Merge tag 'v6.18.5' into 6.18-main

This is the 6.18.5 stable release

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCgAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmljs1IACgkQONu9yGCS
# aT66Kw//czXeq7+Mp+HJQNFQrdwIaaPmAON8gG14t5sAUe86qRGRrGzBr7TsArKA
# dImgnMjg/BO1f1lpxyKxBbs5vxDN+5dPPaJksJn2UKGJhDnqEEvdsaJli69SxNfw
# GXjbf2x2TUQQ/NAiP/qi4xatMjnOgCEcsdgxe64ZP8FzoJZP2NVf0dEBKdgC5Stp
# i0Kg0SqrM39eQd7YXxq+cQmOM+PApeYz1l68OvnxLlIp0oT8emLC5YhscIQfH5PM
# G1kfleYKTmKtf/Gbfq/DcNyhdHYrgJW/bInbx3gJXRdsr5PWoqSWBehvX9rAsnrK
# k/XyK2JlmBRLVJvg3h0M7j90d043fuLncUK0Zj3WmMsN+/NPPr5M0V3lgQgETM6w
# pOPIco2uOF9FHTe8mwXLZzjeLVCzodSDjRqwKWwH4PzobH64vASffVge1aDOzanA
# tShSOiP/Qb31Ag8Q357qJnYhoci1ZslX6dVVI3KVXdy7jkgtJusuKd8TQOH6aCap
# 6p/Rh7fMLp7htRAIGLZbpplgiuu3rQ6bk1MVE2X7FUBZzlkaa78FZTy5HCX+J3YF
# dTCiviHxjqYsEGjw7trnKm7G7TlFRIBZtSeLv7i4mlQlGbWEFSpvjbSsFDg1Al2S
# sOfjYVJk9w60/xBcM9BK44Tw+okpxQ8iBtZT3URG4ZnauUap0Mk=
# =krUN
# -----END PGP SIGNATURE-----
# gpg: Signature made Sun Jan 11 15:27:30 2026 CET
# gpg:                using RSA key 647F28654894E3BD457199BE38DBBDC86092693E
# gpg: Can't check signature: No public key

Author: frank-w

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 18
-SUBLEVEL = 4
+SUBLEVEL = 5
 EXTRAVERSION =
 NAME = Baby Opossum Posse
 

fs/nfs/localio.c

@@ -623,8 +623,6 @@ static void nfs_local_call_read(struct work_struct *work)
 	ssize_t status;
 	int n_iters;
 
-	save_cred = override_creds(filp->f_cred);
-
 	n_iters = atomic_read(&iocb->n_iters);
 	for (int i = 0; i < n_iters ; i++) {
 		if (iocb->iter_is_dio_aligned[i]) {
@@ -637,7 +635,10 @@ static void nfs_local_call_read(struct work_struct *work)
 		} else
 			iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
 
+		save_cred = override_creds(filp->f_cred);
 		status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]);
+		revert_creds(save_cred);
+
 		if (status != -EIOCBQUEUED) {
 			if (unlikely(status >= 0 && status < iocb->iters[i].count))
 				force_done = true; /* Partial read */
@@ -647,8 +648,6 @@ static void nfs_local_call_read(struct work_struct *work)
 			}
 		}
 	}
-
-	revert_creds(save_cred);
 }
 
 static int
@@ -830,7 +829,6 @@ static void nfs_local_call_write(struct work_struct *work)
 	int n_iters;
 
 	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
-	save_cred = override_creds(filp->f_cred);
 
 	file_start_write(filp);
 	n_iters = atomic_read(&iocb->n_iters);
@@ -845,7 +843,10 @@ static void nfs_local_call_write(struct work_struct *work)
 		} else
 			iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
 
+		save_cred = override_creds(filp->f_cred);
 		status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]);
+		revert_creds(save_cred);
+
 		if (status != -EIOCBQUEUED) {
 			if (unlikely(status >= 0 && status < iocb->iters[i].count))
 				force_done = true; /* Partial write */
@@ -857,7 +858,6 @@ static void nfs_local_call_write(struct work_struct *work)
 	}
 	file_end_write(filp);
 
-	revert_creds(save_cred);
 	current->flags = old_flags;
 }
 

include/linux/sched/topology.h

@@ -92,6 +92,9 @@ struct sched_domain {
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
 	/* idle_balance() stats */
+	unsigned int newidle_call;
+	unsigned int newidle_success;
+	unsigned int newidle_ratio;
 	u64 max_newidle_lb_cost;
 	unsigned long last_decay_max_lb_cost;
 

kernel/sched/core.c

@@ -121,6 +121,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
 
 #ifdef CONFIG_SCHED_PROXY_EXEC
 DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
@@ -8591,6 +8592,8 @@ void __init sched_init_smp(void)
 {
 	sched_init_numa(NUMA_NO_NODE);
 
+	prandom_init_once(&sched_rnd_state);
+
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot

kernel/sched/fair.c

@@ -12122,24 +12122,43 @@ void update_max_interval(void)
 	max_load_balance_interval = HZ*num_online_cpus()/10;
 }
 
