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, 113 insertions, 0 deletions

diff --git a/drivers/crypto/bcm/util.h b/drivers/crypto/bcm/util.h
new file mode 100644
index 000000000..61c256384
--- /dev/null
+++ b/drivers/crypto/bcm/util.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2016 Broadcom
+ */
+
+#ifndef _UTIL_H
+#define _UTIL_H
+
+#include <linux/kernel.h>
+#include <linux/delay.h>
+
+#include "spu.h"
+
+extern int flow_debug_logging;
+extern int packet_debug_logging;
+extern int debug_logging_sleep;
+
+#ifdef DEBUG
+#define flow_log(...)	                \
+	do {	                              \
+		if (flow_debug_logging) {	        \
+			printk(__VA_ARGS__);	          \
+			if (debug_logging_sleep)	      \
+				msleep(debug_logging_sleep);	\
+		}	                                \
+	} while (0)
+#define flow_dump(msg, var, var_len)	   \
+	do {	                                 \
+		if (flow_debug_logging) {	           \
+			print_hex_dump(KERN_ALERT, msg, DUMP_PREFIX_NONE,  \
+					16, 1, var, var_len, false); \
+				if (debug_logging_sleep)	       \
+					msleep(debug_logging_sleep);   \
+		}                                    \
+	} while (0)
+
+#define packet_log(...)               \
+	do {                                \
+		if (packet_debug_logging) {       \
+			printk(__VA_ARGS__);            \
+			if (debug_logging_sleep)        \
+				msleep(debug_logging_sleep);  \
+		}                                 \
+	} while (0)
+#define packet_dump(msg, var, var_len)   \
+	do {                                   \
+		if (packet_debug_logging) {          \
+			print_hex_dump(KERN_ALERT, msg, DUMP_PREFIX_NONE,  \
+					16, 1, var, var_len, false); \
+			if (debug_logging_sleep)           \
+				msleep(debug_logging_sleep);     \
+		}                                    \
+	} while (0)
+
+void __dump_sg(struct scatterlist *sg, unsigned int skip, unsigned int len);
+
+#define dump_sg(sg, skip, len)     __dump_sg(sg, skip, len)
+
+#else /* !DEBUG_ON */
+
+static inline void flow_log(const char *format, ...)
+{
+}
+
+static inline void flow_dump(const char *msg, const void *var, size_t var_len)
+{
+}
+
+static inline void packet_log(const char *format, ...)
+{
+}
+
+static inline void packet_dump(const char *msg, const void *var, size_t var_len)
+{
+}
+
+static inline void dump_sg(struct scatterlist *sg, unsigned int skip,
+			   unsigned int len)
+{
+}
+
+#endif /* DEBUG_ON */
+
+int spu_sg_at_offset(struct scatterlist *sg, unsigned int skip,
+		     struct scatterlist **sge, unsigned int *sge_offset);
+
+/* Copy sg data, from skip, length len, to dest */
+void sg_copy_part_to_buf(struct scatterlist *src, u8 *dest,
+			 unsigned int len, unsigned int skip);
+/* Copy src into scatterlist from offset, length len */
+void sg_copy_part_from_buf(struct scatterlist *dest, u8 *src,
+			   unsigned int len, unsigned int skip);
+
+int spu_sg_count(struct scatterlist *sg_list, unsigned int skip, int nbytes);
+u32 spu_msg_sg_add(struct scatterlist **to_sg,
+		   struct scatterlist **from_sg, u32 *skip,
+		   u8 from_nents, u32 tot_len);
+
+void add_to_ctr(u8 *ctr_pos, unsigned int increment);
+
+/* produce a message digest from data of length n bytes */
+int do_shash(unsigned char *name, unsigned char *result,
+	     const u8 *data1, unsigned int data1_len,
+	     const u8 *data2, unsigned int data2_len,
+	     const u8 *key, unsigned int key_len);
+
+char *spu_alg_name(enum spu_cipher_alg alg, enum spu_cipher_mode mode);
+
+void spu_setup_debugfs(void);
+void spu_free_debugfs(void);
+void format_value_ccm(unsigned int val, u8 *buf, u8 len);
+
+#endif