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, 99 insertions, 0 deletions

diff --git a/crypto/lz4.c b/crypto/lz4.c
new file mode 100644
index 000000000..57b713516
--- /dev/null
+++ b/crypto/lz4.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2013 Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/vmalloc.h>
+#include <linux/lz4.h>
+#include <crypto/internal/scompress.h>
+
+static void *lz4_alloc_ctx(void)
+{
+	void *ctx;
+
+	ctx = vmalloc(LZ4_MEM_COMPRESS);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	return ctx;
+}
+
+static void lz4_free_ctx(void *ctx)
+{
+	vfree(ctx);
+}
+
+static int __lz4_compress_crypto(const u8 *src, unsigned int slen,
+				 u8 *dst, unsigned int *dlen, void *ctx)
+{
+	int out_len = LZ4_compress_default(src, dst,
+		slen, *dlen, ctx);
+
+	if (!out_len)
+		return -EINVAL;
+
+	*dlen = out_len;
+	return 0;
+}
+
+static int lz4_scompress(struct crypto_scomp *tfm, const u8 *src,
+			 unsigned int slen, u8 *dst, unsigned int *dlen,
+			 void *ctx)
+{
+	return __lz4_compress_crypto(src, slen, dst, dlen, ctx);
+}
+
+static int __lz4_decompress_crypto(const u8 *src, unsigned int slen,
+				   u8 *dst, unsigned int *dlen, void *ctx)
+{
+	int out_len = LZ4_decompress_safe(src, dst, slen, *dlen);
+
+	if (out_len < 0)
+		return -EINVAL;
+
+	*dlen = out_len;
+	return 0;
+}
+
+static int lz4_sdecompress(struct crypto_scomp *tfm, const u8 *src,
+			   unsigned int slen, u8 *dst, unsigned int *dlen,
+			   void *ctx)
+{
+	return __lz4_decompress_crypto(src, slen, dst, dlen, NULL);
+}
+
+static struct scomp_alg scomp = {
+	.streams		= {
+		.alloc_ctx	= lz4_alloc_ctx,
+		.free_ctx	= lz4_free_ctx,
+	},
+	.compress		= lz4_scompress,
+	.decompress		= lz4_sdecompress,
+	.base			= {
+		.cra_name	= "lz4",
+		.cra_driver_name = "lz4-scomp",
+		.cra_module	 = THIS_MODULE,
+	}
+};
+
+static int __init lz4_mod_init(void)
+{
+	return crypto_register_scomp(&scomp);
+}
+
+static void __exit lz4_mod_fini(void)
+{
+	crypto_unregister_scomp(&scomp);
+}
+
+module_init(lz4_mod_init);
+module_exit(lz4_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4");