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, 91 insertions, 0 deletions

diff --git a/io_uring/loop.c b/io_uring/loop.c
new file mode 100644
index 000000000..bbbb6ef14
--- /dev/null
+++ b/io_uring/loop.c
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "io_uring.h"
+#include "wait.h"
+#include "loop.h"
+
+static inline int io_loop_nr_cqes(const struct io_ring_ctx *ctx,
+				  const struct iou_loop_params *lp)
+{
+	return lp->cq_wait_idx - READ_ONCE(ctx->rings->cq.tail);
+}
+
+static inline void io_loop_wait_start(struct io_ring_ctx *ctx, unsigned nr_wait)
+{
+	atomic_set(&ctx->cq_wait_nr, nr_wait);
+	set_current_state(TASK_INTERRUPTIBLE);
+}
+
+static inline void io_loop_wait_finish(struct io_ring_ctx *ctx)
+{
+	__set_current_state(TASK_RUNNING);
+	atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
+}
+
+static void io_loop_wait(struct io_ring_ctx *ctx, struct iou_loop_params *lp,
+			 unsigned nr_wait)
+{
+	io_loop_wait_start(ctx, nr_wait);
+
+	if (unlikely(io_local_work_pending(ctx) ||
+		     io_loop_nr_cqes(ctx, lp) <= 0) ||
+		     READ_ONCE(ctx->check_cq)) {
+		io_loop_wait_finish(ctx);
+		return;
+	}
+
+	mutex_unlock(&ctx->uring_lock);
+	schedule();
+	io_loop_wait_finish(ctx);
+	mutex_lock(&ctx->uring_lock);
+}
+
+static int __io_run_loop(struct io_ring_ctx *ctx)
+{
+	struct iou_loop_params lp = {};
+
+	while (true) {
+		int nr_wait, step_res;
+
+		if (unlikely(!ctx->loop_step))
+			return -EFAULT;
+
+		step_res = ctx->loop_step(io_loop_mangle_ctx(ctx), &lp);
+		if (step_res == IOU_LOOP_STOP)
+			break;
+		if (step_res != IOU_LOOP_CONTINUE)
+			return -EINVAL;
+
+		nr_wait = io_loop_nr_cqes(ctx, &lp);
+		if (nr_wait > 0)
+			io_loop_wait(ctx, &lp, nr_wait);
+		else
+			nr_wait = 0;
+
+		if (task_work_pending(current)) {
+			mutex_unlock(&ctx->uring_lock);
+			io_run_task_work();
+			mutex_lock(&ctx->uring_lock);
+		}
+		if (unlikely(task_sigpending(current)))
+			return -EINTR;
+		io_run_local_work_locked(ctx, nr_wait);
+
+		if (READ_ONCE(ctx->check_cq) & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
+			io_cqring_overflow_flush_locked(ctx);
+	}
+
+	return 0;
+}
+
+int io_run_loop(struct io_ring_ctx *ctx)
+{
+	int ret;
+
+	if (!io_allowed_run_tw(ctx))
+		return -EEXIST;
+
+	mutex_lock(&ctx->uring_lock);
+	ret = __io_run_loop(ctx);
+	mutex_unlock(&ctx->uring_lock);
+	return ret;
+}