Merge tag 'iommu-updates-v6.13' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/iommu/linux into iommufd.git

Merge with Joerg's tree for dependencies on the next patches.

======================================
IOMMU Updates for Linux v6.13:

Including:

	- Core Updates:
	  - Convert call-sites using iommu_domain_alloc() to more specific
	    versions and remove function.
	  - Introduce iommu_paging_domain_alloc_flags().
	  - Extend support for allocating PASID-capable domains to more
	    drivers.
	  - Remove iommu_present().
	  - Some smaller improvements.

	- New IOMMU driver for RISC-V.

	- Intel VT-d Updates:
	  - Add domain_alloc_paging support.
	  - Enable user space IOPFs in non-PASID and non-svm cases.
	  - Small code refactoring and cleanups.
	  - Add domain replacement support for pasid.

	- AMD-Vi Updates:
	  - Adapt to iommu_paging_domain_alloc_flags() interface and alloc V2
	    page-tables by default.
	  - Replace custom domain ID allocator with IDA allocator.
	  - Add ops->release_domain() support.
	  - Other improvements to device attach and domain allocation code
	    paths.

	- ARM-SMMU Updates:
	  - SMMUv2:
	    - Return -EPROBE_DEFER for client devices probing before their SMMU.
	    - Devicetree binding updates for Qualcomm MMU-500 implementations.
	  - SMMUv3:
	    - Minor fixes and cleanup for NVIDIA's virtual command queue driver.
	  - IO-PGTable:
	    - Fix indexing of concatenated PGDs and extend selftest coverage.
	    - Remove unused block-splitting support.

	- S390 IOMMU:
	  - Implement support for blocking domain.

	- Mediatek IOMMU:
	  - Enable 35-bit physical address support for mt8186.

	- OMAP IOMMU driver:
	  - Adapt to recent IOMMU core changes and unbreak driver.
======================================

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

9 files changed, 95 insertions, 36 deletions

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 5d655e109b2c..f66bc85c6411 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -403,6 +403,7 @@ int  bt_sock_register(int proto, const struct net_proto_family *ops);
 void bt_sock_unregister(int proto);
 void bt_sock_link(struct bt_sock_list *l, struct sock *s);
 void bt_sock_unlink(struct bt_sock_list *l, struct sock *s);
+bool bt_sock_linked(struct bt_sock_list *l, struct sock *s);
 struct sock *bt_sock_alloc(struct net *net, struct socket *sock,
 			   struct proto *prot, int proto, gfp_t prio, int kern);
 int  bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 69ec1eb41a09..941dc62f3027 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6130,6 +6130,50 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
 			      struct wiphy_delayed_work *dwork);
 
 /**
+ * wiphy_delayed_work_pending - Find out whether a wiphy delayable
+ * work item is currently pending.
+ *
+ * @wiphy: the wiphy, for debug purposes
+ * @dwork: the delayed work in question
+ *
+ * Return: true if timer is pending, false otherwise
+ *
+ * How wiphy_delayed_work_queue() works is by setting a timer which
+ * when it expires calls wiphy_work_queue() to queue the wiphy work.
+ * Because wiphy_delayed_work_queue() uses mod_timer(), if it is
+ * called twice and the second call happens before the first call
+ * deadline, the work will rescheduled for the second deadline and
+ * won't run before that.
+ *
+ * wiphy_delayed_work_pending() can be used to detect if calling
+ * wiphy_work_delayed_work_queue() would start a new work schedule
+ * or delayed a previous one. As seen below it cannot be used to
+ * detect precisely if the work has finished to execute nor if it
+ * is currently executing.
+ *
+ *      CPU0                                CPU1
+ * wiphy_delayed_work_queue(wk)
+ *  mod_timer(wk->timer)
+ *                                     wiphy_delayed_work_pending(wk) -> true
+ *
+ * [...]
+ * expire_timers(wk->timer)
+ *  detach_timer(wk->timer)
+ *                                     wiphy_delayed_work_pending(wk) -> false
+ *  wk->timer->function()                          |
+ *   wiphy_work_queue(wk)                          | delayed work pending
+ *    list_add_tail()                              | returns false but
+ *    queue_work(cfg80211_wiphy_work)              | wk->func() has not
+ *                                                 | been run yet
+ * [...]                                           |
+ *  cfg80211_wiphy_work()                          |
+ *   wk->func()                                    V
+ *
+ */
+bool wiphy_delayed_work_pending(struct wiphy *wiphy,
+				struct wiphy_delayed_work *dwork);
+
+/**
  * enum ieee80211_ap_reg_power - regulatory power for an Access Point
  *
  * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 9ab49bfeae78..c1d91f1d20f6 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -531,13 +531,12 @@ static inline int genlmsg_multicast(const struct genl_family *family,
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: offset of multicast group in groups array
- * @flags: allocation flags
  *
  * This function must hold the RTNL or rcu_read_lock().
  */
 int genlmsg_multicast_allns(const struct genl_family *family,
 			    struct sk_buff *skb, u32 portid,
-			    unsigned int group, gfp_t flags);
+			    unsigned int group);
 
