Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf before 7.0-rc2

Cross-merge BPF and other fixes after downstream PR.

No conflicts.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

22 files changed, 79 insertions, 74 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b78b53198a2e..05b34a6355b0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -124,7 +124,7 @@ struct bpf_map_ops {
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
-	int (*map_check_btf)(const struct bpf_map *map,
+	int (*map_check_btf)(struct bpf_map *map,
 			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
@@ -656,7 +656,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 		map->ops->map_seq_show_elem;
 }
 
-int map_check_no_btf(const struct bpf_map *map,
+int map_check_no_btf(struct bpf_map *map,
 		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type);
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 85efa9772530..8157e8da61d4 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -176,7 +176,7 @@ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage);
 void bpf_local_storage_map_free(struct bpf_map *map,
 				struct bpf_local_storage_cache *cache);
 
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+int bpf_local_storage_map_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type);
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index e45162ef59bb..4ce0d27f8ea2 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -14,6 +14,8 @@ struct bpf_mem_alloc {
 	struct obj_cgroup *objcg;
 	bool percpu;
 	struct work_struct work;
+	void (*dtor_ctx_free)(void *ctx);
+	void *dtor_ctx;
 };
 
 /* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects.
@@ -32,6 +34,10 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
 /* The percpu allocation with a specific unit size. */
 int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
+void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma,
+			    void (*dtor)(void *obj, void *ctx),
+			    void (*dtor_ctx_free)(void *ctx),
+			    void *ctx);
 
 /* Check the allocation size for kmalloc equivalent allocator */
 int bpf_mem_alloc_check_size(bool percpu, size_t size);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 28a9cb13fbfa..079c18bcdbde 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -495,19 +495,6 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 		fsnotify_dentry(dentry, mask);
 }
 
-static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
-				    int error)
-{
-	struct fs_error_report report = {
-		.error = error,
-		.inode = inode,
-		.sb = sb,
-	};
-
-	return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR,
-			NULL, NULL, NULL, 0);
-}
-
 static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt)
 {
 	fsnotify_mnt(FS_MNT_ATTACH, ns, mnt);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2b30a0529d48..51ef13ed756e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -14,8 +14,8 @@ struct vm_area_struct;
 struct mempolicy;
 
 /* Helper macro to avoid gfp flags if they are the default one */
-#define __default_gfp(a,...) a
-#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL)
+#define __default_gfp(a,b,...) b
+#define default_gfp(...) __default_gfp(,##__VA_ARGS__,GFP_KERNEL)
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -339,8 +339,11 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde
 {
 	return folio_alloc_noprof(gfp, order);
 }
-#define vma_alloc_folio_noprof(gfp, order, vma, addr)		\
-	folio_alloc_noprof(gfp, order)
+static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order,
+		struct vm_area_struct *vma, unsigned long addr)
+{
+	return folio_alloc_noprof(gfp, order);
+}
 #endif
 
 #define alloc_pages(...)			alloc_hooks(alloc_pages_noprof(__VA_ARGS__))
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 814bb2892f99..6c75df30a281 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
index fe82a6c3005f..dd11fdc76a5f 100644
--- a/include/linux/liveupdate.h
+++ b/include/linux/liveupdate.h
@@ -23,8 +23,11 @@ struct file;
 /**
  * struct liveupdate_file_op_args - Arguments for file operation callbacks.
  * @handler:          The file handler being called.
- * @retrieved:        The retrieve status for the 'can_finish / finish'
- *                    operation.
+ * @retrieve_status:  The retrieve status for the 'can_finish / finish'
+ *                    operation. A value of 0 means the retrieve has not been
+ *                    attempted, a positive value means the retrieve was
+ *                    successful, and a negative value means the retrieve failed,
+ *                    and the value is the error code of the call.
  * @file:             The file object. For retrieve: [OUT] The callback sets
  *                    this to the new file. For other ops: [IN] The caller sets
  *                    this to the file being operated on.
@@ -40,7 +43,7 @@ struct file;
  */
 struct liveupdate_file_op_args {
 	struct liveupdate_file_handler *handler;
-	bool retrieved;
+	int retrieve_status;
 	struct file *file;
 	u64 serialized_data;
 	void *private_data;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index e0e2c265e5d1..ba84f02c2a10 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -486,14 +486,12 @@ struct mmc_host {
 
