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, 75 insertions, 0 deletions

diff --git a/net/ethtool/module_fw.h b/net/ethtool/module_fw.h
new file mode 100644
index 000000000..634543a12
--- /dev/null
+++ b/net/ethtool/module_fw.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <uapi/linux/ethtool.h>
+#include "netlink.h"
+
+/**
+ * struct ethnl_module_fw_flash_ntf_params - module firmware flashing
+ *						notifications parameters
+ * @portid: Netlink portid of sender.
+ * @seq: Sequence number of sender.
+ * @closed_sock: Indicates whether the socket was closed from user space.
+ */
+struct ethnl_module_fw_flash_ntf_params {
+	u32 portid;
+	u32 seq;
+	bool closed_sock;
+};
+
+/**
+ * struct ethtool_module_fw_flash_params - module firmware flashing parameters
+ * @password: Module password. Only valid when @pass_valid is set.
+ * @password_valid: Whether the module password is valid or not.
+ */
+struct ethtool_module_fw_flash_params {
+	__be32 password;
+	u8 password_valid:1;
+};
+
+/**
+ * struct ethtool_cmis_fw_update_params - CMIS firmware update specific
+ *						parameters
+ * @dev: Pointer to the net_device to be flashed.
+ * @params: Module firmware flashing parameters.
+ * @ntf_params: Module firmware flashing notification parameters.
+ * @fw: Firmware to flash.
+ */
+struct ethtool_cmis_fw_update_params {
+	struct net_device *dev;
+	struct ethtool_module_fw_flash_params params;
+	struct ethnl_module_fw_flash_ntf_params ntf_params;
+	const struct firmware *fw;
+};
+
+/**
+ * struct ethtool_module_fw_flash - module firmware flashing
+ * @list: List node for &module_fw_flash_work_list.
+ * @dev_tracker: Refcount tracker for @dev.
+ * @work: The flashing firmware work.
+ * @fw_update: CMIS firmware update specific parameters.
+ */
+struct ethtool_module_fw_flash {
+	struct list_head list;
+	netdevice_tracker dev_tracker;
+	struct work_struct work;
+	struct ethtool_cmis_fw_update_params fw_update;
+};
+
+void ethnl_module_fw_flash_sock_destroy(struct ethnl_sock_priv *sk_priv);
+
+void
+ethnl_module_fw_flash_ntf_err(struct net_device *dev,
+			      struct ethnl_module_fw_flash_ntf_params *params,
+			      char *err_msg, char *sub_err_msg);
+void
+ethnl_module_fw_flash_ntf_start(struct net_device *dev,
+				struct ethnl_module_fw_flash_ntf_params *params);
+void
+ethnl_module_fw_flash_ntf_complete(struct net_device *dev,
+				   struct ethnl_module_fw_flash_ntf_params *params);
+void
+ethnl_module_fw_flash_ntf_in_progress(struct net_device *dev,
+				      struct ethnl_module_fw_flash_ntf_params *params,
+				      u64 done, u64 total);
+
+void ethtool_cmis_fw_update(struct ethtool_cmis_fw_update_params *params);