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, 217 insertions, 0 deletions

diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
new file mode 100644
index 000000000..f97a752e9
--- /dev/null
+++ b/lib/dynamic_queue_limits.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Dynamic byte queue limits.  See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/dynamic_queue_limits.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <trace/events/napi.h>
+
+#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
+#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
+
+static void dql_check_stall(struct dql *dql, unsigned short stall_thrs)
+{
+	unsigned long now;
+
+	if (!stall_thrs)
+		return;
+
+	now = jiffies;
+	/* Check for a potential stall */
+	if (time_after_eq(now, dql->last_reap + stall_thrs)) {
+		unsigned long hist_head, t, start, end;
+
+		/* We are trying to detect a period of at least @stall_thrs
+		 * jiffies without any Tx completions, but during first half
+		 * of which some Tx was posted.
+		 */
+dqs_again:
+		hist_head = READ_ONCE(dql->history_head);
+		/* pairs with smp_wmb() in dql_queued() */
+		smp_rmb();
+
+		/* Get the previous entry in the ring buffer, which is the
+		 * oldest sample.
+		 */
+		start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG;
+
+		/* Advance start to continue from the last reap time */
+		if (time_before(start, dql->last_reap + 1))
+			start = dql->last_reap + 1;
+
+		/* Newest sample we should have already seen a completion for */
+		end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1);
+
+		/* Shrink the search space to [start, (now - start_thrs/2)] if
+		 * `end` is beyond the stall zone
+		 */
+		if (time_before(now, end + stall_thrs / 2))
+			end = now - stall_thrs / 2;
+
+		/* Search for the queued time in [t, end] */
+		for (t = start; time_before_eq(t, end); t++)
+			if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG),
+				     dql->history))
+				break;
+
+		/* Variable t contains the time of the queue */
+		if (!time_before_eq(t, end))
+			goto no_stall;
+
+		/* The ring buffer was modified in the meantime, retry */
+		if (hist_head != READ_ONCE(dql->history_head))
+			goto dqs_again;
+
+		dql->stall_cnt++;
+		dql->stall_max = max_t(unsigned short, dql->stall_max, now - t);
+
+		trace_dql_stall_detected(dql->stall_thrs, now - t,
+					 dql->last_reap, dql->history_head,
+					 now, dql->history);
+	}
+no_stall:
+	dql->last_reap = now;
+}
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+	unsigned int inprogress, prev_inprogress, limit;
+	unsigned int ovlimit, completed, num_queued;
+	unsigned short stall_thrs;
+	bool all_prev_completed;
+
+	num_queued = READ_ONCE(dql->num_queued);
+	/* Read stall_thrs in advance since it belongs to the same (first)
+	 * cache line as ->num_queued. This way, dql_check_stall() does not
+	 * need to touch the first cache line again later, reducing the window
+	 * of possible false sharing.
+	 */
+	stall_thrs = READ_ONCE(dql->stall_thrs);
+
+	/* Can't complete more than what's in queue */
+	BUG_ON(count > num_queued - dql->num_completed);
+
+	completed = dql->num_completed + count;
+	limit = dql->limit;
+	ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
+	inprogress = num_queued - completed;
+	prev_inprogress = dql->prev_num_queued - dql->num_completed;
+	all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
+
+	if ((ovlimit && !inprogress) ||
+	    (dql->prev_ovlimit && all_prev_completed)) {
+		/*
+		 * Queue considered starved if:
+		 *   - The queue was over-limit in the last interval,
+		 *     and there is no more data in the queue.
+		 *  OR
+		 *   - The queue was over-limit in the previous interval and
+		 *     when enqueuing it was possible that all queued data
+		 *     had been consumed.  This covers the case when queue
+		 *     may have becomes starved between completion processing
+		 *     running and next time enqueue was scheduled.
+		 *
+		 *     When queue is starved increase the limit by the amount
+		 *     of bytes both sent and completed in the last interval,
+		 *     plus any previous over-limit.
+		 */
+		limit += POSDIFF(completed, dql->prev_num_queued) +
+		     dql->prev_ovlimit;
+		dql->slack_start_time = jiffies;
+		dql->lowest_slack = UINT_MAX;
+	} else if (inprogress && prev_inprogress && !all_prev_completed) {
+		/*
+		 * Queue was not starved, check if the limit can be decreased.
+		 * A decrease is only considered if the queue has been busy in
+		 * the whole interval (the check above).
+		 *
+		 * If there is slack, the amount of excess data queued above
+		 * the amount needed to prevent starvation, the queue limit
+		 * can be decreased.  To avoid hysteresis we consider the
+		 * minimum amount of slack found over several iterations of the
+		 * completion routine.
+		 */
+		unsigned int slack, slack_last_objs;
+
+		/*
+		 * Slack is the maximum of
+		 *   - The queue limit plus previous over-limit minus twice
+		 *     the number of objects completed.  Note that two times
+		 *     number of completed bytes is a basis for an upper bound
+		 *     of the limit.
+		 *   - Portion of objects in the last queuing operation that
+		 *     was not part of non-zero previous over-limit.  That is
+		 *     "round down" by non-overlimit portion of the last
+		 *     queueing operation.
+		 */
+		slack = POSDIFF(limit + dql->prev_ovlimit,
+		    2 * (completed - dql->num_completed));
+		slack_last_objs = dql->prev_ovlimit ?
+		    POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+		slack = max(slack, slack_last_objs);
+
+		if (slack < dql->lowest_slack)
+			dql->lowest_slack = slack;
+
+		if (time_after(jiffies,
+			       dql->slack_start_time + dql->slack_hold_time)) {
+			limit = POSDIFF(limit, dql->lowest_slack);
+			dql->slack_start_time = jiffies;
+			dql->lowest_slack = UINT_MAX;
+		}
+	}
+
+	/* Enforce bounds on limit */
+	limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+	if (limit != dql->limit) {
+		dql->limit = limit;
+		ovlimit = 0;
+	}
+
+	dql->adj_limit = limit + completed;
+	dql->prev_ovlimit = ovlimit;
+	dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt);
+	dql->num_completed = completed;
+	dql->prev_num_queued = num_queued;
+
+	dql_check_stall(dql, stall_thrs);
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+	/* Reset all dynamic values */
+	dql->limit = dql->min_limit;
+	dql->num_queued = 0;
+	dql->num_completed = 0;
+	dql->last_obj_cnt = 0;
+	dql->prev_num_queued = 0;
+	dql->prev_last_obj_cnt = 0;
+	dql->prev_ovlimit = 0;
+	dql->lowest_slack = UINT_MAX;
+	dql->slack_start_time = jiffies;
+
+	dql->last_reap = jiffies;
+	dql->history_head = jiffies / BITS_PER_LONG;
+	memset(dql->history, 0, sizeof(dql->history));
+}
+EXPORT_SYMBOL(dql_reset);
+
+void dql_init(struct dql *dql, unsigned int hold_time)
+{
+	dql->max_limit = DQL_MAX_LIMIT;
+	dql->min_limit = 0;
+	dql->slack_hold_time = hold_time;
+	dql->stall_thrs = 0;
+	dql_reset(dql);
+}
+EXPORT_SYMBOL(dql_init);