Merge branch 'for-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup into for-7.1

To receive 5b30afc20b3f ("cgroup: Expose some cgroup helpers") which will be
used by sub-sched support.

Signed-off-by: Tejun Heo <tj@kernel.org>

23 files changed, 259 insertions, 58 deletions

diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h
index c89b1b1b12dd..bfe60d6cf28d 100644
--- a/include/kunit/run-in-irq-context.h
+++ b/include/kunit/run-in-irq-context.h
@@ -12,16 +12,16 @@
 #include <linux/hrtimer.h>
 #include <linux/workqueue.h>
 
-#define KUNIT_IRQ_TEST_HRTIMER_INTERVAL us_to_ktime(5)
-
 struct kunit_irq_test_state {
 	bool (*func)(void *test_specific_state);
 	void *test_specific_state;
 	bool task_func_reported_failure;
 	bool hardirq_func_reported_failure;
 	bool softirq_func_reported_failure;
+	atomic_t task_func_calls;
 	atomic_t hardirq_func_calls;
 	atomic_t softirq_func_calls;
+	ktime_t interval;
 	struct hrtimer timer;
 	struct work_struct bh_work;
 };
@@ -30,14 +30,25 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer)
 {
 	struct kunit_irq_test_state *state =
 		container_of(timer, typeof(*state), timer);
+	int task_calls, hardirq_calls, softirq_calls;
 
 	WARN_ON_ONCE(!in_hardirq());
-	atomic_inc(&state->hardirq_func_calls);
+	task_calls = atomic_read(&state->task_func_calls);
+	hardirq_calls = atomic_inc_return(&state->hardirq_func_calls);
+	softirq_calls = atomic_read(&state->softirq_func_calls);
+
+	/*
+	 * If the timer is firing too often for the softirq or task to ever have
+	 * a chance to run, increase the timer interval.  This is needed on very
+	 * slow systems.
+	 */
+	if (hardirq_calls >= 20 && (softirq_calls == 0 || task_calls == 0))
+		state->interval = ktime_add_ns(state->interval, 250);
 
 	if (!state->func(state->test_specific_state))
 		state->hardirq_func_reported_failure = true;
 
-	hrtimer_forward_now(&state->timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL);
+	hrtimer_forward_now(&state->timer, state->interval);
 	queue_work(system_bh_wq, &state->bh_work);
 	return HRTIMER_RESTART;
 }
@@ -86,10 +97,14 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *),
 	struct kunit_irq_test_state state = {
 		.func = func,
 		.test_specific_state = test_specific_state,
+		/*
+		 * Start with a 5us timer interval.  If the system can't keep
+		 * up, kunit_irq_test_timer_func() will increase it.
+		 */
+		.interval = us_to_ktime(5),
 	};
 	unsigned long end_jiffies;
-	int hardirq_calls, softirq_calls;
-	bool allctx = false;
+	int task_calls, hardirq_calls, softirq_calls;
 
 	/*
 	 * Set up a hrtimer (the way we access hardirq context) and a work
@@ -104,21 +119,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *),
 	 * and hardirq), or 1 second, whichever comes first.
 	 */
 	end_jiffies = jiffies + HZ;
-	hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL,
-		      HRTIMER_MODE_REL_HARD);
-	for (int task_calls = 0, calls = 0;
-	     ((calls < max_iterations) || !allctx) &&
-	     !time_after(jiffies, end_jiffies);
-	     task_calls++) {
+	hrtimer_start(&state.timer, state.interval, HRTIMER_MODE_REL_HARD);
+	do {
 		if (!func(test_specific_state))
 			state.task_func_reported_failure = true;
 
