Linux 6.18.5

index b98bb292fef0..ed2a7efaf8f2 100644
@@ -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;
 }
 

index bbcfdf12aa6e..45c0022b91ce 100644
@@ -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;
 

index f754a60de848..eb47d294e2c5 100644
@@ -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

114 lines not on this page · raw message

index 3c12d9f93331..136a6584be79 100644
@@ -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)

index 92ec751799f5..2f8b06b12a98 100644
@@ -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)

index 444bdfdab731..c7a4d2fff571 100644
@@ -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,

index 221a5ea019e6..d4e3111ba643 100644
@@ -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);

index 0e8b0a650108..30d5e5719793 100644
@@ -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;