfo {
 	__be32			flow_label;
 	__u32			frag_size;
 
-	/*
-	 * Packed in 16bits.
-	 * Omit one shift by putting the signed field at MSB.
-	 */
-#if defined(__BIG_ENDIAN_BITFIELD)
-	__s16			hop_limit:9;
-	__u16			__unused_1:7;
-#else
-	__u16			__unused_1:7;
-	__s16			hop_limit:9;
-#endif
+	s16			hop_limit;
+	u8			mcast_hops;
 
-#if defined(__BIG_ENDIAN_BITFIELD)
-	/* Packed in 16bits. */
-	__s16			mcast_hops:9;
-	__u16			__unused_2:6,
-				mc_loop:1;
-#else
-	__u16			mc_loop:1,
-				__unused_2:6;
-	__s16			mcast_hops:9;
-#endif
 	int			ucast_oif;
 	int			mcast_oif;
 
@@ -262,21 +243,11 @@ struct ipv6_pinfo {
 	} rxopt;
 
 	/* sockopt flags */
-	__u16			recverr:1,
-	                        sndflow:1,
-				repflow:1,
-				pmtudisc:3,
-				padding:1,	/* 1 bit hole */
-				srcprefs:3,	/* 001: prefer temporary address
+	__u8			srcprefs;	/* 001: prefer temporary address
 						 * 010: prefer public address
 						 * 100: prefer care-of address
 						 */
-				dontfrag:1,
-				autoflowlabel:1,
-				autoflowlabel_set:1,
-				mc_all:1,
-				recverr_rfc4884:1,
-				rtalert_isolate:1;
+	__u8			pmtudisc;
 	__u8			min_hopcount;
 	__u8			tclass;
 	__be32			rcv_flowinfo;
@@ -293,6 +264,18 @@ struct ipv6_pinfo {
 	struct inet6_cork	cork;
 };
 
+/* We currently use available bits from inet_sk(sk)->inet_flags,
+ * this could change in the future.
+ */
+#define inet6_test_bit(nr, sk)			\
+	test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet6_set_bit(nr, sk)			\
+	set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet6_clear_bit(nr, sk)			\
+	clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet6_assign_bit(nr, sk, val)		\
+	assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
+
 /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */
 struct raw6_sock {
 	/* inet_sock has to be the first member of raw6_sock */
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 71fa9a40fb5a..72cb693b075b 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -285,8 +285,10 @@ static inline bool kasan_check_byte(const void *address)
 
 #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
 void kasan_unpoison_task_stack(struct task_struct *task);
+asmlinkage void kasan_unpoison_task_stack_below(const void *watermark);
 #else
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+static inline void kasan_unpoison_task_stack_below(const void *watermark) {}
 #endif
 
 #ifdef CONFIG_KASAN_GENERIC
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 4d5be378fa8c..8fbe22de16ef 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -366,6 +366,7 @@ enum mlx5_driver_event {
 	MLX5_DRIVER_EVENT_UPLINK_NETDEV,
 	MLX5_DRIVER_EVENT_MACSEC_SA_ADDED,
 	MLX5_DRIVER_EVENT_MACSEC_SA_DELETED,
+	MLX5_DRIVER_EVENT_SF_PEER_DEVLINK,
 };
 
 enum {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 3033bbaeac81..92434814c855 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -155,6 +155,8 @@ enum {
 	MLX5_REG_MCC		 = 0x9062,
 	MLX5_REG_MCDA		 = 0x9063,
 	MLX5_REG_MCAM		 = 0x907f,
+	MLX5_REG_MSECQ		 = 0x9155,
+	MLX5_REG_MSEES		 = 0x9156,
 	MLX5_REG_MIRC		 = 0x9162,
 	MLX5_REG_SBCAM		 = 0xB01F,
 	MLX5_REG_RESOURCE_DUMP   = 0xC000,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index fc3db401f8a2..dd8421d021cf 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10176,7 +10176,9 @@ struct mlx5_ifc_mcam_access_reg_bits2 {
 	u8         mirc[0x1];
 	u8         regs_97_to_96[0x2];
 
-	u8         regs_95_to_64[0x20];
+	u8         regs_95_to_87[0x09];
+	u8         synce_registers[0x2];
+	u8         regs_84_to_64[0x15];
 
 	u8         regs_63_to_32[0x20];
 