-static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success)
 {
+	sd->newidle_call++;
+	sd->newidle_success += success;
+
+	if (sd->newidle_call >= 1024) {
+		sd->newidle_ratio = sd->newidle_success;
+		sd->newidle_call /= 2;
+		sd->newidle_success /= 2;
+	}
+}
+
+static inline bool
+update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success)
+{
+	unsigned long next_decay = sd->last_decay_max_lb_cost + HZ;
+	unsigned long now = jiffies;
+
+	if (cost)
+		update_newidle_stats(sd, success);
+
 	if (cost > sd->max_newidle_lb_cost) {
 		/*
 		 * Track max cost of a domain to make sure to not delay the
 		 * next wakeup on the CPU.
 		 */
 		sd->max_newidle_lb_cost = cost;
-		sd->last_decay_max_lb_cost = jiffies;
-	} else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) {
+		sd->last_decay_max_lb_cost = now;
+
+	} else if (time_after(now, next_decay)) {
 		/*
 		 * Decay the newidle max times by ~1% per second to ensure that
 		 * it is not outdated and the current max cost is actually
 		 * shorter.
 		 */
 		sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256;
-		sd->last_decay_max_lb_cost = jiffies;
-
+		sd->last_decay_max_lb_cost = now;
 		return true;
 	}
 
@@ -12171,7 +12190,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 		 * Decay the newidle max times here because this is a regular
 		 * visit to all the domains.
 		 */
-		need_decay = update_newidle_cost(sd, 0);
+		need_decay = update_newidle_cost(sd, 0, 0);
 		max_cost += sd->max_newidle_lb_cost;
 
 		/*
@@ -12787,14 +12806,16 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 
 	rcu_read_lock();
 	sd = rcu_dereference_check_sched_domain(this_rq->sd);
+	if (!sd) {
+		rcu_read_unlock();
+		goto out;
+	}
 
 	if (!get_rd_overloaded(this_rq->rd) ||
-	    (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
+	    this_rq->avg_idle < sd->max_newidle_lb_cost) {
 
-		if (sd)
-			update_next_balance(sd, &next_balance);
+		update_next_balance(sd, &next_balance);
 		rcu_read_unlock();
-
 		goto out;
 	}
 	rcu_read_unlock();
@@ -12814,17 +12835,37 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 			break;
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			unsigned int weight = 1;
+
+			if (sched_feat(NI_RANDOM)) {
+				/*
+				 * Throw a 1k sided dice; and only run
+				 * newidle_balance according to the success
+				 * rate.
+				 */
+				u32 d1k = sched_rng() % 1024;
+				weight = 1 + sd->newidle_ratio;
+				if (d1k > weight) {
+					update_newidle_stats(sd, 0);
+					continue;
+				}
+				weight = (1024 + weight/2) / weight;
+			}
 
 			pulled_task = sched_balance_rq(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
 
 			t1 = sched_clock_cpu(this_cpu);
 			domain_cost = t1 - t0;
-			update_newidle_cost(sd, domain_cost);
-
 			curr_cost += domain_cost;
 			t0 = t1;
+
+			/*
+			 * Track max cost of a domain to make sure to not delay the
+			 * next wakeup on the CPU.
+			 */
+			update_newidle_cost(sd, domain_cost, weight * !!pulled_task);
 		}
 
 		/*

kernel/sched/features.h

@@ -121,3 +121,8 @@ SCHED_FEAT(WA_BIAS, true)
 SCHED_FEAT(UTIL_EST, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
+
+/*
+ * Do newidle balancing proportional to its success rate using randomization.
+ */
+SCHED_FEAT(NI_RANDOM, true)

kernel/sched/sched.h

@@ -5,6 +5,7 @@
 #ifndef _KERNEL_SCHED_SCHED_H
 #define _KERNEL_SCHED_SCHED_H
 
+#include <linux/prandom.h>
 #include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/cpufreq.h>
@@ -1349,6 +1350,12 @@ static inline bool is_migration_disabled(struct task_struct *p)
 }
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DECLARE_PER_CPU(struct rnd_state, sched_rnd_state);
+
+static inline u32 sched_rng(void)
+{
+	return prandom_u32_state(this_cpu_ptr(&sched_rnd_state));
+}
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
 #define this_rq()		this_cpu_ptr(&runqueues)

kernel/sched/topology.c

@@ -1662,6 +1662,12 @@ sd_init(struct sched_domain_topology_level *tl,
 
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+
+		/* 50% success rate */
+		.newidle_call		= 512,
+		.newidle_success	= 256,
+		.newidle_ratio		= 512,
+
 		.max_newidle_lb_cost	= 0,
 		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,

net/mptcp/protocol.c

@@ -2421,10 +2421,10 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
  */
 static void __mptcp_subflow_disconnect(struct sock *ssk,
 				       struct mptcp_subflow_context *subflow,
-				       unsigned int flags)
+				       bool fastclosing)
 {
 	if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
-	    subflow->send_fastclose) {
+	    fastclosing) {
 		/* The MPTCP code never wait on the subflow sockets, TCP-level
 		 * disconnect should never fail
 		 */
@@ -2476,7 +2476,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
-		__mptcp_subflow_disconnect(ssk, subflow, flags);
+		__mptcp_subflow_disconnect(ssk, subflow, msk->fastclosing);
 		release_sock(ssk);
 
 		goto out;
@@ -2789,6 +2789,7 @@ static void mptcp_do_fastclose(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	mptcp_set_state(sk, TCP_CLOSE);
+	msk->fastclosing = 1;
 
 	/* Explicitly send the fastclose reset as need */
 	if (__mptcp_check_fallback(msk))
@@ -3299,6 +3300,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	msk->bytes_sent = 0;
 	msk->bytes_retrans = 0;
 	msk->rcvspace_init = 0;
+	msk->fastclosing = 0;
 
 	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);

net/mptcp/protocol.h

@@ -321,7 +321,8 @@ struct mptcp_sock {
 			fastopening:1,
 			in_accept_queue:1,
 			free_first:1,
-			rcvspace_init:1;
+			rcvspace_init:1,
+			fastclosing:1;
 	u32		notsent_lowat;
 	int		keepalive_cnt;
 	int		keepalive_idle;