 /**
  * genlmsg_unicast - unicast a netlink message
diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 02fbc036f34e..813e163ce27c 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -24,25 +24,27 @@
  * struct ieee80211_radiotap_header - base radiotap header
  */
 struct ieee80211_radiotap_header {
-	/**
-	 * @it_version: radiotap version, always 0
-	 */
-	uint8_t it_version;
-
-	/**
-	 * @it_pad: padding (or alignment)
-	 */
-	uint8_t it_pad;
-
-	/**
-	 * @it_len: overall radiotap header length
-	 */
-	__le16 it_len;
-
-	/**
-	 * @it_present: (first) present word
-	 */
-	__le32 it_present;
+	__struct_group(ieee80211_radiotap_header_fixed, hdr, __packed,
+		/**
+		 * @it_version: radiotap version, always 0
+		 */
+		uint8_t it_version;
+
+		/**
+		 * @it_pad: padding (or alignment)
+		 */
+		uint8_t it_pad;
+
+		/**
+		 * @it_len: overall radiotap header length
+		 */
+		__le16 it_len;
+
+		/**
+		 * @it_present: (first) present word
+		 */
+		__le32 it_present;
+	);
 
 	/**
 	 * @it_optional: all remaining presence bitmaps
@@ -50,6 +52,9 @@ struct ieee80211_radiotap_header {
 	__le32 it_optional[];
 } __packed;
 
+static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed),
+	      "struct member likely outside of __struct_group()");
+
 /* version is always 0 */
 #define PKTHDR_RADIOTAP_VERSION	0
 
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6194fbb564c6..6a070478254d 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 	memset(fl4, 0, sizeof(*fl4));
 
 	if (oif) {
-		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif);
 		/* Legacy VRF/l3mdev use case */
 		fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
 	}
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 91ae20cb7648..066a3ea33b12 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1103,6 +1103,7 @@ struct nft_rule_blob {
  *	@name: name of the chain
  *	@udlen: user data length
  *	@udata: user data in the chain
+ *	@rcu_head: rcu head for deferred release
  *	@blob_next: rule blob pointer to the next in the chain
  */
 struct nft_chain {
@@ -1120,6 +1121,7 @@ struct nft_chain {
 	char				*name;
 	u16				udlen;
 	u8				*udata;
+	struct rcu_head			rcu_head;
 
 	/* Only used during control plane commit phase: */
 	struct nft_rule_blob		*blob_next;
@@ -1263,6 +1265,7 @@ static inline void nft_use_inc_restore(u32 *use)
  *	@sets: sets in the table
  *	@objects: stateful objects in the table
  *	@flowtables: flow tables in the table
+ *	@net: netnamespace this table belongs to
  *	@hgenerator: handle generator state
  *	@handle: table handle
  *	@use: number of chain references to this table
@@ -1282,6 +1285,7 @@ struct nft_table {
 	struct list_head		sets;
 	struct list_head		objects;
 	struct list_head		flowtables;
+	possible_net_t			net;
 	u64				hgenerator;
 	u64				handle;
 	u32				use;
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index d489d9250bff..ae60d6664095 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -51,7 +51,6 @@ struct netns_xfrm {
 	struct hlist_head	*policy_byidx;
 	unsigned int		policy_idx_hmask;
 	unsigned int		idx_generator;
-	struct hlist_head	policy_inexact[XFRM_POLICY_MAX];
 	struct xfrm_policy_hash	policy_bydst[XFRM_POLICY_MAX];
 	unsigned int		policy_count[XFRM_POLICY_MAX * 2];
 	struct work_struct	policy_hash_work;
diff --git a/include/net/sock.h b/include/net/sock.h
index db29c39e19a7..f29c14448938 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2717,6 +2717,11 @@ static inline bool sk_is_stream_unix(const struct sock *sk)
 	return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM;
 }
 
+static inline bool sk_is_vsock(const struct sock *sk)
+{
+	return sk->sk_family == AF_VSOCK;
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b6bfdc6416c7..a0bdd58f401c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -349,20 +349,25 @@ struct xfrm_if_cb {
 void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
 void xfrm_if_unregister_cb(void);
 
+struct xfrm_dst_lookup_params {
+	struct net *net;
+	int tos;
+	int oif;
+	xfrm_address_t *saddr;
+	xfrm_address_t *daddr;
+	u32 mark;
+	__u8 ipproto;
+	union flowi_uli uli;
+};
+
 struct net_device;
 struct xfrm_type;
 struct xfrm_dst;
 struct xfrm_policy_afinfo {
 	struct dst_ops		*dst_ops;
-	struct dst_entry	*(*dst_lookup)(struct net *net,
-					       int tos, int oif,
-					       const xfrm_address_t *saddr,
-					       const xfrm_address_t *daddr,
-					       u32 mark);
-	int			(*get_saddr)(struct net *net, int oif,
-					     xfrm_address_t *saddr,
-					     xfrm_address_t *daddr,
-					     u32 mark);
+	struct dst_entry	*(*dst_lookup)(const struct xfrm_dst_lookup_params *params);
+	int			(*get_saddr)(xfrm_address_t *saddr,
+					     const struct xfrm_dst_lookup_params *params);
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
 					    const struct flowi *fl);
@@ -1764,10 +1769,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname,
 }
 #endif
 
-struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
-				    const xfrm_address_t *saddr,
-				    const xfrm_address_t *daddr,
-				    int family, u32 mark);
+struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params);
 
 struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);