 	struct mmc_ios		ios;		/* current io bus settings */
 
+	bool			claimed;	/* host exclusively claimed */
+
 	/* group bitfields together to minimize padding */
 	unsigned int		use_spi_crc:1;
-	unsigned int		claimed:1;	/* host exclusively claimed */
 	unsigned int		doing_init_tune:1; /* initial tuning in progress */
-	unsigned int		can_retune:1;	/* re-tuning can be used */
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
-	unsigned int		retune_now:1;	/* do re-tuning at next req */
-	unsigned int		retune_paused:1; /* re-tuning is temporarily disabled */
 	unsigned int		retune_crc_disable:1; /* don't trigger retune upon crc */
 	unsigned int		can_dma_map_merge:1; /* merging can be used */
 	unsigned int		vqmmc_enabled:1; /* vqmmc regulator is enabled */
@@ -508,6 +506,9 @@ struct mmc_host {
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
 
+	bool			can_retune;	/* re-tuning can be used */
+	bool			retune_now;	/* do re-tuning at next req */
+	bool			retune_paused;	/* re-tuning is temporarily disabled */
 	int			need_retune;	/* re-tuning is needed */
 	int			hold_retune;	/* hold off re-tuning */
 	unsigned int		retune_period;	/* re-tuning period in secs */
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index eddd987a8513..a8cb6319b4fb 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -42,7 +42,7 @@
  * both the type-agnostic benefits of the macros while also being able to
  * enforce that the return value is, in fact, checked.
  */
-static inline bool __must_check __must_check_overflow(bool overflow)
+static __always_inline bool __must_check __must_check_overflow(bool overflow)
 {
 	return unlikely(overflow);
 }
@@ -327,7 +327,7 @@ static inline bool __must_check __must_check_overflow(bool overflow)
  * with any overflow causing the return value to be SIZE_MAX. The
  * lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
+static __always_inline size_t __must_check size_mul(size_t factor1, size_t factor2)
 {
 	size_t bytes;
 
@@ -346,7 +346,7 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
  * with any overflow causing the return value to be SIZE_MAX. The
  * lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_add(size_t addend1, size_t addend2)
+static __always_inline size_t __must_check size_add(size_t addend1, size_t addend2)
 {
 	size_t bytes;
 
@@ -367,7 +367,7 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2)
  * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX).
  * The lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
+static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
 {
 	size_t bytes;
 
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 41037c513f06..64921b10ac74 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -545,22 +545,10 @@ static inline int pm_runtime_resume_and_get(struct device *dev)
  *
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, queue up a work item for @dev like in pm_request_idle().
- *
- * Return:
- * * 1: Success. Usage counter dropped to zero, but device was already suspended.
- * * 0: Success.
- * * -EINVAL: Runtime PM error.
- * * -EACCES: Runtime PM disabled.
- * * -EAGAIN: Runtime PM usage counter became non-zero or Runtime PM status
- *            change ongoing.
- * * -EBUSY: Runtime PM child_count non-zero.
- * * -EPERM: Device PM QoS resume latency 0.
- * * -EINPROGRESS: Suspend already in progress.
- * * -ENOSYS: CONFIG_PM not enabled.
  */
-static inline int pm_runtime_put(struct device *dev)
+static inline void pm_runtime_put(struct device *dev)
 {
-	return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
+	__pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
 /**
diff --git a/include/linux/slab.h b/include/linux/slab.h
index a5a5e4108ae5..15a60b501b95 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp);
 DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T))
 DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T))
 
