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, 79 insertions, 0 deletions

diff --git a/io_uring/net.h b/io_uring/net.h
new file mode 100644
index 000000000..51fda715d
--- /dev/null
+++ b/io_uring/net.h
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/net.h>
+#include <linux/uio.h>
+#include <linux/io_uring_types.h>
+#include <uapi/linux/io_uring/bpf_filter.h>
+
+struct io_async_msghdr {
+#if defined(CONFIG_NET)
+	struct iou_vec				vec;
+
+	struct_group(clear,
+		int				namelen;
+		struct iovec			fast_iov;
+		__kernel_size_t			controllen;
+		__kernel_size_t			payloadlen;
+		struct sockaddr __user		*uaddr;
+		struct msghdr			msg;
+		struct sockaddr_storage		addr;
+	);
+#else
+	struct_group(clear);
+#endif
+};
+
+#if defined(CONFIG_NET)
+
+int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_shutdown(struct io_kiocb *req, unsigned int issue_flags);
+
+void io_sendmsg_recvmsg_cleanup(struct io_kiocb *req);
+int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_send(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags);
+int io_recv(struct io_kiocb *req, unsigned int issue_flags);
+
+void io_sendrecv_fail(struct io_kiocb *req);
+
+int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_accept(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_socket(struct io_kiocb *req, unsigned int issue_flags);
+void io_socket_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req);
+void io_connect_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req);
+
+int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_connect(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags);
+int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+void io_send_zc_cleanup(struct io_kiocb *req);
+
+int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_bind(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_listen_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_listen(struct io_kiocb *req, unsigned int issue_flags);
+
+void io_netmsg_cache_free(const void *entry);
+#else
+static inline void io_netmsg_cache_free(const void *entry)
+{
+}
+static inline void io_socket_bpf_populate(struct io_uring_bpf_ctx *bctx,
+					  struct io_kiocb *req)
+{
+}
+
+static inline void io_connect_bpf_populate(struct io_uring_bpf_ctx *bctx,
+					   struct io_kiocb *req)
+{
+}
+
+#endif