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, 44 insertions, 0 deletions

diff --git a/block/partitions/mac.h b/block/partitions/mac.h
new file mode 100644
index 000000000..0e41c9da7
--- /dev/null
+++ b/block/partitions/mac.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  fs/partitions/mac.h
+ */
+
+#define MAC_PARTITION_MAGIC	0x504d
+
+/* type field value for A/UX or other Unix partitions */
+#define APPLE_AUX_TYPE	"Apple_UNIX_SVR2"
+
+struct mac_partition {
+	__be16	signature;	/* expected to be MAC_PARTITION_MAGIC */
+	__be16	res1;
+	__be32	map_count;	/* # blocks in partition map */
+	__be32	start_block;	/* absolute starting block # of partition */
+	__be32	block_count;	/* number of blocks in partition */
+	char	name[32];	/* partition name */
+	char	type[32];	/* string type description */
+	__be32	data_start;	/* rel block # of first data block */
+	__be32	data_count;	/* number of data blocks */
+	__be32	status;		/* partition status bits */
+	__be32	boot_start;
+	__be32	boot_size;
+	__be32	boot_load;
+	__be32	boot_load2;
+	__be32	boot_entry;
+	__be32	boot_entry2;
+	__be32	boot_cksum;
+	char	processor[16];	/* identifies ISA of boot */
+	/* there is more stuff after this that we don't need */
+};
+
+#define MAC_STATUS_BOOTABLE	8	/* partition is bootable */
+
+#define MAC_DRIVER_MAGIC	0x4552
+
+/* Driver descriptor structure, in block 0 */
+struct mac_driver_desc {
+	__be16	signature;	/* expected to be MAC_DRIVER_MAGIC */
+	__be16	block_size;
+	__be32	block_count;
+    /* ... more stuff */
+};
+