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/batman-adv/bitarray.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 net/batman-adv/bitarray.c (limited to 'net/batman-adv/bitarray.c') diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c new file mode 100644 index 000000000..f814756d9 --- /dev/null +++ b/net/batman-adv/bitarray.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) B.A.T.M.A.N. contributors: + * + * Simon Wunderlich, Marek Lindner + */ + +#include "bitarray.h" +#include "main.h" + +#include + +#include "log.h" + +/** + * batadv_bitmap_shift_left() - shift the sequence number bitmap left + * @seq_bits: the sequence number bitmap to shift + * @n: number of positions to shift left + * + * Shift @seq_bits by @n positions. No-op if @n is not within the bounds of + * the bitmap. + */ +static void batadv_bitmap_shift_left(unsigned long *seq_bits, s32 n) +{ + if (n <= 0 || n >= BATADV_TQ_LOCAL_WINDOW_SIZE) + return; + + bitmap_shift_left(seq_bits, seq_bits, n, BATADV_TQ_LOCAL_WINDOW_SIZE); +} + +/** + * batadv_bit_get_packet() - receive and process one packet within the sequence + * number window + * @priv: the bat priv with all the mesh interface information + * @seq_bits: pointer to the sequence number bitmap of received packets + * @seq_num_diff: difference between the current/received sequence number and + * the last sequence number + * @set_mark: whether this packet should be marked in seq_bits + * + * Return: true if the window was moved (either new or very old), + * false if the window was not moved/shifted. + */ +bool batadv_bit_get_packet(void *priv, unsigned long *seq_bits, + s32 seq_num_diff, int set_mark) +{ + struct batadv_priv *bat_priv = priv; + + /* sequence number is slightly older. We already got a sequence number + * higher than this one, so we just mark it. + */ + if (seq_num_diff <= 0 && seq_num_diff > -BATADV_TQ_LOCAL_WINDOW_SIZE) { + if (set_mark) + batadv_set_bit(seq_bits, -seq_num_diff); + return false; + } + + /* sequence number is slightly newer, so we shift the window and + * set the mark if required + */ + if (seq_num_diff > 0 && seq_num_diff < BATADV_TQ_LOCAL_WINDOW_SIZE) { + batadv_bitmap_shift_left(seq_bits, seq_num_diff); + + if (set_mark) + batadv_set_bit(seq_bits, 0); + return true; + } + + /* sequence number is much newer, probably missed a lot of packets */ + if (seq_num_diff >= BATADV_TQ_LOCAL_WINDOW_SIZE && + seq_num_diff < BATADV_EXPECTED_SEQNO_RANGE) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "We missed a lot of packets (%i) !\n", + seq_num_diff - 1); + bitmap_zero(seq_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); + if (set_mark) + batadv_set_bit(seq_bits, 0); + return true; + } + + /* received a much older packet. The other host either restarted + * or the old packet got delayed somewhere in the network. The + * packet should be dropped without calling this function if the + * seqno window is protected. + * + * seq_num_diff <= -BATADV_TQ_LOCAL_WINDOW_SIZE + * or + * seq_num_diff >= BATADV_EXPECTED_SEQNO_RANGE + */ + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Other host probably restarted!\n"); + + bitmap_zero(seq_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); + if (set_mark) + batadv_set_bit(seq_bits, 0); + + return true; +} -- cgit v1.3.1