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, 106 insertions, 0 deletions

diff --git a/net/802/fc.c b/net/802/fc.c
new file mode 100644
index 000000000..afd3d288a
--- /dev/null
+++ b/net/802/fc.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * NET3:	Fibre Channel device handling subroutines
+ *
+ *		Vineet Abraham <vma@iol.unh.edu>
+ *		v 1.0 03/22/99
+ */
+
+#include <linux/uaccess.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/fcdevice.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/timer.h>
+#include <linux/net.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <net/arp.h>
+
+/*
+ *	Put the headers on a Fibre Channel packet.
+ */
+
+static int fc_header(struct sk_buff *skb, struct net_device *dev,
+		     unsigned short type,
+		     const void *daddr, const void *saddr, unsigned int len)
+{
+	struct fch_hdr *fch;
+	int hdr_len;
+
+	/*
+	 * Add the 802.2 SNAP header if IP as the IPv4 code calls
+	 * dev->hard_header directly.
+	 */
+	if (type == ETH_P_IP || type == ETH_P_ARP)
+	{
+		struct fcllc *fcllc;
+
+		hdr_len = sizeof(struct fch_hdr) + sizeof(struct fcllc);
+		fch = skb_push(skb, hdr_len);
+		fcllc = (struct fcllc *)(fch+1);
+		fcllc->dsap = fcllc->ssap = EXTENDED_SAP;
+		fcllc->llc = UI_CMD;
+		fcllc->protid[0] = fcllc->protid[1] = fcllc->protid[2] = 0x00;
+		fcllc->ethertype = htons(type);
+	}
+	else
+	{
+		hdr_len = sizeof(struct fch_hdr);
+		fch = skb_push(skb, hdr_len);
+	}
+
+	if(saddr)
+		memcpy(fch->saddr,saddr,dev->addr_len);
+	else
+		memcpy(fch->saddr,dev->dev_addr,dev->addr_len);
+
+	if(daddr)
+	{
+		memcpy(fch->daddr,daddr,dev->addr_len);
+		return hdr_len;
+	}
+	return -hdr_len;
+}
+
+static const struct header_ops fc_header_ops = {
+	.create	 = fc_header,
+};
+
+static void fc_setup(struct net_device *dev)
+{
+	dev->header_ops		= &fc_header_ops;
+	dev->type		= ARPHRD_IEEE802;
+	dev->hard_header_len	= FC_HLEN;
+	dev->mtu		= 2024;
+	dev->addr_len		= FC_ALEN;
+	dev->tx_queue_len	= 100; /* Long queues on fc */
+	dev->flags		= IFF_BROADCAST;
+
+	memset(dev->broadcast, 0xFF, FC_ALEN);
+}
+
+/**
+ * alloc_fcdev - Register fibre channel device
+ * @sizeof_priv: Size of additional driver-private structure to be allocated
+ *	for this fibre channel device
+ *
+ * Fill in the fields of the device structure with fibre channel-generic values.
+ *
+ * Constructs a new net device, complete with a private data area of
+ * size @sizeof_priv.  A 32-byte (not bit) alignment is enforced for
+ * this private data area.
+ */
+struct net_device *alloc_fcdev(int sizeof_priv)
+{
+	return alloc_netdev(sizeof_priv, "fc%d", NET_NAME_UNKNOWN, fc_setup);
+}
+EXPORT_SYMBOL(alloc_fcdev);