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, 175 insertions, 0 deletions

diff --git a/crypto/chacha.c b/crypto/chacha.c
new file mode 100644
index 000000000..ec16d5a33
--- /dev/null
+++ b/crypto/chacha.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Crypto API wrappers for the ChaCha20, XChaCha20, and XChaCha12 stream ciphers
+ *
+ * Copyright (C) 2015 Martin Willi
+ * Copyright (C) 2018 Google LLC
+ */
+
+#include <linux/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/chacha.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/module.h>
+
+struct chacha_ctx {
+	u32 key[8];
+	int nrounds;
+};
+
+static int chacha_setkey(struct crypto_skcipher *tfm,
+			 const u8 *key, unsigned int keysize, int nrounds)
+{
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int i;
+
+	if (keysize != CHACHA_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+		ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
+
+	ctx->nrounds = nrounds;
+	return 0;
+}
+
+static int chacha20_setkey(struct crypto_skcipher *tfm,
+			   const u8 *key, unsigned int keysize)
+{
+	return chacha_setkey(tfm, key, keysize, 20);
+}
+
+static int chacha12_setkey(struct crypto_skcipher *tfm,
+			   const u8 *key, unsigned int keysize)
+{
+	return chacha_setkey(tfm, key, keysize, 12);
+}
+
+static int chacha_stream_xor(struct skcipher_request *req,
+			     const struct chacha_ctx *ctx,
+			     const u8 iv[CHACHA_IV_SIZE])
+{
+	struct skcipher_walk walk;
+	struct chacha_state state;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	chacha_init(&state, ctx->key, iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE);
+
+		chacha_crypt(&state, walk.dst.virt.addr, walk.src.virt.addr,
+			     nbytes, ctx->nrounds);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	return err;
+}
+
+static int crypto_chacha_crypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return chacha_stream_xor(req, ctx, req->iv);
+}
+
+static int crypto_xchacha_crypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct chacha_ctx subctx;
+	struct chacha_state state;
+	u8 real_iv[16];
+
+	/* Compute the subkey given the original key and first 128 nonce bits */
+	chacha_init(&state, ctx->key, req->iv);
+	hchacha_block(&state, subctx.key, ctx->nrounds);
+	subctx.nrounds = ctx->nrounds;
+
+	/* Build the real IV */
+	memcpy(&real_iv[0], req->iv + 24, 8); /* stream position */
+	memcpy(&real_iv[8], req->iv + 16, 8); /* remaining 64 nonce bits */
+
+	/* Generate the stream and XOR it with the data */
+	return chacha_stream_xor(req, &subctx, real_iv);
+}
+
+static struct skcipher_alg algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-lib",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= crypto_chacha_crypt,
+		.decrypt		= crypto_chacha_crypt,
+	},
+	{
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-lib",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= crypto_xchacha_crypt,
+		.decrypt		= crypto_xchacha_crypt,
+	},
+	{
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-lib",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha12_setkey,
+		.encrypt		= crypto_xchacha_crypt,
+		.decrypt		= crypto_xchacha_crypt,
+	}
+};
+
+static int __init crypto_chacha_mod_init(void)
+{
+	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit crypto_chacha_mod_fini(void)
+{
+	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+module_init(crypto_chacha_mod_init);
+module_exit(crypto_chacha_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("Crypto API wrappers for the ChaCha20, XChaCha20, and XChaCha12 stream ciphers");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-lib");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-lib");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-lib");