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, 103 insertions, 0 deletions

diff --git a/io_uring/epoll.c b/io_uring/epoll.c
new file mode 100644
index 000000000..b9db8bde2
--- /dev/null
+++ b/io_uring/epoll.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/io_uring.h>
+#include <linux/eventpoll.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "epoll.h"
+
+struct io_epoll {
+	struct file			*file;
+	int				epfd;
+	int				op;
+	int				fd;
+	struct epoll_event		event;
+};
+
+struct io_epoll_wait {
+	struct file			*file;
+	int				maxevents;
+	struct epoll_event __user	*events;
+};
+
+int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll);
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	epoll->epfd = READ_ONCE(sqe->fd);
+	epoll->op = READ_ONCE(sqe->len);
+	epoll->fd = READ_ONCE(sqe->off);
+
+	if (ep_op_has_event(epoll->op)) {
+		struct epoll_event __user *ev;
+
+		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
+		if (copy_from_user(&epoll->event, ev, sizeof(*ev)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_epoll *ie = io_kiocb_to_cmd(req, struct io_epoll);
+	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+	struct epoll_key key;
+	int ret;
+
+	CLASS(fd, f)(ie->epfd);
+	if (fd_empty(f))
+		return -EBADF;
+
+	CLASS(fd, tf)(ie->fd);
+	if (fd_empty(tf))
+		return -EBADF;
+
+	key.file = fd_file(tf);
+	key.fd = ie->fd;
+	ret = do_epoll_ctl_file(fd_file(f), ie->op, &key, &ie->event, force_nonblock);
+	if (force_nonblock && ret == -EAGAIN)
+		return -EAGAIN;
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+	if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	iew->maxevents = READ_ONCE(sqe->len);
+	iew->events = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	return 0;
+}
+
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+	int ret;
+
+	ret = epoll_sendevents(req->file, iew->events, iew->maxevents);
+	if (ret == 0)
+		return -EAGAIN;
+	if (ret < 0)
+		req_set_fail(req);
+
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}