+		task_calls = atomic_inc_return(&state.task_func_calls);
 		hardirq_calls = atomic_read(&state.hardirq_func_calls);
 		softirq_calls = atomic_read(&state.softirq_func_calls);
-		calls = task_calls + hardirq_calls + softirq_calls;
-		allctx = (task_calls > 0) && (hardirq_calls > 0) &&
-			 (softirq_calls > 0);
-	}
+	} while ((task_calls + hardirq_calls + softirq_calls < max_iterations ||
+		  (task_calls == 0 || hardirq_calls == 0 ||
+		   softirq_calls == 0)) &&
+		 !time_after(jiffies, end_jiffies));
 
 	/* Cancel the timer and work. */
 	hrtimer_cancel(&state.timer);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index bc892e3b37ee..e52160e85af4 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -42,6 +42,14 @@ struct kernel_clone_args;
 
 #ifdef CONFIG_CGROUPS
 
+/*
+ * To avoid confusing the compiler (and generating warnings) with code
+ * that attempts to access what would be a 0-element array (i.e. sized
+ * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this
+ * constant expression can be added.
+ */
+#define CGROUP_HAS_SUBSYS_CONFIG	(CGROUP_SUBSYS_COUNT > 0)
+
 enum css_task_iter_flags {
 	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
 	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
@@ -76,6 +84,7 @@ enum cgroup_lifetime_events {
 extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
+extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 extern struct blocking_notifier_head cgroup_lifetime_notifier;
 
@@ -103,6 +112,8 @@ extern struct blocking_notifier_head cgroup_lifetime_notifier;
 #define cgroup_subsys_on_dfl(ss)						\
 	static_branch_likely(&ss ## _on_dfl_key)
 
+bool cgroup_on_dfl(const struct cgroup *cgrp);
+
 bool css_has_online_children(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
 struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup,
@@ -274,6 +285,32 @@ void css_task_iter_end(struct css_task_iter *it);
 	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
 	     (pos) = css_next_descendant_post((pos), (css)))
 
+/* iterate over child cgrps, lock should be held throughout iteration */
+#define cgroup_for_each_live_child(child, cgrp)				\
+	list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       cgroup_is_dead(child); }))			\
+			;						\
+		else
+
+/* walk live descendants in pre order */
+#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)		\
+	css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL))	\
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       (dsct) = (d_css)->cgroup;			\
+		       cgroup_is_dead(dsct); }))			\
+			;						\
+		else
+
+/* walk live descendants in postorder */
+#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp)		\
+	css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL))	\
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       (dsct) = (d_css)->cgroup;			\
+		       cgroup_is_dead(dsct); }))			\
+			;						\
+		else
+
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
@@ -337,6 +374,27 @@ static inline u64 cgroup_id(const struct cgroup *cgrp)
 }
 
 /**
+ * cgroup_css - obtain a cgroup's css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest (%NULL returns @cgrp->self)
+ *
+ * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
+ * function must be called either under cgroup_mutex or rcu_read_lock() and
+ * the caller is responsible for pinning the returned css if it wants to
+ * keep accessing it outside the said locks.  This function may return
+ * %NULL if @cgrp doesn't have @subsys_id enabled.
+ */
+static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+						     struct cgroup_subsys *ss)
+{
+	if (CGROUP_HAS_SUBSYS_CONFIG && ss)
+		return rcu_dereference_check(cgrp->subsys[ss->id],
+					lockdep_is_held(&cgroup_mutex));
+	else
+		return &cgrp->self;
+}
+
+/**
  * css_is_dying - test whether the specified css is dying
  * @css: target css
  *
@@ -372,6 +430,11 @@ static inline bool css_is_self(struct cgroup_subsys_state *css)
 	return false;
 }
 
+static inline bool cgroup_is_dead(const struct cgroup *cgrp)
+{
+	return !(cgrp->self.flags & CSS_ONLINE);
+}
+
 static inline void cgroup_get(struct cgroup *cgrp)
 {
 	css_get(&cgrp->self);
@@ -387,8 +450,6 @@ static inline void cgroup_put(struct cgroup *cgrp)
 	css_put(&cgrp->self);
 }
 
