Merge tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from CAN, netfilter, wireguard and IPsec.

  I'd like to highlight [ lowlight? - Linus ] Florian W stepping down as
  a netfilter maintainer due to constant stream of bug reports. Not sure
  what we can do but IIUC this is not the first such case.

  Current release - regressions:

   - rxrpc: fix use of page_frag_alloc_align(), it changed semantics and
     we added a new caller in a different subtree

   - xfrm: allow UDP encapsulation only in offload modes

  Current release - new code bugs:

   - tcp: fix refcnt handling in __inet_hash_connect()

   - Revert "net: Re-use and set mono_delivery_time bit for userspace
     tstamp packets", conflicted with some expectations in BPF uAPI

  Previous releases - regressions:

   - ipv4: raw: fix sending packets from raw sockets via IPsec tunnels

   - devlink: fix devlink's parallel command processing

   - veth: do not manipulate GRO when using XDP

   - esp: fix bad handling of pages from page_pool

  Previous releases - always broken:

   - report RCU QS for busy network kthreads (with Paul McK's blessing)

   - tcp/rds: fix use-after-free on netns with kernel TCP reqsk

   - virt: vmxnet3: fix missing reserved tailroom with XDP

  Misc:

   - couple of build fixes for Documentation"

* tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (59 commits)
  selftests: forwarding: Fix ping failure due to short timeout
  MAINTAINERS: step down as netfilter maintainer
  netfilter: nf_tables: Fix a memory leak in nf_tables_updchain
  net: dsa: mt7530: fix handling of all link-local frames
  net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports
  bpf: report RCU QS in cpumap kthread
  net: report RCU QS on threaded NAPI repolling
  rcu: add a helper to report consolidated flavor QS
  ionic: update documentation for XDP support
  lib/bitmap: Fix bitmap_scatter() and bitmap_gather() kernel doc
  netfilter: nf_tables: do not compare internal table flags on updates
  netfilter: nft_set_pipapo: release elements in clone only from destroy path
  octeontx2-af: Use separate handlers for interrupts
  octeontx2-pf: Send UP messages to VF only when VF is up.
  octeontx2-pf: Use default max_active works instead of one
  octeontx2-pf: Wait till detach_resources msg is complete
  octeontx2: Detect the mbox up or down message via register
  devlink: fix port new reply cmd type
  tcp: Clear req->syncookie in reqsk_alloc().
  net/bnx2x: Prevent access to a freed page in page_pool
  ...

6 files changed, 74 insertions, 33 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index fb3a9c93ac86..aa4096126553 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -522,17 +522,18 @@ static inline void bitmap_replace(unsigned long *dst,
  *
  * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12)
  *
- * A more 'visual' description of the operation:
- * src:  0000000001011010
- *                 ||||||
- *          +------+|||||
- *          |  +----+||||
- *          |  |+----+|||
- *          |  ||   +-+||
- *          |  ||   |  ||
- * mask: ...v..vv...v..vv
- *       ...0..11...0..10
- * dst:  0000001100000010
+ * A more 'visual' description of the operation::
+ *
+ *	src:  0000000001011010
+ *	                ||||||
+ *	         +------+|||||
+ *	         |  +----+||||
+ *	         |  |+----+|||
+ *	         |  ||   +-+||
+ *	         |  ||   |  ||
+ *	mask: ...v..vv...v..vv
+ *	      ...0..11...0..10
+ *	dst:  0000001100000010
  *
  * A relationship exists between bitmap_scatter() and bitmap_gather().
  * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation.
@@ -568,16 +569,17 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src,
  *
  * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5)
  *
- * A more 'visual' description of the operation:
- * mask: ...v..vv...v..vv
- * src:  0000001100000010
- *          ^  ^^   ^   0
- *          |  ||   |  10
- *          |  ||   > 010
- *          |  |+--> 1010
- *          |  +--> 11010
- *          +----> 011010
- * dst:  0000000000011010
+ * A more 'visual' description of the operation::
+ *
+ *	mask: ...v..vv...v..vv
+ *	src:  0000001100000010
+ *	         ^  ^^   ^   0
+ *	         |  ||   |  10
+ *	         |  ||   > 010
+ *	         |  |+--> 1010
+ *	         |  +--> 11010
+ *	         +----> 011010
+ *	dst:  0000000000011010
  *
  * A relationship exists between bitmap_gather() and bitmap_scatter(). See
  * bitmap_scatter() for the bitmap scatter detailed operations.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c6f6ac779b34..cb37817d6382 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2072,6 +2072,7 @@ struct net_device {
 		struct pcpu_sw_netstats __percpu	*tstats;
 		struct pcpu_dstats __percpu		*dstats;
 	};
+	unsigned long		state;
 	unsigned int		flags;
 	unsigned short		hard_header_len;
 	netdev_features_t	features;
@@ -2117,7 +2118,6 @@ struct net_device {
 	 *	part of the usual set specified in Space.c.
 	 */
 
