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, 118 insertions, 0 deletions

diff --git a/drivers/md/dm-ima.h b/drivers/md/dm-ima.h
new file mode 100644
index 000000000..0ec013d15
--- /dev/null
+++ b/drivers/md/dm-ima.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Microsoft Corporation
+ *
+ * Author: Tushar Sugandhi <tusharsu@linux.microsoft.com>
+ *
+ * Header file for device mapper IMA measurements.
+ */
+
+#ifndef DM_IMA_H
+#define DM_IMA_H
+
+#define DM_IMA_MEASUREMENT_BUF_LEN	4096
+#define DM_IMA_DEVICE_BUF_LEN		1024
+#define DM_IMA_TARGET_METADATA_BUF_LEN	128
+#define DM_IMA_TARGET_DATA_BUF_LEN	2048
+#define DM_IMA_DEVICE_CAPACITY_BUF_LEN	128
+
+#define __dm_ima_stringify(s) #s
+#define __dm_ima_str(s) __dm_ima_stringify(s)
+
+#define DM_IMA_VERSION_STR "dm_version="	\
+	__dm_ima_str(DM_VERSION_MAJOR) "."	\
+	__dm_ima_str(DM_VERSION_MINOR) "."	\
+	__dm_ima_str(DM_VERSION_PATCHLEVEL) ";"
+
+enum dm_ima_table_op {
+	DM_IMA_TABLE_SAVE,
+	DM_IMA_TABLE_RESTORE,
+};
+
+#ifdef CONFIG_IMA
+
+struct dm_ima_device_table_metadata {
+	/*
+	 * Contains data specific to the device which is common across
+	 * all the targets in the table (e.g. name, uuid, major, minor, etc).
+	 * The values are stored in comma separated list of key1=val1,key2=val2;
+	 * pairs delimited by a semicolon at the end of the list.
+	 */
+	char *device_metadata;
+	unsigned int device_metadata_len;
+	unsigned int num_targets;
+	sector_t capacity;
+
+	/*
+	 * Contains the sha256 hashes of the IMA measurements of the target
+	 * attributes' key-value pairs from the active/inactive tables.
+	 */
+	char *hash;
+	unsigned int hash_len;
+};
+
+struct dm_ima_context {
+	struct dm_ima_device_table_metadata table;
+	unsigned int update_idx;
+	char dev_name[DM_NAME_LEN*2];
+	char dev_uuid[DM_UUID_LEN*2];
+};
+
+/*
+ * This structure contains device metadata, and table hash for
+ * active and inactive tables for ima measurements.
+ */
+struct dm_ima_measurements {
+	unsigned int update_idx;
+	unsigned int measure_idx;
+	struct wait_queue_head ima_wq;
+	spinlock_t ima_lock;
+	struct dm_ima_device_table_metadata active_table;
+	struct dm_ima_device_table_metadata inactive_table;
+};
+
+void dm_ima_init(struct mapped_device *md);
+void dm_ima_alloc_context(struct dm_ima_context **context, bool noio);
+void dm_ima_free_context(struct dm_ima_context *context);
+void dm_ima_context_table_op(struct mapped_device *md,
+			     struct dm_ima_context *context,
+			     enum dm_ima_table_op op);
+void dm_ima_measure_on_table_load(struct dm_table *table,
+				  struct dm_ima_context *context);
+void dm_ima_measure_on_device_resume(struct mapped_device *md, bool swap,
+				     struct dm_ima_context *context);
+void dm_ima_measure_on_device_remove(struct mapped_device *md, bool remove_all,
+				     struct dm_ima_context *context,
+				     unsigned int idx);
+void dm_ima_measure_on_table_clear(struct mapped_device *md,
+				   struct dm_ima_context *context);
+void dm_ima_measure_on_device_rename(struct mapped_device *md,
+				     struct dm_ima_context *context);
+
+#else
+
+struct dm_ima_context;
+
+static inline void dm_ima_init(struct mapped_device *md) {}
+static inline void dm_ima_alloc_context(struct dm_ima_context **context, bool noio) {}
+static inline void dm_ima_free_context(struct dm_ima_context *context) {}
+static inline void dm_ima_context_table_op(struct mapped_device *md,
+					   struct dm_ima_context *context,
+					   enum dm_ima_table_op op) {}
+static inline void dm_ima_measure_on_table_load(struct dm_table *table,
+						struct dm_ima_context *context) {}
+static inline void dm_ima_measure_on_device_resume(struct mapped_device *md,
+						   bool swap,
+						   struct dm_ima_context *context) {}
+static inline void dm_ima_measure_on_device_remove(struct mapped_device *md,
+						   bool remove_all,
+						   struct dm_ima_context *context,
+						   unsigned int idx) {}
+static inline void dm_ima_measure_on_table_clear(struct mapped_device *md,
+						 struct dm_ima_context *context) {}
+static inline void dm_ima_measure_on_device_rename(struct mapped_device *md,
+						   struct dm_ima_context *context) {}
+
+#endif /* CONFIG_IMA */
+
+#endif /* DM_IMA_H */