-extern struct mutex cgroup_mutex;
-
 static inline void cgroup_lock(void)
 {
 	mutex_lock(&cgroup_mutex);
diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 35227d47cfc9..dc272b514a01 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -16,22 +16,26 @@
  */
 #define INDIRECT_CALL_1(f, f1, ...)					\
 	({								\
-		likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__);	\
+		typeof(f) __f1 = (f);					\
+		likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_2(f, f2, f1, ...)					\
 	({								\
-		likely(f == f2) ? f2(__VA_ARGS__) :			\
-				  INDIRECT_CALL_1(f, f1, __VA_ARGS__);	\
+		typeof(f) __f2 = (f);					\
+		likely(__f2 == f2) ? f2(__VA_ARGS__) :			\
+				  INDIRECT_CALL_1(__f2, f1, __VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_3(f, f3, f2, f1, ...)					\
 	({									\
-		likely(f == f3) ? f3(__VA_ARGS__) :				\
-				  INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__);	\
+		typeof(f) __f3 = (f);						\
+		likely(__f3 == f3) ? f3(__VA_ARGS__) :				\
+				  INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...)					\
 	({									\
-		likely(f == f4) ? f4(__VA_ARGS__) :				\
-				  INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__);	\
+		typeof(f) __f4 = (f);						\
+		likely(__f4 == f4) ? f4(__VA_ARGS__) :				\
+				  INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__);	\
 	})
 
 #define INDIRECT_CALLABLE_DECLARE(f)	f
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index c92c1149ee6e..a01a474719a7 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -7,6 +7,24 @@
 
 struct mm_struct;
 
+/* opaque kthread data */
+struct kthread;
+
+/*
+ * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
+ * always remain a kthread.  For kthreads p->worker_private always
+ * points to a struct kthread.  For tasks that are not kthreads
+ * p->worker_private is used to point to other things.
+ *
+ * Return NULL for any task that is not a kthread.
+ */
+static inline struct kthread *tsk_is_kthread(struct task_struct *p)
+{
+	if (p->flags & PF_KTHREAD)
+		return p->worker_private;
+	return NULL;
+}
+
 __printf(4, 5)
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 					   void *data,
@@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k);
 int kthread_park(struct task_struct *k);
 void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
-void kthread_exit(long result) __noreturn;
+#define kthread_exit(result) do_exit(result)
 void kthread_complete_and_exit(struct completion *, long) __noreturn;
 int kthreads_update_housekeeping(void);
+void kthread_do_exit(struct kthread *, long);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d4e6e00bb90a..67e25f6d15a4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
 	spin_lock(&txq->_xmit_lock);
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, cpu);
 }
 
@@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
 	spin_lock_bh(&txq->_xmit_lock);
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 }
 
@@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 	bool ok = spin_trylock(&txq->_xmit_lock);
 
 	if (likely(ok)) {
-		/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+		/* Pairs with READ_ONCE() in netif_tx_owned() */
 		WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 	}
 	return ok;
@@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock_bh(&txq->_xmit_lock);
 }
@@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev)
 	local_bh_enable();
 }
 
+#ifndef CONFIG_PREEMPT_RT
+static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu)
+{
+	/* Other cpus might concurrently change txq->xmit_lock_owner
+	 * to -1 or to their cpu id, but not to our id.
+	 */
+	return READ_ONCE(txq->xmit_lock_owner) == cpu;
+}
+
+#else
+static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu)
+{
+	return rt_mutex_owner(&txq->_xmit_lock.lock) == current;
+}
+
+#endif
+
 static inline void netif_addr_lock(struct net_device *dev)
 {
 	unsigned char nest_level = 0;
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 825f5865bfc5..c8e227a3f9e2 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns)
 
 #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns)))
 
