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, 243 insertions, 0 deletions

diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
new file mode 100644
index 000000000..2c7a04465
--- /dev/null
+++ b/block/blk-crypto-internal.h
@@ -0,0 +1,243 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_BLK_CRYPTO_INTERNAL_H
+#define __LINUX_BLK_CRYPTO_INTERNAL_H
+
+#include <linux/bio.h>
+#include <linux/blk-mq.h>
+
+/* Represents a crypto mode supported by blk-crypto  */
+struct blk_crypto_mode {
+	const char *name; /* name of this mode, shown in sysfs */
+	const char *cipher_str; /* crypto API name (for fallback case) */
+	unsigned int keysize; /* key size in bytes */
+	unsigned int security_strength; /* security strength in bytes */
+	unsigned int ivsize; /* iv size in bytes */
+};
+
+extern const struct blk_crypto_mode blk_crypto_modes[];
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+int blk_crypto_sysfs_register(struct gendisk *disk);
+
+void blk_crypto_sysfs_unregister(struct gendisk *disk);
+
+void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
+			     unsigned int inc);
+
+bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio);
+
+bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes,
+			     struct bio_crypt_ctx *bc2);
+
+static inline bool bio_crypt_ctx_back_mergeable(struct request *req,
+						struct bio *bio)
+{
+	return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req),
+				       bio->bi_crypt_context);
+}
+
+static inline bool bio_crypt_ctx_front_mergeable(struct request *req,
+						 struct bio *bio)
+{
+	return bio_crypt_ctx_mergeable(bio->bi_crypt_context,
+				       bio->bi_iter.bi_size, req->crypt_ctx);
+}
+
+static inline bool bio_crypt_ctx_merge_rq(struct request *req,
+					  struct request *next)
+{
+	return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req),
+				       next->crypt_ctx);
+}
+
+static inline void blk_crypto_rq_set_defaults(struct request *rq)
+{
+	rq->crypt_ctx = NULL;
+	rq->crypt_keyslot = NULL;
+}
+
+static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
+{
+	return rq->crypt_ctx;
+}
+
+static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
+{
+	return rq->crypt_keyslot;
+}
+
+blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
+				    const struct blk_crypto_key *key,
+				    struct blk_crypto_keyslot **slot_ptr);
+
+void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot);
+
+int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
+			   const struct blk_crypto_key *key);
+
+int blk_crypto_ioctl(struct block_device *bdev, unsigned int cmd,
+		     void __user *argp);
+
+static inline bool blk_crypto_supported(struct bio *bio)
+{
+	return blk_crypto_config_supported_natively(bio->bi_bdev,
+			&bio->bi_crypt_context->bc_key->crypto_cfg);
+}
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline int blk_crypto_sysfs_register(struct gendisk *disk)
+{
+	return 0;
+}
+
+static inline void blk_crypto_sysfs_unregister(struct gendisk *disk)
+{
+}
+
+static inline bool bio_crypt_rq_ctx_compatible(struct request *rq,
+					       struct bio *bio)
+{
+	return true;
+}
+
+static inline bool bio_crypt_ctx_front_mergeable(struct request *req,
+						 struct bio *bio)
+{
+	return true;
+}
+
+static inline bool bio_crypt_ctx_back_mergeable(struct request *req,
+						struct bio *bio)
+{
+	return true;
+}
+
+static inline bool bio_crypt_ctx_merge_rq(struct request *req,
+					  struct request *next)
+{
+	return true;
+}
+
+static inline void blk_crypto_rq_set_defaults(struct request *rq) { }
+
+static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
+{
+	return false;
+}
+
+static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
+{
+	return false;
+}
+
+static inline int blk_crypto_ioctl(struct block_device *bdev, unsigned int cmd,
+				   void __user *argp)
+{
+	return -ENOTTY;
+}
+
+static inline bool blk_crypto_supported(struct bio *bio)
+{
+	return false;
+}
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+void __bio_crypt_advance(struct bio *bio, unsigned int bytes);
+static inline void bio_crypt_advance(struct bio *bio, unsigned int bytes)
+{
+	if (bio_has_crypt_ctx(bio))
+		__bio_crypt_advance(bio, bytes);
+}
+
+void __bio_crypt_free_ctx(struct bio *bio);
+static inline void bio_crypt_free_ctx(struct bio *bio)
+{
+	if (bio_has_crypt_ctx(bio))
+		__bio_crypt_free_ctx(bio);
+}
+
+static inline void bio_crypt_do_front_merge(struct request *rq,
+					    struct bio *bio)
+{
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	if (bio_has_crypt_ctx(bio))
+		memcpy(rq->crypt_ctx->bc_dun, bio->bi_crypt_context->bc_dun,
+		       sizeof(rq->crypt_ctx->bc_dun));
+#endif
+}
+
+blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq);
+static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq)
+{
+	if (blk_crypto_rq_is_encrypted(rq))
+		return __blk_crypto_rq_get_keyslot(rq);
+	return BLK_STS_OK;
+}
+
+void __blk_crypto_rq_put_keyslot(struct request *rq);
+static inline void blk_crypto_rq_put_keyslot(struct request *rq)
+{
+	if (blk_crypto_rq_has_keyslot(rq))
+		__blk_crypto_rq_put_keyslot(rq);
+}
+
+void __blk_crypto_free_request(struct request *rq);
+static inline void blk_crypto_free_request(struct request *rq)
+{
+	if (blk_crypto_rq_is_encrypted(rq))
+		__blk_crypto_free_request(rq);
+}
+
+int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+			     gfp_t gfp_mask);
+/**
+ * blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio
+ *			    is inserted
+ * @rq: The request to prepare
+ * @bio: The first bio being inserted into the request
+ * @gfp_mask: Memory allocation flags
+ *
+ * Return: 0 on success, -ENOMEM if out of memory.  -ENOMEM is only possible if
+ *	   @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM.
+ */
+static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+					 gfp_t gfp_mask)
+{
+	if (bio_has_crypt_ctx(bio))
+		return __blk_crypto_rq_bio_prep(rq, bio, gfp_mask);
+	return 0;
+}
+
+bool blk_crypto_fallback_bio_prep(struct bio *bio);
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK
+
+int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num);
+
+int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key);
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */
+
+static inline int
+blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num)
+{
+	pr_warn_once("crypto API fallback is disabled\n");
+	return -ENOPKG;
+}
+
+static inline int
+blk_crypto_fallback_evict_key(const struct blk_crypto_key *key)
+{
+	return 0;
+}
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */
+
+#endif /* __LINUX_BLK_CRYPTO_INTERNAL_H */