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, 94 insertions, 0 deletions

diff --git a/drivers/crypto/qce/common.h b/drivers/crypto/qce/common.h
new file mode 100644
index 000000000..9cd2e6ed8
--- /dev/null
+++ b/drivers/crypto/qce/common.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _COMMON_H_
+#define _COMMON_H_
+
+#include <linux/crypto.h>
+#include <linux/types.h>
+#include <crypto/aes.h>
+#include <crypto/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/internal/aead.h>
+
+/* xts du size */
+#define QCE_SECTOR_SIZE			512
+
+/* key size in bytes */
+#define QCE_SHA_HMAC_KEY_SIZE		64
+#define QCE_MAX_CIPHER_KEY_SIZE		AES_KEYSIZE_256
+
+/* IV length in bytes */
+#define QCE_AES_IV_LENGTH		AES_BLOCK_SIZE
+/* max of AES_BLOCK_SIZE */
+#define QCE_MAX_IV_SIZE			AES_BLOCK_SIZE
+
+/* maximum nonce bytes  */
+#define QCE_MAX_NONCE			16
+#define QCE_MAX_NONCE_WORDS		(QCE_MAX_NONCE / sizeof(u32))
+
+/* burst size alignment requirement */
+#define QCE_MAX_ALIGN_SIZE		64
+
+/* cipher algorithms */
+#define QCE_ALG_AES			BIT(2)
+
+/* hash and hmac algorithms */
+#define QCE_HASH_SHA256			BIT(4)
+#define QCE_HASH_SHA256_HMAC		BIT(6)
+#define QCE_HASH_AES_CMAC		BIT(7)
+
+/* cipher modes */
+#define QCE_MODE_CBC			BIT(8)
+#define QCE_MODE_ECB			BIT(9)
+#define QCE_MODE_CTR			BIT(10)
+#define QCE_MODE_XTS			BIT(11)
+#define QCE_MODE_CCM			BIT(12)
+#define QCE_MODE_MASK			GENMASK(12, 8)
+
+#define QCE_MODE_CCM_RFC4309		BIT(13)
+
+/* cipher encryption/decryption operations */
+#define QCE_ENCRYPT			BIT(30)
+#define QCE_DECRYPT			BIT(31)
+
+#define IS_AES(flags)			(flags & QCE_ALG_AES)
+
+#define IS_SHA256(flags)		(flags & QCE_HASH_SHA256)
+#define IS_SHA256_HMAC(flags)		(flags & QCE_HASH_SHA256_HMAC)
+#define IS_CMAC(flags)			(flags & QCE_HASH_AES_CMAC)
+#define IS_SHA(flags)			IS_SHA256(flags)
+#define IS_SHA_HMAC(flags)		IS_SHA256_HMAC(flags)
+
+#define IS_CBC(mode)			(mode & QCE_MODE_CBC)
+#define IS_CTR(mode)			(mode & QCE_MODE_CTR)
+#define IS_XTS(mode)			(mode & QCE_MODE_XTS)
+#define IS_CCM(mode)			(mode & QCE_MODE_CCM)
+#define IS_CCM_RFC4309(mode)		((mode) & QCE_MODE_CCM_RFC4309)
+
+#define IS_ENCRYPT(dir)			(dir & QCE_ENCRYPT)
+#define IS_DECRYPT(dir)			(dir & QCE_DECRYPT)
+
+struct qce_alg_template {
+	struct list_head entry;
+	u32 crypto_alg_type;
+	unsigned long alg_flags;
+	const u32 *std_iv;
+	union {
+		struct skcipher_alg skcipher;
+		struct ahash_alg ahash;
+		struct aead_alg aead;
+	} alg;
+	struct qce_device *qce;
+	const u8 *hash_zero;
+	const u32 digest_size;
+};
+
+void qce_cpu_to_be32p_array(__be32 *dst, const u8 *src, unsigned int len);
+int qce_check_status(struct qce_device *qce, u32 *status);
+void qce_get_version(struct qce_device *qce, u32 *major, u32 *minor, u32 *step);
+int qce_start(struct crypto_async_request *async_req, u32 type);
+
+#endif /* _COMMON_H_ */