-	unsigned long		state;
 
 	struct list_head	dev_list;
 	struct list_head	napi_list;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 16f519914415..17d7ed5f3ae6 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -247,6 +247,37 @@ do { \
 	cond_resched(); \
 } while (0)
 
+/**
+ * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states
+ * @old_ts: jiffies at start of processing.
+ *
+ * This helper is for long-running softirq handlers, such as NAPI threads in
+ * networking. The caller should initialize the variable passed in as @old_ts
+ * at the beginning of the softirq handler. When invoked frequently, this macro
+ * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will
+ * provide both RCU and RCU-Tasks quiescent states. Note that this macro
+ * modifies its old_ts argument.
+ *
+ * Because regions of code that have disabled softirq act as RCU read-side
+ * critical sections, this macro should be invoked with softirq (and
+ * preemption) enabled.
+ *
+ * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would
+ * have more chance to invoke schedule() calls and provide necessary quiescent
+ * states. As a contrast, calling cond_resched() only won't achieve the same
+ * effect because cond_resched() does not provide RCU-Tasks quiescent states.
+ */
+#define rcu_softirq_qs_periodic(old_ts) \
+do { \
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \
+	    time_after(jiffies, (old_ts) + HZ / 10)) { \
+		preempt_disable(); \
+		rcu_softirq_qs(); \
+		preempt_enable(); \
+		(old_ts) = jiffies; \
+	} \
+} while (0)
+
 /*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3023bc2be6a1..0c7c67b3a87b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -822,9 +822,9 @@ typedef unsigned char *sk_buff_data_t;
  *	@decrypted: Decrypted SKB
  *	@slow_gro: state present at GRO time, slower prepare step required
  *	@mono_delivery_time: When set, skb->tstamp has the
- *		delivery_time in mono clock base (i.e., EDT) or a clock base chosen
- *		by SO_TXTIME. If zero, skb->tstamp has the (rcv) timestamp at
- *		ingress.
+ *		delivery_time in mono clock base (i.e. EDT).  Otherwise, the
+ *		skb->tstamp has the (rcv) timestamp at ingress and
+ *		delivery_time at egress.
  *	@napi_id: id of the NAPI struct this skb came from
  *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@alloc_cpu: CPU which did the skb allocation.
@@ -3524,6 +3524,16 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
 bool napi_pp_put_page(struct page *page, bool napi_safe);
 
 static inline void
+skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe)
+{
+#ifdef CONFIG_PAGE_POOL
+	if (skb->pp_recycle && napi_pp_put_page(page, napi_safe))
+		return;
+#endif
+	put_page(page);
+}
+
+static inline void
 napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe)
 {
 	struct page *page = skb_frag_page(frag);
diff --git a/include/linux/socket.h b/include/linux/socket.h
index cfcb7e2c3813..139c330ccf2c 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -422,13 +422,6 @@ extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
 			       struct user_msghdr __user *umsg,
 			       struct sockaddr __user *uaddr,
 			       unsigned int flags);
-extern int sendmsg_copy_msghdr(struct msghdr *msg,
-			       struct user_msghdr __user *umsg, unsigned flags,
-			       struct iovec **iov);
-extern int recvmsg_copy_msghdr(struct msghdr *msg,
-			       struct user_msghdr __user *umsg, unsigned flags,
-			       struct sockaddr __user **uaddr,
-			       struct iovec **iov);
 extern int __copy_msghdr(struct msghdr *kmsg,
 			 struct user_msghdr *umsg,
 			 struct sockaddr __user **save_addr);
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 8839133d6f6b..004e651e6067 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -61,7 +61,11 @@ struct request_sock {
 	struct request_sock		*dl_next;
 	u16				mss;
 	u8				num_retrans; /* number of retransmits */
-	u8				syncookie:1; /* syncookie: encode tcpopts in timestamp */
+	u8				syncookie:1; /* True if
+						      * 1) tcpopts needs to be encoded in
+						      *    TS of SYN+ACK
+						      * 2) ACK is validated by BPF kfunc.
+						      */
 	u8				num_timeout:7; /* number of timeouts */
 	u32				ts_recent;
 	struct timer_list		rsk_timer;
@@ -144,6 +148,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
 	sk_node_init(&req_to_sk(req)->sk_node);
 	sk_tx_queue_clear(req_to_sk(req));
 	req->saved_syn = NULL;
+	req->syncookie = 0;
 	req->timeout = 0;
 	req->num_timeout = 0;
 	req->num_retrans = 0;