@@ -12549,4 +12551,59 @@ struct mlx5_ifc_modify_page_track_obj_in_bits {
 	struct mlx5_ifc_page_track_bits obj_context;
 };
 
+struct mlx5_ifc_msecq_reg_bits {
+	u8         reserved_at_0[0x20];
+
+	u8         reserved_at_20[0x12];
+	u8         network_option[0x2];
+	u8         local_ssm_code[0x4];
+	u8         local_enhanced_ssm_code[0x8];
+
+	u8         local_clock_identity[0x40];
+
+	u8         reserved_at_80[0x180];
+};
+
+enum {
+	MLX5_MSEES_FIELD_SELECT_ENABLE			= BIT(0),
+	MLX5_MSEES_FIELD_SELECT_ADMIN_STATUS		= BIT(1),
+	MLX5_MSEES_FIELD_SELECT_ADMIN_FREQ_MEASURE	= BIT(2),
+};
+
+enum mlx5_msees_admin_status {
+	MLX5_MSEES_ADMIN_STATUS_FREE_RUNNING		= 0x0,
+	MLX5_MSEES_ADMIN_STATUS_TRACK			= 0x1,
+};
+
+enum mlx5_msees_oper_status {
+	MLX5_MSEES_OPER_STATUS_FREE_RUNNING		= 0x0,
+	MLX5_MSEES_OPER_STATUS_SELF_TRACK		= 0x1,
+	MLX5_MSEES_OPER_STATUS_OTHER_TRACK		= 0x2,
+	MLX5_MSEES_OPER_STATUS_HOLDOVER			= 0x3,
+	MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER		= 0x4,
+	MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING	= 0x5,
+};
+
+struct mlx5_ifc_msees_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         local_port[0x8];
+	u8         pnat[0x2];
+	u8         lp_msb[0x2];
+	u8         reserved_at_14[0xc];
+
+	u8         field_select[0x20];
+
+	u8         admin_status[0x4];
+	u8         oper_status[0x4];
+	u8         ho_acq[0x1];
+	u8         reserved_at_49[0xc];
+	u8         admin_freq_measure[0x1];
+	u8         oper_freq_measure[0x1];
+	u8         failure_reason[0x9];
+
+	u8         frequency_diff[0x20];
+
+	u8         reserved_at_80[0x180];
+};
+
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0896aaa91dd7..7e520c14eb8c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -79,6 +79,8 @@ struct xdp_buff;
 struct xdp_frame;
 struct xdp_metadata_ops;
 struct xdp_md;
+/* DPLL specific */
+struct dpll_pin;
 
 typedef u32 xdp_features_t;
 
@@ -917,6 +919,7 @@ struct net_device_path {
 			u8 queue;
 			u16 wcid;
 			u8 bss;
+			u8 amsdu;
 		} mtk_wdma;
 	};
 };
@@ -2049,6 +2052,9 @@ enum netdev_ml_priv_type {
  *			SET_NETDEV_DEVLINK_PORT macro. This pointer is static
  *			during the time netdevice is registered.
  *
+ *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
+ *		   where the clock is recovered.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -2405,6 +2411,10 @@ struct net_device {
 	struct rtnl_hw_stats64	*offload_xstats_l3;
 
 	struct devlink_port	*devlink_port;
+
+#if IS_ENABLED(CONFIG_DPLL)
+	struct dpll_pin		*dpll_pin;
+#endif
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -3940,6 +3950,18 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
 int dev_get_port_parent_id(struct net_device *dev,
 			   struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
+void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
+void netdev_dpll_pin_clear(struct net_device *dev);
+
+static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_DPLL)
+	return dev->dpll_pin;
+#else
+	return NULL;
+#endif
+}
+
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
diff --git a/include/linux/pds/pds_core_if.h b/include/linux/pds/pds_core_if.h
index e838a2b90440..17a87c1a55d7 100644
--- a/include/linux/pds/pds_core_if.h
+++ b/include/linux/pds/pds_core_if.h
@@ -79,6 +79,7 @@ enum pds_core_status_code {
 	PDS_RC_EVFID	= 31,	/* VF ID does not exist */
 	PDS_RC_BAD_FW	= 32,	/* FW file is invalid or corrupted */
 	PDS_RC_ECLIENT	= 33,   /* No such client id */
+	PDS_RC_BAD_PCI	= 255,  /* Broken PCI when reading status */
 };
 
