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, 79 insertions, 0 deletions

diff --git a/crypto/aegis.h b/crypto/aegis.h
new file mode 100644
index 000000000..ffcf8e85e
--- /dev/null
+++ b/crypto/aegis.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * AEGIS common definitions
+ *
+ * Copyright (c) 2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (c) 2018 Red Hat, Inc. All rights reserved.
+ */
+
+#ifndef _CRYPTO_AEGIS_H
+#define _CRYPTO_AEGIS_H
+
+#include <crypto/aes.h>
+#include <linux/bitops.h>
+#include <linux/types.h>
+
+#define AEGIS_BLOCK_SIZE 16
+
+union aegis_block {
+	__le64 words64[AEGIS_BLOCK_SIZE / sizeof(__le64)];
+	__le32 words32[AEGIS_BLOCK_SIZE / sizeof(__le32)];
+	u8 bytes[AEGIS_BLOCK_SIZE];
+};
+
+struct aegis_state;
+
+extern int aegis128_have_aes_insn;
+
+#define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block))
+#define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN)
+
+bool crypto_aegis128_have_simd(void);
+void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg);
+void crypto_aegis128_init_simd(struct aegis_state *state,
+			       const union aegis_block *key,
+			       const u8 *iv);
+void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
+					const u8 *src, unsigned int size);
+void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
+					const u8 *src, unsigned int size);
+int crypto_aegis128_final_simd(struct aegis_state *state,
+			       union aegis_block *tag_xor,
+			       unsigned int assoclen,
+			       unsigned int cryptlen,
+			       unsigned int authsize);
+
+static __always_inline void crypto_aegis_block_xor(union aegis_block *dst,
+						   const union aegis_block *src)
+{
+	dst->words64[0] ^= src->words64[0];
+	dst->words64[1] ^= src->words64[1];
+}
+
+static __always_inline void crypto_aegis_block_and(union aegis_block *dst,
+						   const union aegis_block *src)
+{
+	dst->words64[0] &= src->words64[0];
+	dst->words64[1] &= src->words64[1];
+}
+
+static __always_inline void crypto_aegis_aesenc(union aegis_block *dst,
+						const union aegis_block *src,
+						const union aegis_block *key)
+{
+	const u8  *s  = src->bytes;
+	const u32 *t = aes_enc_tab;
+	u32 d0, d1, d2, d3;
+
+	d0 = t[s[ 0]] ^ rol32(t[s[ 5]], 8) ^ rol32(t[s[10]], 16) ^ rol32(t[s[15]], 24);
+	d1 = t[s[ 4]] ^ rol32(t[s[ 9]], 8) ^ rol32(t[s[14]], 16) ^ rol32(t[s[ 3]], 24);
+	d2 = t[s[ 8]] ^ rol32(t[s[13]], 8) ^ rol32(t[s[ 2]], 16) ^ rol32(t[s[ 7]], 24);
+	d3 = t[s[12]] ^ rol32(t[s[ 1]], 8) ^ rol32(t[s[ 6]], 16) ^ rol32(t[s[11]], 24);
+
+	dst->words32[0] = cpu_to_le32(d0) ^ key->words32[0];
+	dst->words32[1] = cpu_to_le32(d1) ^ key->words32[1];
+	dst->words32[2] = cpu_to_le32(d2) ^ key->words32[2];
+	dst->words32[3] = cpu_to_le32(d3) ^ key->words32[3];
+}
+
+#endif /* _CRYPTO_AEGIS_H */