+bool may_see_all_namespaces(void);
+
 static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns)
 {
 	return atomic_read(&ns->__ns_ref_active);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 876358cfe1b1..d862fa610270 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
 
 int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		    struct vm_area_struct *vma);
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu);
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu);
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu);
 #endif /* _LINUX_RING_BUFFER_H */
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 2ca60828f28b..1502b2a355f9 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -32,6 +32,7 @@
 #define VENDOR_ID_DLINK			0x2001
 #define VENDOR_ID_DELL			0x413c
 #define VENDOR_ID_ASUS			0x0b05
+#define VENDOR_ID_TRENDNET		0x20f4
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);
diff --git a/include/net/act_api.h b/include/net/act_api.h
index e1e8f0f7dacb..d11b79107930 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -70,6 +70,7 @@ struct tc_action {
 #define TCA_ACT_FLAGS_REPLACE	(1U << (TCA_ACT_FLAGS_USER_BITS + 2))
 #define TCA_ACT_FLAGS_NO_RTNL	(1U << (TCA_ACT_FLAGS_USER_BITS + 3))
 #define TCA_ACT_FLAGS_AT_INGRESS	(1U << (TCA_ACT_FLAGS_USER_BITS + 4))
+#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT	(1U << (TCA_ACT_FLAGS_USER_BITS + 5))
 
 /* Update lastuse only if needed, to avoid dirtying a cache line.
  * We use a temp variable to avoid fetching jiffies twice.
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 4ad5521e7731..395c6e281c5f 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond);
 void bond_debug_unregister(struct bonding *bond);
 void bond_debug_reregister(struct bonding *bond);
 const char *bond_mode_name(int mode);
+bool __bond_xdp_check(int mode, int xmit_policy);
 bool bond_xdp_check(struct bonding *bond, int mode);
 void bond_setup(struct net_device *bond_dev);
 unsigned int bond_get_num_tx_queues(void);
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 282e29237d93..c16de5b7963f 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk,
 {
 	if (!net_eq(sock_net(sk), net) ||
 	    sk->sk_family != AF_INET6 ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
 	    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 		return false;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ac05a52d9e13..5a979dcab538 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk,
 			      int dif, int sdif)
 {
 	if (!net_eq(sock_net(sk), net) ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    sk->sk_addrpair != cookie)
 	        return false;
 
diff --git a/include/net/ip.h b/include/net/ip.h
index 69d5cef46004..7f9abd457e01 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
-	ipcm->protocol = inet->inet_num;
+	ipcm->protocol = READ_ONCE(inet->inet_num);
 }
 
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b4495c38e0a0..318593743b6e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net,
 	siphash_aligned_key_t hash_key;
 	u32 mp_seed;
 
-	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;
+	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed);
 	fib_multipath_hash_construct_key(&hash_key, mp_seed);
 
 	return flow_hash_from_keys_seed(keys, &hash_key);
diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h
index 481a7b28e6f2..82b5d21aae87 100644
--- a/include/net/libeth/xsk.h
+++ b/include/net/libeth/xsk.h
@@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp,
  * @pending: current number of XSkFQEs to refill
  * @thresh: threshold below which the queue is refilled
  * @buf_len: HW-writeable length per each buffer
+ * @truesize: step between consecutive buffers, 0 if none exists
  * @nid: ID of the closest NUMA node with memory
  */
 struct libeth_xskfq {
@@ -614,6 +615,8 @@ struct libeth_xskfq {
 	u32			thresh;
 
 	u32			buf_len;
+	u32			truesize;
+
 	int			nid;
 };
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 426534a711b0..e2d2bfc1f989 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv)
  * @NFT_ITER_UNSPEC: unspecified, to catch errors
  * @NFT_ITER_READ: read-only iteration over set elements
  * @NFT_ITER_UPDATE: iteration under mutex to update set element state
+ * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element
  */
 enum nft_iter_type {
 	NFT_ITER_UNSPEC,
 	NFT_ITER_READ,
 	NFT_ITER_UPDATE,
+	NFT_ITER_UPDATE_CLONE,
 };
 
 struct nft_set;
@@ -1861,6 +1863,11 @@ struct nft_trans_gc {
 	struct rcu_head		rcu;
 };
 
