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, 85 insertions, 0 deletions

diff --git a/samples/check-exec/set-exec.c b/samples/check-exec/set-exec.c
new file mode 100644
index 000000000..ba86a60a2
--- /dev/null
+++ b/samples/check-exec/set-exec.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Simple tool to set SECBIT_EXEC_RESTRICT_FILE, SECBIT_EXEC_DENY_INTERACTIVE,
+ * before executing a command.
+ *
+ * Copyright © 2024 Microsoft Corporation
+ */
+
+#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__
+#include <errno.h>
+#include <linux/prctl.h>
+#include <linux/securebits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+static void print_usage(const char *argv0)
+{
+	fprintf(stderr, "usage: %s -f|-i -- <cmd> [args]...\n\n", argv0);
+	fprintf(stderr, "Execute a command with\n");
+	fprintf(stderr, "- SECBIT_EXEC_RESTRICT_FILE set: -f\n");
+	fprintf(stderr, "- SECBIT_EXEC_DENY_INTERACTIVE set: -i\n");
+}
+
+int main(const int argc, char *const argv[], char *const *const envp)
+{
+	const char *cmd_path;
+	char *const *cmd_argv;
+	int opt, secbits_cur, secbits_new;
+	bool has_policy = false;
+
+	secbits_cur = prctl(PR_GET_SECUREBITS);
+	if (secbits_cur == -1) {
+		/*
+		 * This should never happen, except with a buggy seccomp
+		 * filter.
+		 */
+		perror("ERROR: Failed to get securebits");
+		return 1;
+	}
+
+	secbits_new = secbits_cur;
+	while ((opt = getopt(argc, argv, "fi")) != -1) {
+		switch (opt) {
+		case 'f':
+			secbits_new |= SECBIT_EXEC_RESTRICT_FILE |
+				       SECBIT_EXEC_RESTRICT_FILE_LOCKED;
+			has_policy = true;
+			break;
+		case 'i':
+			secbits_new |= SECBIT_EXEC_DENY_INTERACTIVE |
+				       SECBIT_EXEC_DENY_INTERACTIVE_LOCKED;
+			has_policy = true;
+			break;
+		default:
+			print_usage(argv[0]);
+			return 1;
+		}
+	}
+
+	if (!argv[optind] || !has_policy) {
+		print_usage(argv[0]);
+		return 1;
+	}
+
+	if (secbits_cur != secbits_new &&
+	    prctl(PR_SET_SECUREBITS, secbits_new)) {
+		perror("Failed to set secure bit(s).");
+		fprintf(stderr,
+			"Hint: The running kernel may not support this feature.\n");
+		return 1;
+	}
+
+	cmd_path = argv[optind];
+	cmd_argv = argv + optind;
+	fprintf(stderr, "Executing command...\n");
+	execvpe(cmd_path, cmd_argv, envp);
+	fprintf(stderr, "Failed to execute \"%s\": %s\n", cmd_path,
+		strerror(errno));
+	return 1;
+}