 /**
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 1351b802ffcf..3cc52826f18e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1736,6 +1736,7 @@ void phy_detach(struct phy_device *phydev);
 void phy_start(struct phy_device *phydev);
 void phy_stop(struct phy_device *phydev);
 int phy_config_aneg(struct phy_device *phydev);
+int _phy_start_aneg(struct phy_device *phydev);
 int phy_start_aneg(struct phy_device *phydev);
 int phy_aneg_done(struct phy_device *phydev);
 int phy_speed_down(struct phy_device *phydev, bool sync);
diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h
index b2b28180dff7..a476648858a6 100644
--- a/include/linux/soc/mediatek/mtk_wed.h
+++ b/include/linux/soc/mediatek/mtk_wed.h
@@ -10,6 +10,7 @@
 
 #define MTK_WED_TX_QUEUES		2
 #define MTK_WED_RX_QUEUES		2
+#define MTK_WED_RX_PAGE_QUEUES		3
 
 #define WED_WO_STA_REC			0x6
 
@@ -45,7 +46,7 @@ enum mtk_wed_wo_cmd {
 	MTK_WED_WO_CMD_WED_END
 };
 
-struct mtk_rxbm_desc {
+struct mtk_wed_bm_desc {
 	__le32 buf0;
 	__le32 token;
 } __packed __aligned(4);
@@ -76,6 +77,11 @@ struct mtk_wed_wo_rx_stats {
 	__le32 rx_drop_cnt;
 };
 
+struct mtk_wed_buf {
+	void *p;
+	dma_addr_t phy_addr;
+};
+
 struct mtk_wed_device {
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
 	const struct mtk_wed_ops *ops;
@@ -94,17 +100,20 @@ struct mtk_wed_device {
 	struct mtk_wed_ring txfree_ring;
 	struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES];
 	struct mtk_wed_ring rx_wdma[MTK_WED_RX_QUEUES];
+	struct mtk_wed_ring rx_rro_ring[MTK_WED_RX_QUEUES];
+	struct mtk_wed_ring rx_page_ring[MTK_WED_RX_PAGE_QUEUES];
+	struct mtk_wed_ring ind_cmd_ring;
 
 	struct {
 		int size;
-		void **pages;
+		struct mtk_wed_buf *pages;
 		struct mtk_wdma_desc *desc;
 		dma_addr_t desc_phys;
 	} tx_buf_ring;
 
 	struct {
 		int size;
-		struct mtk_rxbm_desc *desc;
+		struct mtk_wed_bm_desc *desc;
 		dma_addr_t desc_phys;
 	} rx_buf_ring;
 
@@ -114,6 +123,13 @@ struct mtk_wed_device {
 		dma_addr_t fdbk_phys;
 	} rro;
 
+	struct {
+		int size;
+		struct mtk_wed_buf *pages;
+		struct mtk_wed_bm_desc *desc;
+		dma_addr_t desc_phys;
+	} hw_rro;
+
 	/* filled by driver: */
 	struct {
 		union {
@@ -123,6 +139,7 @@ struct mtk_wed_device {
 		enum mtk_wed_bus_tye bus_type;
 		void __iomem *base;
 		u32 phy_base;
+		u32 id;
 
 		u32 wpdma_phys;
 		u32 wpdma_int;
@@ -131,18 +148,35 @@ struct mtk_wed_device {
 		u32 wpdma_txfree;
 		u32 wpdma_rx_glo;
 		u32 wpdma_rx;
+		u32 wpdma_rx_rro[MTK_WED_RX_QUEUES];
+		u32 wpdma_rx_pg;
 
 		bool wcid_512;
+		bool hw_rro;
+		bool msi;
 
 		u16 token_start;
 		unsigned int nbuf;
 		unsigned int rx_nbuf;
 		unsigned int rx_npkt;
 		unsigned int rx_size;
+		unsigned int amsdu_max_len;
 
 		u8 tx_tbit[MTK_WED_TX_QUEUES];
 		u8 rx_tbit[MTK_WED_RX_QUEUES];
+		u8 rro_rx_tbit[MTK_WED_RX_QUEUES];
+		u8 rx_pg_tbit[MTK_WED_RX_PAGE_QUEUES];
 		u8 txfree_tbit;
+		u8 amsdu_max_subframes;
+
+		struct {
+			u8 se_group_nums;
+			u16 win_size;
+			u16 particular_sid;
+			u32 ack_sn_addr;
+			dma_addr_t particular_se_phys;
+			dma_addr_t addr_elem_phys[1024];
+		} ind_cmd;
 
