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, 218 insertions, 0 deletions

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
new file mode 100644
index 000000000..8d05ad480
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ */
+#ifndef __IPVLAN_H
+#define __IPVLAN_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rculist.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_link.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/inetdevice.h>
+#include <linux/netfilter.h>
+#include <net/ip.h>
+#include <net/ip6_route.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+#include <net/route.h>
+#include <net/addrconf.h>
+#include <net/l3mdev.h>
+
+#define IPVLAN_DRV	"ipvlan"
+#define IPV_DRV_VER	"0.1"
+
+#define IPVLAN_HASH_SIZE	(1 << BITS_PER_BYTE)
+#define IPVLAN_HASH_MASK	(IPVLAN_HASH_SIZE - 1)
+
+#define IPVLAN_MAC_FILTER_BITS	8
+#define IPVLAN_MAC_FILTER_SIZE	(1 << IPVLAN_MAC_FILTER_BITS)
+#define IPVLAN_MAC_FILTER_MASK	(IPVLAN_MAC_FILTER_SIZE - 1)
+
+#define IPVLAN_QBACKLOG_LIMIT	1000
+
+typedef enum {
+	IPVL_IPV6 = 0,
+	IPVL_ICMPV6,
+	IPVL_IPV4,
+	IPVL_ARP,
+} ipvl_hdr_type;
+
+struct ipvl_pcpu_stats {
+	u64_stats_t		rx_pkts;
+	u64_stats_t		rx_bytes;
+	u64_stats_t		rx_mcast;
+	u64_stats_t		tx_pkts;
+	u64_stats_t		tx_bytes;
+	struct u64_stats_sync	syncp;
+	u32			rx_errs;
+	u32			tx_drps;
+};
+
+struct ipvl_port;
+
+struct ipvl_dev {
+	struct net_device	*dev;
+	struct list_head	pnode;
+	struct ipvl_port	*port;
+	struct net_device	*phy_dev;
+	struct list_head	addrs;
+	struct ipvl_pcpu_stats	__percpu *pcpu_stats;
+	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
+	netdev_features_t	sfeatures;
+	u32			msg_enable;
+	bool			dying;
+};
+
+struct ipvl_addr {
+	struct ipvl_dev		*master; /* Back pointer to master */
+	union {
+		struct in6_addr	ip6;	 /* IPv6 address on logical interface */
+		struct in_addr	ip4;	 /* IPv4 address on logical interface */
+	} ipu;
+#define ip6addr	ipu.ip6
+#define ip4addr ipu.ip4
+	struct hlist_node	hlnode;  /* Hash-table linkage */
+	struct list_head	anode;   /* logical-interface linkage */
+	ipvl_hdr_type		atype;
+	struct rcu_head		rcu;
+};
+
+struct ipvl_port {
+	struct net_device	*dev;
+	possible_net_t		pnet;
+	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
+	spinlock_t		addrs_lock; /* guards hash-table and addrs */
+	struct list_head	ipvlans;
+	struct mutex		pnodes_lock;
+	u16			mode;
+	u16			flags;
+	u16			dev_id_start;
+	struct work_struct	wq;
+	struct sk_buff_head	backlog;
+	refcount_t		count;
+	struct ida		ida;
+	netdevice_tracker	dev_tracker;
+};
+
+struct ipvl_skb_cb {
+	bool tx_pkt;
+};
+#define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0]))
+
+static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
+{
+	return rcu_dereference(d->rx_handler_data);
+}
+
+static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d)
+{
+	return rcu_dereference_bh(d->rx_handler_data);
+}
+
+static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
+{
+	return rtnl_dereference(d->rx_handler_data);
+}
+
+static inline bool ipvlan_is_private(const struct ipvl_port *port)
+{
+	return !!(port->flags & IPVLAN_F_PRIVATE);
+}
+
+static inline void ipvlan_mark_private(struct ipvl_port *port)
+{
+	port->flags |= IPVLAN_F_PRIVATE;
+}
+
+static inline void ipvlan_clear_private(struct ipvl_port *port)
+{
+	port->flags &= ~IPVLAN_F_PRIVATE;
+}
+
+static inline bool ipvlan_is_vepa(const struct ipvl_port *port)
+{
+	return !!(port->flags & IPVLAN_F_VEPA);
+}
+
+static inline void ipvlan_mark_vepa(struct ipvl_port *port)
+{
+	port->flags |= IPVLAN_F_VEPA;
+}
+
+static inline void ipvlan_clear_vepa(struct ipvl_port *port)
+{
+	port->flags &= ~IPVLAN_F_VEPA;
+}
+
+void ipvlan_init_secret(void);
+unsigned int ipvlan_mac_hash(const unsigned char *addr);
+rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);
+void ipvlan_process_multicast(struct work_struct *work);
+int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev);
+void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr);
+struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
+				   const void *iaddr, bool is_v6);
+bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6);
+void ipvlan_ht_addr_del(struct ipvl_addr *addr);
+struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
+				     int addr_type, bool use_dest);
+void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type);
+void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+		     unsigned int len, bool success, bool mcast);
+int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
+		    struct netlink_ext_ack *extack);
+void __ipvlan_link_delete(struct net *net, struct net_device *dev,
+			  struct list_head *head);
+void ipvlan_link_setup(struct net_device *dev);
+int ipvlan_link_register(struct rtnl_link_ops *ops);
+#ifdef CONFIG_IPVLAN_L3S
+int ipvlan_l3s_register(struct ipvl_port *port);
+void ipvlan_l3s_unregister(struct ipvl_port *port);
+void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet);
+int ipvlan_l3s_init(void);
+void ipvlan_l3s_cleanup(void);
+#else
+static inline int ipvlan_l3s_register(struct ipvl_port *port)
+{
+	return -ENOTSUPP;
+}
+
+static inline void ipvlan_l3s_unregister(struct ipvl_port *port)
+{
+}
+
+static inline void ipvlan_migrate_l3s_hook(struct net *oldnet,
+					   struct net *newnet)
+{
+}
+
+static inline int ipvlan_l3s_init(void)
+{
+	return 0;
+}
+
+static inline void ipvlan_l3s_cleanup(void)
+{
+}
+#endif /* CONFIG_IPVLAN_L3S */
+
+static inline bool netif_is_ipvlan_port(const struct net_device *dev)
+{
+	return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame;
+}
+
+#if IS_ENABLED(CONFIG_IPVTAP)
+extern void (*__ipvtap_dellink_ptr)(struct net *net, struct net_device *dev,
+				    struct list_head *head);
+#endif
+
+#endif /* __IPVLAN_H */