From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- net/sunrpc/timer.c | 123 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 123 insertions(+) create mode 100644 net/sunrpc/timer.c (limited to 'net/sunrpc/timer.c') diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c new file mode 100644 index 000000000..81ae35b37 --- /dev/null +++ b/net/sunrpc/timer.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/net/sunrpc/timer.c + * + * Estimate RPC request round trip time. + * + * Based on packet round-trip and variance estimator algorithms described + * in appendix A of "Congestion Avoidance and Control" by Van Jacobson + * and Michael J. Karels (ACM Computer Communication Review; Proceedings + * of the Sigcomm '88 Symposium in Stanford, CA, August, 1988). + * + * This RTT estimator is used only for RPC over datagram protocols. + * + * Copyright (C) 2002 Trond Myklebust + */ + +#include + +#include +#include +#include + +#include + +#define RPC_RTO_MAX (60*HZ) +#define RPC_RTO_INIT (HZ/5) +#define RPC_RTO_MIN (HZ/10) + +/** + * rpc_init_rtt - Initialize an RPC RTT estimator context + * @rt: context to initialize + * @timeo: initial timeout value, in jiffies + * + */ +void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) +{ + unsigned long init = 0; + unsigned int i; + + rt->timeo = timeo; + + if (timeo > RPC_RTO_INIT) + init = (timeo - RPC_RTO_INIT) << 3; + for (i = 0; i < 5; i++) { + rt->srtt[i] = init; + rt->sdrtt[i] = RPC_RTO_INIT; + rt->ntimeouts[i] = 0; + } +} +EXPORT_SYMBOL_GPL(rpc_init_rtt); + +/** + * rpc_update_rtt - Update an RPC RTT estimator context + * @rt: context to update + * @timer: timer array index (request type) + * @m: recent actual RTT, in jiffies + * + * NB: When computing the smoothed RTT and standard deviation, + * be careful not to produce negative intermediate results. + */ +void rpc_update_rtt(struct rpc_rtt *rt, unsigned int timer, long m) +{ + long *srtt, *sdrtt; + + if (timer-- == 0) + return; + + /* jiffies wrapped; ignore this one */ + if (m < 0) + return; + + if (m == 0) + m = 1L; + + srtt = (long *)&rt->srtt[timer]; + m -= *srtt >> 3; + *srtt += m; + + if (m < 0) + m = -m; + + sdrtt = (long *)&rt->sdrtt[timer]; + m -= *sdrtt >> 2; + *sdrtt += m; + + /* Set lower bound on the variance */ + if (*sdrtt < RPC_RTO_MIN) + *sdrtt = RPC_RTO_MIN; +} +EXPORT_SYMBOL_GPL(rpc_update_rtt); + +/** + * rpc_calc_rto - Provide an estimated timeout value + * @rt: context to use for calculation + * @timer: timer array index (request type) + * + * Estimate RTO for an NFS RPC sent via an unreliable datagram. Use + * the mean and mean deviation of RTT for the appropriate type of RPC + * for frequently issued RPCs, and a fixed default for the others. + * + * The justification for doing "other" this way is that these RPCs + * happen so infrequently that timer estimation would probably be + * stale. Also, since many of these RPCs are non-idempotent, a + * conservative timeout is desired. + * + * getattr, lookup, + * read, write, commit - A+4D + * other - timeo + */ +unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned int timer) +{ + unsigned long res; + + if (timer-- == 0) + return rt->timeo; + + res = ((rt->srtt[timer] + 7) >> 3) + rt->sdrtt[timer]; + if (res > RPC_RTO_MAX) + res = RPC_RTO_MAX; + + return res; +} +EXPORT_SYMBOL_GPL(rpc_calc_rto); -- cgit v1.3.1