+static inline int nft_trans_gc_space(const struct nft_trans_gc *trans)
+{
+	return NFT_TRANS_GC_BATCHCOUNT - trans->count;
+}
+
 static inline void nft_ctx_update(struct nft_ctx *ctx,
 				  const struct nft_trans *trans)
 {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c3a7268b567e..d5d55cb21686 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -778,13 +778,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb)
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 {
 	struct Qdisc *qdisc;
+	bool nolock;
 
 	for (; i < dev->num_tx_queues; i++) {
 		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
 		if (qdisc) {
+			nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+			if (nolock)
+				spin_lock_bh(&qdisc->seqlock);
 			spin_lock_bh(qdisc_lock(qdisc));
 			qdisc_reset(qdisc);
 			spin_unlock_bh(qdisc_lock(qdisc));
+			if (nolock) {
+				clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+				clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
+				spin_unlock_bh(&qdisc->seqlock);
+			}
 		}
 	}
 }
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index cddebafb9f77..6f996229167b 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -5,16 +5,47 @@
 #include <linux/types.h>
 
 struct net;
+extern struct net init_net;
+
+union tcp_seq_and_ts_off {
+	struct {
+		u32 seq;
+		u32 ts_off;
+	};
+	u64 hash64;
+};
 
 u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
-u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
-		   __be16 sport, __be16 dport);
-u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr);
-u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
-		     __be16 sport, __be16 dport);
-u32 secure_tcpv6_ts_off(const struct net *net,
-			const __be32 *saddr, const __be32 *daddr);
+union tcp_seq_and_ts_off
+secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr,
+			  __be16 sport, __be16 dport);
+
+static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+				 __be16 sport, __be16 dport)
+{
+	union tcp_seq_and_ts_off ts;
+
+	ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr,
+				       sport, dport);
+
+	return ts.seq;
+}
+
+union tcp_seq_and_ts_off
+secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr,
+			    const __be32 *daddr,
+			    __be16 sport, __be16 dport);
+
+static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+				   __be16 sport, __be16 dport)
+{
+	union tcp_seq_and_ts_off ts;
+
+	ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr,
+					 sport, dport);
 
+	return ts.seq;
+}
 #endif /* _NET_SECURE_SEQ */
diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h
index b147a3bb1a46..e0fded18e18c 100644
--- a/include/net/tc_act/tc_gate.h
+++ b/include/net/tc_act/tc_gate.h
@@ -32,6 +32,7 @@ struct tcf_gate_params {
 	s32			tcfg_clockid;
 	size_t			num_entries;
 	struct list_head	entries;
+	struct rcu_head		rcu;
 };
 
 #define GATE_ACT_GATE_OPEN	BIT(0)
@@ -39,7 +40,7 @@ struct tcf_gate_params {
 
 struct tcf_gate {
 	struct tc_action	common;
-	struct tcf_gate_params	param;
+	struct tcf_gate_params __rcu *param;
 	u8			current_gate_status;
 	ktime_t			current_close_time;
 	u32			current_entry_octets;
@@ -51,47 +52,65 @@ struct tcf_gate {
 
 #define to_gate(a) ((struct tcf_gate *)a)
 
+static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a)
+{
+	struct tcf_gate *gact = to_gate(a);
+
+	return rcu_dereference_protected(gact->param,
+					 lockdep_is_held(&gact->tcf_lock));
+}
+
 static inline s32 tcf_gate_prio(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	s32 tcfg_prio;
 
-	tcfg_prio = to_gate(a)->param.tcfg_priority;
+	p = tcf_gate_params_locked(a);
+	tcfg_prio = p->tcfg_priority;
 
 	return tcfg_prio;
 }
 
 static inline u64 tcf_gate_basetime(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_basetime;
 