 		u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id);
 		int (*offload_enable)(struct mtk_wed_device *wed);
@@ -182,6 +216,14 @@ struct mtk_wed_ops {
 	void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask);
 	int (*setup_tc)(struct mtk_wed_device *wed, struct net_device *dev,
 			enum tc_setup_type type, void *type_data);
+	void (*start_hw_rro)(struct mtk_wed_device *dev, u32 irq_mask,
+			     bool reset);
+	void (*rro_rx_ring_setup)(struct mtk_wed_device *dev, int ring,
+				  void __iomem *regs);
+	void (*msdu_pg_rx_ring_setup)(struct mtk_wed_device *dev, int ring,
+				      void __iomem *regs);
+	int (*ind_rx_ring_setup)(struct mtk_wed_device *dev,
+				 void __iomem *regs);
 };
 
 extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops;
@@ -206,16 +248,27 @@ mtk_wed_device_attach(struct mtk_wed_device *dev)
 	return ret;
 }
 
-static inline bool
-mtk_wed_get_rx_capa(struct mtk_wed_device *dev)
+static inline bool mtk_wed_get_rx_capa(struct mtk_wed_device *dev)
 {
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	if (dev->version == 3)
+		return dev->wlan.hw_rro;
+
 	return dev->version != 1;
 #else
 	return false;
 #endif
 }
 
+static inline bool mtk_wed_is_amsdu_supported(struct mtk_wed_device *dev)
+{
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	return dev->version == 3;
+#else
+	return false;
+#endif
+}
+
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
 #define mtk_wed_device_active(_dev) !!(_dev)->ops
 #define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev)
@@ -242,6 +295,15 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev)
 #define mtk_wed_device_dma_reset(_dev) (_dev)->ops->reset_dma(_dev)
 #define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) \
 	(_dev)->ops->setup_tc(_dev, _netdev, _type, _type_data)
+#define mtk_wed_device_start_hw_rro(_dev, _mask, _reset) \
+	(_dev)->ops->start_hw_rro(_dev, _mask, _reset)
+#define mtk_wed_device_rro_rx_ring_setup(_dev, _ring, _regs) \
+	(_dev)->ops->rro_rx_ring_setup(_dev, _ring, _regs)
+#define mtk_wed_device_msdu_pg_rx_ring_setup(_dev, _ring, _regs) \
+	(_dev)->ops->msdu_pg_rx_ring_setup(_dev, _ring, _regs)
+#define mtk_wed_device_ind_rx_ring_setup(_dev, _regs) \
+	(_dev)->ops->ind_rx_ring_setup(_dev, _regs)
+
 #else
 static inline bool mtk_wed_device_active(struct mtk_wed_device *dev)
 {
@@ -261,6 +323,10 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev)
 #define mtk_wed_device_stop(_dev) do {} while (0)
 #define mtk_wed_device_dma_reset(_dev) do {} while (0)
 #define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) -EOPNOTSUPP
+#define mtk_wed_device_start_hw_rro(_dev, _mask, _reset) do {} while (0)
+#define mtk_wed_device_rro_rx_ring_setup(_dev, _ring, _regs) -ENODEV
+#define mtk_wed_device_msdu_pg_rx_ring_setup(_dev, _ring, _regs) -ENODEV
+#define mtk_wed_device_ind_rx_ring_setup(_dev, _regs) -ENODEV
 #endif
 
 #endif
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index ce89cc3e4913..c0079a7574ae 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -139,6 +139,7 @@ struct stmmac_rxq_cfg {
 
 struct stmmac_txq_cfg {
 	u32 weight;
+	bool coe_unsupported;
 	u8 mode_to_use;
 	/* Credit Base Shaper parameters */
 	u32 send_slope;
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 3c5efeeb024f..e15452df9804 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -377,6 +377,14 @@ struct tcp_sock {
 				 * Total data bytes retransmitted
 				 */
 	u32	total_retrans;	/* Total retransmits for entire connection */
+	u32	rto_stamp;	/* Start time (ms) of last CA_Loss recovery */
+	u16	total_rto;	/* Total number of RTO timeouts, including
+				 * SYN/SYN-ACK and recurring timeouts.
+				 */
+	u16	total_rto_recoveries;	/* Total number of RTO recoveries,
+					 * including any unfinished recovery.
+					 */
+	u32	total_rto_time;	/* ms spent in (completed) RTO recoveries. */
 
