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/tcrypt.h b/crypto/tcrypt.h
new file mode 100644
index 000000000..85c3f77bc
--- /dev/null
+++ b/crypto/tcrypt.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Quick & dirty crypto benchmarking module.
+ *
+ * This will only exist until we have a better benchmarking mechanism
+ * (e.g. a char device).
+ *
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ * Copyright (c) 2002 Jean-Francois Dive <jef@linuxbe.org>
+ * Copyright (c) 2007 Nokia Siemens Networks
+ */
+#ifndef _CRYPTO_TCRYPT_H
+#define _CRYPTO_TCRYPT_H
+
+struct cipher_speed_template {
+	const char *key;
+	unsigned int klen;
+};
+
+struct aead_speed_template {
+	const char *key;
+	unsigned int klen;
+};
+
+struct hash_speed {
+	unsigned int blen;	/* buffer length */
+	unsigned int plen;	/* per-update length */
+};
+
+/*
+ * DES test vectors.
+ */
+#define DES3_SPEED_VECTORS	1
+
+static struct cipher_speed_template des3_speed_template[] = {
+	{
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\x55\x55\x55\x55\x55\x55\x55\x55"
+			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.klen	= 24,
+	}
+};
+
+/*
+ * Cipher speed tests
+ */
+static u8 speed_template_8[] = {8, 0};
+static u8 speed_template_16[] = {16, 0};
+static u8 speed_template_24[] = {24, 0};
+static u8 speed_template_8_16[] = {8, 16, 0};
+static u8 speed_template_8_32[] = {8, 32, 0};
+static u8 speed_template_16_32[] = {16, 32, 0};
+static u8 speed_template_16_24_32[] = {16, 24, 32, 0};
+static u8 speed_template_20_28_36[] = {20, 28, 36, 0};
+static u8 speed_template_32_40_48[] = {32, 40, 48, 0};
+static u8 speed_template_32_48[] = {32, 48, 0};
+static u8 speed_template_32_48_64[] = {32, 48, 64, 0};
+static u8 speed_template_32_64[] = {32, 64, 0};
+static u8 speed_template_32[] = {32, 0};
+
+/*
+ * AEAD speed tests
+ */
+static u8 aead_speed_template_19[] = {19, 0};
+static u8 aead_speed_template_20_28_36[] = {20, 28, 36, 0};
+static u8 aead_speed_template_36[] = {36, 0};
+
+/*
+ * Digest speed tests
+ */
+static struct hash_speed generic_hash_speed_template[] = {
+	{ .blen = 16,	.plen = 16, },
+	{ .blen = 64,	.plen = 16, },
+	{ .blen = 64,	.plen = 64, },
+	{ .blen = 256,	.plen = 16, },
+	{ .blen = 256,	.plen = 64, },
+	{ .blen = 256,	.plen = 256, },
+	{ .blen = 1024,	.plen = 16, },
+	{ .blen = 1024,	.plen = 256, },
+	{ .blen = 1024,	.plen = 1024, },
+	{ .blen = 2048,	.plen = 16, },
+	{ .blen = 2048,	.plen = 256, },
+	{ .blen = 2048,	.plen = 1024, },
+	{ .blen = 2048,	.plen = 2048, },
+	{ .blen = 4096,	.plen = 16, },
+	{ .blen = 4096,	.plen = 256, },
+	{ .blen = 4096,	.plen = 1024, },
+	{ .blen = 4096,	.plen = 4096, },
+	{ .blen = 8192,	.plen = 16, },
+	{ .blen = 8192,	.plen = 256, },
+	{ .blen = 8192,	.plen = 1024, },
+	{ .blen = 8192,	.plen = 4096, },
+	{ .blen = 8192,	.plen = 8192, },
+
+	/* End marker */
+	{  .blen = 0,	.plen = 0, }
+};
+
+#endif	/* _CRYPTO_TCRYPT_H */