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, 120 insertions, 0 deletions

diff --git a/net/sctp/offload.c b/net/sctp/offload.c
new file mode 100644
index 000000000..e6f863c03
--- /dev/null
+++ b/net/sctp/offload.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * sctp_offload - GRO/GSO Offloading for SCTP
+ *
+ * Copyright (C) 2015, Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/socket.h>
+#include <linux/sctp.h>
+#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/kfifo.h>
+#include <linux/time.h>
+#include <net/net_namespace.h>
+
+#include <linux/skbuff.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/checksum.h>
+#include <net/protocol.h>
+#include <net/gso.h>
+
+static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
+{
+	skb->ip_summed = CHECKSUM_NONE;
+	skb->csum_not_inet = 0;
+	/* csum and csum_start in GSO CB may be needed to do the UDP
+	 * checksum when it's a UDP tunneling packet.
+	 */
+	SKB_GSO_CB(skb)->csum = (__force __wsum)~0;
+	SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len;
+	return sctp_compute_cksum(skb, skb_transport_offset(skb));
+}
+
+static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
+					netdev_features_t features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct sctphdr *sh;
+
+	if (!skb_is_gso_sctp(skb))
+		goto out;
+
+	sh = sctp_hdr(skb);
+	if (!pskb_may_pull(skb, sizeof(*sh)))
+		goto out;
+
+	__skb_pull(skb, sizeof(*sh));
+
+	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+		/* Packet is from an untrusted source, reset gso_segs. */
+		struct skb_shared_info *pinfo = skb_shinfo(skb);
+		struct sk_buff *frag_iter;
+
+		pinfo->gso_segs = 0;
+		if (skb->len != skb->data_len) {
+			/* Means we have chunks in here too */
+			pinfo->gso_segs++;
+		}
+
+		skb_walk_frags(skb, frag_iter)
+			pinfo->gso_segs++;
+
+		segs = NULL;
+		goto out;
+	}
+
+	segs = skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG);
+	if (IS_ERR(segs))
+		goto out;
+
+	/* All that is left is update SCTP CRC if necessary */
+	if (!(features & NETIF_F_SCTP_CRC)) {
+		for (skb = segs; skb; skb = skb->next) {
+			if (skb->ip_summed == CHECKSUM_PARTIAL) {
+				sh = sctp_hdr(skb);
+				sh->checksum = sctp_gso_make_checksum(skb);
+			}
+		}
+	}
+
+out:
+	return segs;
+}
+
+static const struct net_offload sctp_offload = {
+	.callbacks = {
+		.gso_segment = sctp_gso_segment,
+	},
+};
+
+static const struct net_offload sctp6_offload = {
+	.callbacks = {
+		.gso_segment = sctp_gso_segment,
+	},
+};
+
+int __init sctp_offload_init(void)
+{
+	int ret;
+
+	ret = inet_add_offload(&sctp_offload, IPPROTO_SCTP);
+	if (ret)
+		goto out;
+
+	ret = inet6_add_offload(&sctp6_offload, IPPROTO_SCTP);
+	if (ret)
+		goto ipv4;
+
+	return ret;
+
+ipv4:
+	inet_del_offload(&sctp_offload, IPPROTO_SCTP);
+out:
+	return ret;
+}