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. */<