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, 101 insertions, 0 deletions

diff --git a/crypto/lzo.c b/crypto/lzo.c
new file mode 100644
index 000000000..d43242b24
--- /dev/null
+++ b/crypto/lzo.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Cryptographic API.
+ */
+
+#include <crypto/internal/scompress.h>
+#include <linux/init.h>
+#include <linux/lzo.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+static void *lzo_alloc_ctx(void)
+{
+	void *ctx;
+
+	ctx = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	return ctx;
+}
+
+static void lzo_free_ctx(void *ctx)
+{
+	kvfree(ctx);
+}
+
+static int __lzo_compress(const u8 *src, unsigned int slen,
+			  u8 *dst, unsigned int *dlen, void *ctx)
+{
+	size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */
+	int err;
+
+	err = lzo1x_1_compress_safe(src, slen, dst, &tmp_len, ctx);
+
+	if (err != LZO_E_OK)
+		return -EINVAL;
+
+	*dlen = tmp_len;
+	return 0;
+}
+
+static int lzo_scompress(struct crypto_scomp *tfm, const u8 *src,
+			 unsigned int slen, u8 *dst, unsigned int *dlen,
+			 void *ctx)
+{
+	return __lzo_compress(src, slen, dst, dlen, ctx);
+}
+
+static int __lzo_decompress(const u8 *src, unsigned int slen,
+			    u8 *dst, unsigned int *dlen)
+{
+	int err;
+	size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */
+
+	err = lzo1x_decompress_safe(src, slen, dst, &tmp_len);
+
+	if (err != LZO_E_OK)
+		return -EINVAL;
+
+	*dlen = tmp_len;
+	return 0;
+}
+
+static int lzo_sdecompress(struct crypto_scomp *tfm, const u8 *src,
+			   unsigned int slen, u8 *dst, unsigned int *dlen,
+			   void *ctx)
+{
+	return __lzo_decompress(src, slen, dst, dlen);
+}
+
+static struct scomp_alg scomp = {
+	.streams		= {
+		.alloc_ctx	= lzo_alloc_ctx,
+		.free_ctx	= lzo_free_ctx,
+	},
+	.compress		= lzo_scompress,
+	.decompress		= lzo_sdecompress,
+	.base			= {
+		.cra_name	= "lzo",
+		.cra_driver_name = "lzo-scomp",
+		.cra_module	 = THIS_MODULE,
+	}
+};
+
+static int __init lzo_mod_init(void)
+{
+	return crypto_register_scomp(&scomp);
+}
+
+static void __exit lzo_mod_fini(void)
+{
+	crypto_unregister_scomp(&scomp);
+}
+
+module_init(lzo_mod_init);
+module_exit(lzo_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZO Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lzo");