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/mptcp/crypto.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 net/mptcp/crypto.c (limited to 'net/mptcp/crypto.c') diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c new file mode 100644 index 000000000..31948e18d --- /dev/null +++ b/net/mptcp/crypto.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP cryptographic functions + * Copyright (c) 2017 - 2019, Intel Corporation. + * + * Note: This code is based on mptcp_ctrl.c, mptcp_ipv4.c, and + * mptcp_ipv6 from multipath-tcp.org, authored by: + * + * Sébastien Barré + * Christoph Paasch + * Jaakko Korkeaniemi + * Gregory Detal + * Fabien Duchêne + * Andreas Seelinger + * Lavkesh Lahngir + * Andreas Ripke + * Vlad Dogaru + * Octavian Purdila + * John Ronan + * Catalin Nicutar + * Brandon Heller + */ + +#include +#include + +#include "protocol.h" + +#define SHA256_DIGEST_WORDS (SHA256_DIGEST_SIZE / 4) + +void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn) +{ + __be32 mptcp_hashed_key[SHA256_DIGEST_WORDS]; + __be64 input = cpu_to_be64(key); + + sha256((__force u8 *)&input, sizeof(input), (u8 *)mptcp_hashed_key); + + if (token) + *token = be32_to_cpu(mptcp_hashed_key[0]); + if (idsn) + *idsn = be64_to_cpu(*((__be64 *)&mptcp_hashed_key[6])); +} + +void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac) +{ + __be64 key[2] = { cpu_to_be64(key1), cpu_to_be64(key2) }; + + hmac_sha256_usingrawkey((const u8 *)key, sizeof(key), msg, len, hmac); +} + +#if IS_MODULE(CONFIG_MPTCP_KUNIT_TEST) +EXPORT_SYMBOL_GPL(mptcp_crypto_hmac_sha); +#endif -- cgit v1.3.1