-	tcfg_basetime = to_gate(a)->param.tcfg_basetime;
+	p = tcf_gate_params_locked(a);
+	tcfg_basetime = p->tcfg_basetime;
 
 	return tcfg_basetime;
 }
 
 static inline u64 tcf_gate_cycletime(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_cycletime;
 
-	tcfg_cycletime = to_gate(a)->param.tcfg_cycletime;
+	p = tcf_gate_params_locked(a);
+	tcfg_cycletime = p->tcfg_cycletime;
 
 	return tcfg_cycletime;
 }
 
 static inline u64 tcf_gate_cycletimeext(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_cycletimeext;
 
-	tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext;
+	p = tcf_gate_params_locked(a);
+	tcfg_cycletimeext = p->tcfg_cycletime_ext;
 
 	return tcfg_cycletimeext;
 }
 
 static inline u32 tcf_gate_num_entries(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u32 num_entries;
 
-	num_entries = to_gate(a)->param.num_entries;
+	p = tcf_gate_params_locked(a);
+	num_entries = p->num_entries;
 
 	return num_entries;
 }
@@ -105,7 +124,7 @@ static inline struct action_gate_entry
 	u32 num_entries;
 	int i = 0;
 
-	p = &to_gate(a)->param;
+	p = tcf_gate_params_locked(a);
 	num_entries = p->num_entries;
 
 	list_for_each_entry(entry, &p->entries, list)
diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index c7f24a2da1ca..24d4d5a62b3c 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -13,15 +13,13 @@ struct tcf_ife_params {
 	u8 eth_src[ETH_ALEN];
 	u16 eth_type;
 	u16 flags;
-
+	struct list_head metalist;
 	struct rcu_head rcu;
 };
 
 struct tcf_ife_info {
 	struct tc_action common;
 	struct tcf_ife_params __rcu *params;
-	/* list of metaids allowed */
-	struct list_head metalist;
 };
 #define to_ife(a) ((struct tcf_ife_info *)a)
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index eb8bf63fdafc..978eea2d5df0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -43,6 +43,7 @@
 #include <net/dst.h>
 #include <net/mptcp.h>
 #include <net/xfrm.h>
+#include <net/secure_seq.h>
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
@@ -2464,8 +2465,9 @@ struct tcp_request_sock_ops {
 				       struct flowi *fl,
 				       struct request_sock *req,
 				       u32 tw_isn);
-	u32 (*init_seq)(const struct sk_buff *skb);
-	u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb);
+	union tcp_seq_and_ts_off (*init_seq_and_ts_off)(
+					const struct net *net,
+					const struct sk_buff *skb);
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 242e34f771cc..6b9ebae2dc95 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
 }
 
+static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
+{
+	return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool);
+}
+
 static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
@@ -122,7 +127,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 		goto out;
 
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 		xp_free(pos);
 	}
 
@@ -157,7 +162,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
 	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
 					struct xdp_buff_xsk, list_node);
 	if (frag) {
-		list_del(&frag->list_node);
+		list_del_init(&frag->list_node);
 		ret = &frag->xdp;
 	}
 
@@ -168,7 +173,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
-	list_del(&xskb->list_node);
+	list_del_init(&xskb->list_node);
 }
 
 static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
@@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 	return 0;
 }
 
+static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
+{
+	return 0;
+}
+
 static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 64a382fbc31a..2d366be46a1c 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -57,6 +57,7 @@
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_end_copy_to_cache,	"END-C2C")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_intr,		"INTR   ")	\
 	EM(netfs_rreq_trace_ki_complete,	"KI-CMPL")	\
 	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
@@ -169,7 +170,8 @@
 	EM(netfs_sreq_trace_put_oom,		"PUT OOM    ")	\
 	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
 	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
-	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
+	EM(netfs_sreq_trace_put_terminated,	"PUT TERM   ")	\
+	E_(netfs_sreq_trace_see_failed,		"SEE FAILED ")
 
 #define netfs_folio_traces					\
 	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\