 	u32	urg_seq;	/* Seq of received urgent pointer */
 	unsigned int		keepalive_time;	  /* time before keep alive takes place */
@@ -463,15 +471,17 @@ enum tsq_enum {
 	TCP_MTU_REDUCED_DEFERRED,  /* tcp_v{4|6}_err() could not call
 				    * tcp_v{4|6}_mtu_reduced()
 				    */
+	TCP_ACK_DEFERRED,	   /* TX pure ack is deferred */
 };
 
 enum tsq_flags {
-	TSQF_THROTTLED			= (1UL << TSQ_THROTTLED),
-	TSQF_QUEUED			= (1UL << TSQ_QUEUED),
-	TCPF_TSQ_DEFERRED		= (1UL << TCP_TSQ_DEFERRED),
-	TCPF_WRITE_TIMER_DEFERRED	= (1UL << TCP_WRITE_TIMER_DEFERRED),
-	TCPF_DELACK_TIMER_DEFERRED	= (1UL << TCP_DELACK_TIMER_DEFERRED),
-	TCPF_MTU_REDUCED_DEFERRED	= (1UL << TCP_MTU_REDUCED_DEFERRED),
+	TSQF_THROTTLED			= BIT(TSQ_THROTTLED),
+	TSQF_QUEUED			= BIT(TSQ_QUEUED),
+	TCPF_TSQ_DEFERRED		= BIT(TCP_TSQ_DEFERRED),
+	TCPF_WRITE_TIMER_DEFERRED	= BIT(TCP_WRITE_TIMER_DEFERRED),
+	TCPF_DELACK_TIMER_DEFERRED	= BIT(TCP_DELACK_TIMER_DEFERRED),
+	TCPF_MTU_REDUCED_DEFERRED	= BIT(TCP_MTU_REDUCED_DEFERRED),
+	TCPF_ACK_DEFERRED		= BIT(TCP_ACK_DEFERRED),
 };
 
 #define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 21ae37e49319..5eb88a66eb68 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -761,7 +761,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name);
 void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp);
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
-			    u64 *probe_offset, u64 *probe_addr);
+			    u64 *probe_offset, u64 *probe_addr,
+			    unsigned long *missed);
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 #else
@@ -801,7 +802,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
 static inline int bpf_get_perf_event_info(const struct perf_event *event,
 					  u32 *prog_id, u32 *fd_type,
 					  const char **buf, u64 *probe_offset,
-					  u64 *probe_addr)
+					  u64 *probe_addr, unsigned long *missed)
 {
 	return -EOPNOTSUPP;
 }
@@ -877,6 +878,7 @@ extern void perf_kprobe_destroy(struct perf_event *event);
 extern int bpf_get_kprobe_info(const struct perf_event *event,
 			       u32 *fd_type, const char **symbol,
 			       u64 *probe_offset, u64 *probe_addr,
+			       unsigned long *missed,
 			       bool perf_type_tracepoint);
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 43c1fb2d2c21..d04188714dca 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -32,25 +32,30 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask)
 	return (num + net_hash_mix(net)) & mask;
 }
 