-/**
- * ksize - Report actual allocation size of associated object
- *
- * @objp: Pointer returned from a prior kmalloc()-family allocation.
- *
- * This should not be used for writing beyond the originally requested
- * allocation size. Either use krealloc() or round up the allocation size
- * with kmalloc_size_roundup() prior to allocation. If this is used to
- * access beyond the originally requested allocation size, UBSAN_BOUNDS
- * and/or FORTIFY_SOURCE may trip, since they only know about the
- * originally allocated size via the __alloc_size attribute.
- */
 size_t ksize(const void *objp);
 
 #ifdef CONFIG_PRINTK
diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index fa4654ffb621..ca2cfec8de08 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -131,4 +131,7 @@ static inline bool tnum_subreg_is_const(struct tnum a)
 	return !(tnum_subreg(a)).mask;
 }
 
+/* Returns the smallest member of t larger than z */
+u64 tnum_step(struct tnum t, u64 z);
+
 #endif /* _LINUX_TNUM_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d3ff48a2fbe0..533d8e75f7bb 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -276,10 +276,19 @@ static inline bool vsock_net_mode_global(struct vsock_sock *vsk)
 	return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL;
 }
 
-static inline void vsock_net_set_child_mode(struct net *net,
+static inline bool vsock_net_set_child_mode(struct net *net,
 					    enum vsock_net_mode mode)
 {
-	WRITE_ONCE(net->vsock.child_ns_mode, mode);
+	int new_locked = mode + 1;
+	int old_locked = 0; /* unlocked */
+
+	if (try_cmpxchg(&net->vsock.child_ns_mode_locked,
+			&old_locked, new_locked)) {
+		WRITE_ONCE(net->vsock.child_ns_mode, mode);
+		return true;
+	}
+
+	return old_locked == new_locked;
 }
 
 static inline enum vsock_net_mode vsock_net_child_mode(struct net *net)
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index ec3af01e4db9..010f1a8fd15f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -284,9 +284,9 @@ struct l2cap_conn_rsp {
 #define L2CAP_CR_LE_BAD_KEY_SIZE	0x0007
 #define L2CAP_CR_LE_ENCRYPTION		0x0008
 #define L2CAP_CR_LE_INVALID_SCID	0x0009
-#define L2CAP_CR_LE_SCID_IN_USE		0X000A
-#define L2CAP_CR_LE_UNACCEPT_PARAMS	0X000B
-#define L2CAP_CR_LE_INVALID_PARAMS	0X000C
+#define L2CAP_CR_LE_SCID_IN_USE		0x000A
+#define L2CAP_CR_LE_UNACCEPT_PARAMS	0x000B
+#define L2CAP_CR_LE_INVALID_PARAMS	0x000C
 
 /* connect/create channel status */
 #define L2CAP_CS_NO_INFO	0x0000
@@ -493,6 +493,8 @@ struct l2cap_ecred_reconf_req {
 #define L2CAP_RECONF_SUCCESS		0x0000
 #define L2CAP_RECONF_INVALID_MTU	0x0001
 #define L2CAP_RECONF_INVALID_MPS	0x0002
+#define L2CAP_RECONF_INVALID_CID	0x0003
+#define L2CAP_RECONF_INVALID_PARAMS	0x0004
 
 struct l2cap_ecred_reconf_rsp {
 	__le16 result;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index ecb362025c4e..5cb3056d6ddc 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -42,7 +42,9 @@ struct inet_connection_sock_af_ops {
 				      struct request_sock *req,
 				      struct dst_entry *dst,
 				      struct request_sock *req_unhash,
-				      bool *own_req);
+				      bool *own_req,
+				      void (*opt_child_init)(struct sock *newsk,
+							     const struct sock *sk));
 	u16	    net_header_len;
 	int	    (*setsockopt)(struct sock *sk, int level, int optname,
 				  sockptr_t optval, unsigned int optlen);
diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
index b34d69a22fa8..dc8cbe45f406 100644
--- a/include/net/netns/vsock.h
+++ b/include/net/netns/vsock.h
@@ -17,5 +17,8 @@ struct netns_vsock {
 
