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, 37 insertions, 0 deletions

diff --git a/Documentation/ABI/removed/sysfs-mce b/Documentation/ABI/removed/sysfs-mce
new file mode 100644
index 000000000..ef5dd2a80
--- /dev/null
+++ b/Documentation/ABI/removed/sysfs-mce
@@ -0,0 +1,37 @@
+What:		/sys/devices/system/machinecheck/machinecheckX/tolerant
+Contact:	Borislav Petkov <bp@suse.de>
+Date:		Dec, 2021
+Description:
+		Unused and obsolete after the advent of recoverable machine
+		checks (see last sentence below) and those are present since
+		2010 (Nehalem).
+
+		Original description:
+
+		The entries appear for each CPU, but they are truly shared
+		between all CPUs.
+
+		Tolerance level. When a machine check exception occurs for a
+		non corrected machine check the kernel can take different
+		actions.
+
+		Since machine check exceptions can happen any time it is
+		sometimes risky for the kernel to kill a process because it
+		defies normal kernel locking rules. The tolerance level
+		configures how hard the kernel tries to recover even at some
+		risk of	deadlock. Higher tolerant values trade potentially
+		better uptime with the risk of a crash or even corruption
+		(for tolerant >= 3).
+
+		==  ===========================================================
+		 0  always panic on uncorrected errors, log corrected errors
+		 1  panic or SIGBUS on uncorrected errors, log corrected errors
+		 2  SIGBUS or log uncorrected errors, log corrected errors
+		 3  never panic or SIGBUS, log all errors (for testing only)
+		==  ===========================================================
+
+		Default: 1
+
+		Note this only makes a difference if the CPU allows recovery
+		from a machine check exception. Current x86 CPUs generally
+		do not.