+enum {
+	UDP_FLAGS_CORK,		/* Cork is required */
+	UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */
+	UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */
+	UDP_FLAGS_GRO_ENABLED,	/* Request GRO aggregation */
+	UDP_FLAGS_ACCEPT_FRAGLIST,
+	UDP_FLAGS_ACCEPT_L4,
+	UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */
+	UDP_FLAGS_UDPLITE_SEND_CC, /* set via udplite setsockopt */
+	UDP_FLAGS_UDPLITE_RECV_CC, /* set via udplite setsockopt */
+};
+
 struct udp_sock {
 	/* inet_sock has to be the first member */
 	struct inet_sock inet;
 #define udp_port_hash		inet.sk.__sk_common.skc_u16hashes[0]
 #define udp_portaddr_hash	inet.sk.__sk_common.skc_u16hashes[1]
 #define udp_portaddr_node	inet.sk.__sk_common.skc_portaddr_node
+
+	unsigned long	 udp_flags;
+
 	int		 pending;	/* Any pending frames ? */
-	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
-	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
-			 encap_enabled:1, /* This socket enabled encap
-					   * processing; UDP tunnels and
-					   * different encapsulation layer set
-					   * this
-					   */
-			 gro_enabled:1,	/* Request GRO aggregation */
-			 accept_udp_l4:1,
-			 accept_udp_fraglist:1;
+
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
@@ -62,12 +67,6 @@ struct udp_sock {
 	 */
 	__u16		 pcslen;
 	__u16		 pcrlen;
-/* indicator bits used by pcflag: */
-#define UDPLITE_BIT      0x1  		/* set by udplite proto init function */
-#define UDPLITE_SEND_CC  0x2  		/* set via udplite setsockopt         */
-#define UDPLITE_RECV_CC  0x4		/* set via udplite setsocktopt        */
-	__u8		 pcflag;        /* marks socket as UDP-Lite if > 0    */
-	__u8		 unused[3];
 	/*
 	 * For encapsulation sockets.
 	 */
@@ -95,28 +94,39 @@ struct udp_sock {
 	int		forward_threshold;
 };
 
+#define udp_test_bit(nr, sk)			\
+	test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags)
+#define udp_set_bit(nr, sk)			\
+	set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags)
+#define udp_test_and_set_bit(nr, sk)		\
+	test_and_set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags)
+#define udp_clear_bit(nr, sk)			\
+	clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags)
+#define udp_assign_bit(nr, sk, val)		\
+	assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val)
+
 #define UDP_MAX_SEGMENTS	(1 << 6UL)
 
 #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk)
 
 static inline void udp_set_no_check6_tx(struct sock *sk, bool val)
 {
-	udp_sk(sk)->no_check6_tx = val;
+	udp_assign_bit(NO_CHECK6_TX, sk, val);
 }
 
 static inline void udp_set_no_check6_rx(struct sock *sk, bool val)
 {
-	udp_sk(sk)->no_check6_rx = val;
+	udp_assign_bit(NO_CHECK6_RX, sk, val);
 }
 
-static inline bool udp_get_no_check6_tx(struct sock *sk)
+static inline bool udp_get_no_check6_tx(const struct sock *sk)
 {
-	return udp_sk(sk)->no_check6_tx;
+	return udp_test_bit(NO_CHECK6_TX, sk);
 }
 
-static inline bool udp_get_no_check6_rx(struct sock *sk)
+static inline bool udp_get_no_check6_rx(const struct sock *sk)
 {
-	return udp_sk(sk)->no_check6_rx;
+	return udp_test_bit(NO_CHECK6_RX, sk);
 }
 
 static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
@@ -135,10 +145,12 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
 	if (!skb_is_gso(skb))
 		return false;
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4)
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
+	    !udp_test_bit(ACCEPT_L4, sk))
 		return true;
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist)
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST &&
+	    !udp_test_bit(ACCEPT_FRAGLIST, sk))
 		return true;
 
 	return false;
@@ -146,8 +158,8 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
 
 static inline void udp_allow_gso(struct sock *sk)
 {
-	udp_sk(sk)->accept_udp_l4 = 1;
-	udp_sk(sk)->accept_udp_fraglist = 1;
+	udp_set_bit(ACCEPT_L4, sk);
+	udp_set_bit(ACCEPT_FRAGLIST, sk);
 }
 
 #define udp_portaddr_for_each_entry(__sk, list) \
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index c58453699ee9..ebb3ce63d64d 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -12,6 +12,7 @@
 struct virtio_vsock_skb_cb {
 	bool reply;
 	bool tap_delivered;
+	u32 offset;
 };
 
 #define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb))
@@ -159,6 +160,15 @@ struct virtio_transport {
 
 	/* Takes ownership of the packet */
 	int (*send_pkt)(struct sk_buff *skb);
+
+	/* Used in MSG_ZEROCOPY mode. Checks, that provided data
+	 * (number of buffers) could be transmitted with zerocopy
+	 * mode. If this callback is not implemented for the current
+	 * transport - this means that this transport doesn't need
+	 * extra checks and can perform zerocopy transmission by
+	 * default.
+	 */
+	bool (*can_msgzerocopy)(int bufs_num);
 };
 
 ssize_t