 	enum vsock_net_mode mode;
 	enum vsock_net_mode child_ns_mode;
+
+	/* 0 = unlocked, 1 = locked to global, 2 = locked to local */
+	int child_ns_mode_locked;
 };
 #endif /* __NET_NET_NAMESPACE_VSOCK_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 66b56288c1d3..6c9a83016e95 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2098,7 +2098,7 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk->sk_socket = sock;
+	WRITE_ONCE(sk->sk_socket, sock);
 	if (sock) {
 		WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
 		WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 40e72b9cb85f..eb8bf63fdafc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -544,7 +544,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req);
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk));
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
 int tcp_connect(struct sock *sk);
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 6de6fd8bd15e..d639ff889e64 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -181,7 +181,7 @@ void rdma_destroy_id(struct rdma_cm_id *id);
  *
  * It needs to be called before the RDMA identifier is bound
  * to an device, which mean it should be called before
- * rdma_bind_addr(), rdma_bind_addr() and rdma_listen().
+ * rdma_bind_addr(), rdma_resolve_addr() and rdma_listen().
  */
 int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type);
 
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 7f93e754da5c..cd7920c81f85 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -440,7 +440,13 @@ TRACE_EVENT(rss_stat,
 
 	TP_fast_assign(
 		__entry->mm_id = mm_ptr_to_hash(mm);
-		__entry->curr = !!(current->mm == mm);
+		/*
+		 * curr is true if the mm matches the current task's mm_struct.
+		 * Since kthreads (PF_KTHREAD) have no mm_struct of their own
+		 * but can borrow one via kthread_use_mm(), we must filter them
+		 * out to avoid incorrectly attributing the RSS update to them.
+		 */
+		__entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD);
 		__entry->member = member;
 		__entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member])
 							    << PAGE_SHIFT);
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index e527b24bd824..c89aede3cb12 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -401,8 +401,8 @@ extern "C" {
  * implementation can multiply the values by 2^6=64. For that reason the padding
  * must only contain zeros.
  * index 0 = Y plane, [15:0] z:Y [6:10] little endian
- * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian
- * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [6:10] little endian
  */
 #define DRM_FORMAT_S010	fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
 #define DRM_FORMAT_S210	fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
@@ -414,8 +414,8 @@ extern "C" {
  * implementation can multiply the values by 2^4=16. For that reason the padding
  * must only contain zeros.
  * index 0 = Y plane, [15:0] z:Y [4:12] little endian
- * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian
- * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [4:12] little endian
  */
 #define DRM_FORMAT_S012	fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
 #define DRM_FORMAT_S212	fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
@@ -424,8 +424,8 @@ extern "C" {
 /*
  * 3 plane YCbCr
  * index 0 = Y plane, [15:0] Y little endian
- * index 1 = Cr plane, [15:0] Cr little endian
- * index 2 = Cb plane, [15:0] Cb little endian
+ * index 1 = Cb plane, [15:0] Cb little endian
+ * index 2 = Cr plane, [15:0] Cr little endian
  */
 #define DRM_FORMAT_S016	fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
 #define DRM_FORMAT_S216	fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index ec1c54b5a310..14f634ab9350 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -712,7 +712,7 @@
 #define  PCI_EXP_LNKCTL2_HASD		0x0020 /* HW Autonomous Speed Disable */
 #define PCI_EXP_LNKSTA2		0x32	/* Link Status 2 */
 #define  PCI_EXP_LNKSTA2_FLIT		0x0400 /* Flit Mode Status */
-#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x32	/* end of v2 EPs w/ link */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x34	/* end of v2 EPs w/ link */
 #define PCI_EXP_SLTCAP2		0x34	/* Slot Capabilities 2 */
 #define  PCI_EXP_SLTCAP2_IBPD	0x00000001 /* In-band PD Disable Supported */
 #define PCI_EXP_SLTCTL2		0x38	/* Slot Control 2 */