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, 73 insertions, 0 deletions

diff --git a/sound/soc/sof/ipc4-telemetry.h b/sound/soc/sof/ipc4-telemetry.h
new file mode 100644
index 000000000..9298f8acc
--- /dev/null
+++ b/sound/soc/sof/ipc4-telemetry.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * Copyright(c) 2023 Intel Corporation
+ */
+
+#ifndef __SOUND_SOC_SOF_IPC4_TELEMETRY_H
+#define __SOUND_SOC_SOF_IPC4_TELEMETRY_H
+
+/* Target code */
+enum sof_ipc4_coredump_tgt_code {
+	COREDUMP_TGT_UNKNOWN = 0,
+	COREDUMP_TGT_X86,
+	COREDUMP_TGT_X86_64,
+	COREDUMP_TGT_ARM_CORTEX_M,
+	COREDUMP_TGT_RISC_V,
+	COREDUMP_TGT_XTENSA,
+};
+
+#define COREDUMP_ARCH_HDR_ID 'A'
+#define COREDUMP_HDR_ID0 'Z'
+#define COREDUMP_HDR_ID1 'E'
+
+#define XTENSA_BLOCK_HDR_VER		2
+#define XTENSA_CORE_DUMP_SEPARATOR	0x0DEC0DEB
+#define XTENSA_CORE_AR_REGS_COUNT	16
+#define XTENSA_SOC_INTEL_ADSP		3
+#define XTENSA_TOOL_CHAIN_ZEPHYR	1
+#define XTENSA_TOOL_CHAIN_XCC		2
+
+/* Coredump header */
+struct sof_ipc4_coredump_hdr {
+	/* 'Z', 'E' as identifier of file */
+	char id[2];
+
+	/* Identify the version of the header */
+	u16 hdr_version;
+
+	/* Indicate which target (e.g. architecture or SoC) */
+	u16 tgt_code;
+
+	/* Size of uintptr_t in power of 2. (e.g. 5 for 32-bit, 6 for 64-bit) */
+	u8 ptr_size_bits;
+
+	u8 flag;
+
+	/* Reason for the fatal error */
+	u32 reason;
+} __packed;
+
+/* Architecture-specific block header */
+struct sof_ipc4_coredump_arch_hdr {
+	/* COREDUMP_ARCH_HDR_ID to indicate this is a architecture-specific block */
+	char id;
+
+	/* Identify the version of this block */
+	u16 hdr_version;
+
+	/* Number of bytes following the header */
+	u16 num_bytes;
+} __packed;
+
+struct sof_ipc4_telemetry_slot_data {
+	u32 separator;
+	struct sof_ipc4_coredump_hdr hdr;
+	struct sof_ipc4_coredump_arch_hdr arch_hdr;
+	u32 arch_data[];
+} __packed;
+
+void sof_ipc4_create_exception_debugfs_node(struct snd_sof_dev *sdev);
+#endif