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, 81 insertions, 0 deletions

diff --git a/include/rdma/ib.h b/include/rdma/ib.h
new file mode 100644
index 000000000..f7c185ff7
--- /dev/null
+++ b/include/rdma/ib.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2010 Intel Corporation.  All rights reserved.
+ */
+
+#ifndef _RDMA_IB_H
+#define _RDMA_IB_H
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/uaccess.h>
+#include <linux/fs.h>
+
+struct ib_addr {
+	union {
+		__u8		uib_addr8[16];
+		__be16		uib_addr16[8];
+		__be32		uib_addr32[4];
+		__be64		uib_addr64[2];
+	} ib_u;
+#define sib_addr8		ib_u.uib_addr8
+#define sib_addr16		ib_u.uib_addr16
+#define sib_addr32		ib_u.uib_addr32
+#define sib_addr64		ib_u.uib_addr64
+#define sib_raw			ib_u.uib_addr8
+#define sib_subnet_prefix	ib_u.uib_addr64[0]
+#define sib_interface_id	ib_u.uib_addr64[1]
+};
+
+static inline bool ib_addr_any(const struct ib_addr *a)
+{
+	return ((a->sib_addr64[0] | a->sib_addr64[1]) == 0);
+}
+
+static inline bool ib_addr_loopback(const struct ib_addr *a)
+{
+	return ((a->sib_addr32[0] | a->sib_addr32[1] |
+		 a->sib_addr32[2] | (a->sib_addr32[3] ^ htonl(1))) == 0);
+}
+
+static inline void ib_addr_set(struct ib_addr *addr,
+			       __be32 w1, __be32 w2, __be32 w3, __be32 w4)
+{
+	addr->sib_addr32[0] = w1;
+	addr->sib_addr32[1] = w2;
+	addr->sib_addr32[2] = w3;
+	addr->sib_addr32[3] = w4;
+}
+
+static inline int ib_addr_cmp(const struct ib_addr *a1, const struct ib_addr *a2)
+{
+	return memcmp(a1, a2, sizeof(struct ib_addr));
+}
+
+struct sockaddr_ib {
+	unsigned short int	sib_family;	/* AF_IB */
+	__be16			sib_pkey;
+	__be32			sib_flowinfo;
+	struct ib_addr		sib_addr;
+	__be64			sib_sid;
+	__be64			sib_sid_mask;
+	__u64			sib_scope_id;
+};
+
+/*
+ * The IB interfaces that use write() as bi-directional ioctl() are
+ * fundamentally unsafe, since there are lots of ways to trigger "write()"
+ * calls from various contexts with elevated privileges. That includes the
+ * traditional suid executable error message writes, but also various kernel
+ * interfaces that can write to file descriptors.
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static inline bool ib_safe_file_access(struct file *filp)
+{
+	return filp->f_cred == current_cred();
+}
+
+#endif /* _RDMA_IB_H */