sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

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 <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 30 insertions, 0 deletions

diff --git a/scripts/extract-fwblobs b/scripts/extract-fwblobs
new file mode 100755
index 000000000..53729124e
--- /dev/null
+++ b/scripts/extract-fwblobs
@@ -0,0 +1,30 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# -----------------------------------------------------------------------------
+# Extracts the vmlinux built-in firmware blobs - requires a non-stripped image
+# -----------------------------------------------------------------------------
+
+if [ -z "$1" ]; then
+	echo "Must provide a non-stripped vmlinux as argument"
+	exit 1
+fi
+
+read -r RD_ADDR_HEX RD_OFF_HEX <<< "$( readelf -SW "$1" |\
+grep -w rodata | awk '{print "0x"$5" 0x"$6}' )"
+
+FW_SYMS="$(readelf -sW "$1" |\
+awk -n '/fw_end/ { end=$2 ; print name " 0x" start " 0x" end; } { start=$2; name=$8; }')"
+
+while IFS= read -r entry; do
+	read -r FW_NAME FW_ADDR_ST_HEX FW_ADDR_END_HEX <<< "$entry"
+
+	# Notice kernel prepends _fw_ and appends _bin to the FW name
+	# in rodata; hence we hereby filter that out.
+	FW_NAME=${FW_NAME:4:-4}
+
+	FW_OFFSET="$(printf "%d" $((FW_ADDR_ST_HEX - RD_ADDR_HEX + RD_OFF_HEX)))"
+	FW_SIZE="$(printf "%d" $((FW_ADDR_END_HEX - FW_ADDR_ST_HEX)))"
+
+	dd if="$1" of="./${FW_NAME}" bs="${FW_SIZE}" count=1 iflag=skip_bytes skip="${FW_OFFSET}"
+done <<< "${FW_SYMS}"