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, 57 insertions, 0 deletions

diff --git a/io_uring/notif.h b/io_uring/notif.h
new file mode 100644
index 000000000..f3589cfef
--- /dev/null
+++ b/io_uring/notif.h
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/net.h>
+#include <linux/uio.h>
+#include <net/sock.h>
+#include <linux/nospec.h>
+
+#include "rsrc.h"
+
+#define IO_NOTIF_UBUF_FLAGS	(SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN)
+#define IO_NOTIF_SPLICE_BATCH	32
+
+struct io_notif_data {
+	struct file		*file;
+	struct ubuf_info	uarg;
+
+	struct io_notif_data	*next;
+	struct io_notif_data	*head;
+
+	unsigned		account_pages;
+	bool			zc_report;
+	bool			zc_used;
+	bool			zc_copied;
+};
+
+struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx);
+void io_tx_ubuf_complete(struct sk_buff *skb, struct ubuf_info *uarg,
+			 bool success);
+
+static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif)
+{
+	return io_kiocb_to_cmd(notif, struct io_notif_data);
+}
+
+static inline void io_notif_flush(struct io_kiocb *notif)
+	__must_hold(&notif->ctx->uring_lock)
+{
+	struct io_notif_data *nd = io_notif_to_data(notif);
+
+	io_tx_ubuf_complete(NULL, &nd->uarg, true);
+}
+
+static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len)
+{
+	struct io_ring_ctx *ctx = notif->ctx;
+	struct io_notif_data *nd = io_notif_to_data(notif);
+	unsigned nr_pages = (len >> PAGE_SHIFT) + 2;
+	int ret;
+
+	if (ctx->user) {
+		ret = __io_account_mem(ctx->user, nr_pages);
+		if (ret)
+			return ret;
+		nd->account_pages += nr_pages;
+	}
+	return 0;
+}