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, 149 insertions, 0 deletions

diff --git a/io_uring/splice.c b/io_uring/splice.c
new file mode 100644
index 000000000..e81ebbb91
--- /dev/null
+++ b/io_uring/splice.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/io_uring.h>
+#include <linux/splice.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "filetable.h"
+#include "io_uring.h"
+#include "splice.h"
+
+struct io_splice {
+	struct file			*file_out;
+	loff_t				off_out;
+	loff_t				off_in;
+	u64				len;
+	int				splice_fd_in;
+	unsigned int			flags;
+	struct io_rsrc_node		*rsrc_node;
+};
+
+static int __io_splice_prep(struct io_kiocb *req,
+			    const struct io_uring_sqe *sqe)
+{
+	struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
+	unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
+
+	sp->len = READ_ONCE(sqe->len);
+	sp->flags = READ_ONCE(sqe->splice_flags);
+	if (unlikely(sp->flags & ~valid_flags))
+		return -EINVAL;
+	sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
+	sp->rsrc_node = NULL;
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_tee_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off))
+		return -EINVAL;
+	return __io_splice_prep(req, sqe);
+}
+
+void io_splice_cleanup(struct io_kiocb *req)
+{
+	struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
+
+	if (sp->rsrc_node)
+		io_put_rsrc_node(req->ctx, sp->rsrc_node);
+}
+
+static struct file *io_splice_get_file(struct io_kiocb *req,
+				       unsigned int issue_flags)
+{
+	struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_rsrc_node *node;
+	struct file *file = NULL;
+
+	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
+		return io_file_get_normal(req, sp->splice_fd_in);
+
+	io_ring_submit_lock(ctx, issue_flags);
+	node = io_rsrc_node_lookup(&ctx->file_table.data, sp->splice_fd_in);
+	if (node) {
+		node->refs++;
+		sp->rsrc_node = node;
+		file = io_slot_file(node);
+		req->flags |= REQ_F_NEED_CLEANUP;
+	}
+	io_ring_submit_unlock(ctx, issue_flags);
+	return file;
+}
+
+int io_tee(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
+	struct file *out = sp->file_out;
+	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+	struct file *in;
+	ssize_t ret = 0;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	in = io_splice_get_file(req, issue_flags);
+	if (!in) {
+		ret = -EBADF;
+		goto done;
+	}
+
+	if (sp->len)
+		ret = do_tee(in, out, sp->len, flags);
+
+	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
+		fput(in);
+done:
+	if (ret != sp->len)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
+
+	sp->off_in = READ_ONCE(sqe->splice_off_in);
+	sp->off_out = READ_ONCE(sqe->off);
+	return __io_splice_prep(req, sqe);
+}
+
+int io_splice(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
+	struct file *out = sp->file_out;
+	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+	loff_t *poff_in, *poff_out;
+	struct file *in;
+	ssize_t ret = 0;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	in = io_splice_get_file(req, issue_flags);
+	if (!in) {
+		ret = -EBADF;
+		goto done;
+	}
+
+	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
+	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
+
+	if (sp->len)
+		ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
+
+	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
+		fput(in);
+done:
+	if (ret != sp->len)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}