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, 113 insertions, 0 deletions

diff --git a/net/mac80211/aead_api.c b/net/mac80211/aead_api.c
new file mode 100644
index 000000000..b00d6f5b3
--- /dev/null
+++ b/net/mac80211/aead_api.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2003-2004, Instant802 Networks, Inc.
+ * Copyright 2005-2006, Devicescape Software, Inc.
+ * Copyright 2014-2015, Qualcomm Atheros, Inc.
+ *
+ * Rewrite: Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/scatterlist.h>
+#include <crypto/aead.h>
+
+#include "aead_api.h"
+
+int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
+		 u8 *data, size_t data_len, u8 *mic)
+{
+	size_t mic_len = crypto_aead_authsize(tfm);
+	struct scatterlist sg[3];
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+	u8 *__aad;
+	int ret;
+
+	aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
+
+	__aad = (u8 *)aead_req + reqsize;
+	memcpy(__aad, aad, aad_len);
+
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], __aad, aad_len);
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, mic_len);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_crypt(aead_req, sg, sg, data_len, b_0);
+	aead_request_set_ad(aead_req, sg[0].length);
+
+	ret = crypto_aead_encrypt(aead_req);
+	kfree_sensitive(aead_req);
+
+	return ret;
+}
+
+int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
+		 u8 *data, size_t data_len, u8 *mic)
+{
+	size_t mic_len = crypto_aead_authsize(tfm);
+	struct scatterlist sg[3];
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+	u8 *__aad;
+	int err;
+
+	if (data_len == 0)
+		return -EINVAL;
+
+	aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
+
+	__aad = (u8 *)aead_req + reqsize;
+	memcpy(__aad, aad, aad_len);
+
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], __aad, aad_len);
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, mic_len);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_crypt(aead_req, sg, sg, data_len + mic_len, b_0);
+	aead_request_set_ad(aead_req, sg[0].length);
+
+	err = crypto_aead_decrypt(aead_req);
+	kfree_sensitive(aead_req);
+
+	return err;
+}
+
+struct crypto_aead *
+aead_key_setup_encrypt(const char *alg, const u8 key[],
+		       size_t key_len, size_t mic_len)
+{
+	struct crypto_aead *tfm;
+	int err;
+
+	tfm = crypto_alloc_aead(alg, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return tfm;
+
+	err = crypto_aead_setkey(tfm, key, key_len);
+	if (err)
+		goto free_aead;
+	err = crypto_aead_setauthsize(tfm, mic_len);
+	if (err)
+		goto free_aead;
+
+	return tfm;
+
+free_aead:
+	crypto_free_aead(tfm);
+	return ERR_PTR(err);
+}
+
+void aead_key_free(struct crypto_aead *tfm)
+{
+	crypto_free_aead(tfm);
+}