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, 35 insertions, 0 deletions

diff --git a/crypto/jitterentropy.h b/crypto/jitterentropy.h
new file mode 100644
index 000000000..5bb15cb33
--- /dev/null
+++ b/crypto/jitterentropy.h
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+struct sha3_ctx;
+extern void *jent_kvzalloc(unsigned int len);
+extern void jent_kvzfree(void *ptr, unsigned int len);
+extern void *jent_zalloc(unsigned int len);
+extern void jent_zfree(void *ptr);
+extern void jent_get_nstime(__u64 *out);
+void jent_hash_time(struct sha3_ctx *hash_state, __u64 time, u8 *addtl,
+		    unsigned int addtl_len, __u64 hash_loop_cnt,
+		    unsigned int stuck);
+void jent_read_random_block(struct sha3_ctx *hash_state, char *dst,
+			    unsigned int dst_len);
+
+struct rand_data;
+extern int jent_entropy_init(unsigned int osr, unsigned int flags,
+			     struct sha3_ctx *hash_state,
+			     struct rand_data *p_ec);
+extern int jent_read_entropy(struct rand_data *ec, unsigned char *data,
+			     unsigned int len);
+
+extern struct rand_data *
+jent_entropy_collector_alloc(unsigned int osr, unsigned int flags,
+			     struct sha3_ctx *hash_state);
+extern void jent_entropy_collector_free(struct rand_data *entropy_collector);
+
+#ifdef CONFIG_CRYPTO_JITTERENTROPY_TESTINTERFACE
+int jent_raw_hires_entropy_store(__u64 value);
+void jent_testing_init(void);
+void jent_testing_exit(void);
+#else /* CONFIG_CRYPTO_JITTERENTROPY_TESTINTERFACE */
+static inline int jent_raw_hires_entropy_store(__u64 value) { return 0; }
+static inline void jent_testing_init(void) { }
+static inline void jent_testing_exit(void) { }
+#endif /* CONFIG_CRYPTO_JITTERENTROPY_TESTINTERFACE */