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

3 files changed, 87 insertions, 0 deletions

diff --git a/tools/testing/selftests/tmpfs/.gitignore b/tools/testing/selftests/tmpfs/.gitignore
new file mode 100644
index 000000000..b1afaa925
--- /dev/null
+++ b/tools/testing/selftests/tmpfs/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/bug-link-o-tmpfile
diff --git a/tools/testing/selftests/tmpfs/Makefile b/tools/testing/selftests/tmpfs/Makefile
new file mode 100644
index 000000000..3be931e11
--- /dev/null
+++ b/tools/testing/selftests/tmpfs/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -Wall -O2
+
+TEST_GEN_PROGS :=
+TEST_GEN_PROGS += bug-link-o-tmpfile
+
+include ../lib.mk
diff --git a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c
new file mode 100644
index 000000000..5cb4e404a
--- /dev/null
+++ b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2019 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test that open(O_TMPFILE), linkat() doesn't screw accounting. */
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/mount.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+
+int main(void)
+{
+	int fd;
+
+	// Setting up kselftest framework
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	// Check if test is run as root
+	if (geteuid()) {
+		ksft_exit_skip("This test needs root to run!\n");
+		return 1;
+	}
+
+	if (unshare(CLONE_NEWNS) == -1) {
+		if (errno == ENOSYS || errno == EPERM) {
+			ksft_exit_skip("unshare() error: unshare, errno %d\n", errno);
+		} else {
+			ksft_exit_fail_msg("unshare() error: unshare, errno %d\n", errno);
+		}
+	}
+
+	if (mount(NULL, "/", NULL, MS_PRIVATE|MS_REC, NULL) == -1) {
+		ksft_exit_fail_msg("mount() error: Root filesystem private mount: Fail %d\n", errno);
+	}
+
+	/* Our heroes: 1 root inode, 1 O_TMPFILE inode, 1 permanent inode. */
+	if (mount(NULL, "/tmp", "tmpfs", 0, "nr_inodes=3") == -1) {
+		ksft_exit_fail_msg("mount() error: Mounting tmpfs on /tmp: Fail %d\n", errno);
+	}
+
+	fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_TMPFILE, 0600);
+	if (fd == -1) {
+		ksft_exit_fail_msg("openat() error: Open first temporary file: Fail %d\n", errno);
+	}
+
+	if (linkat(fd, "", AT_FDCWD, "/tmp/1", AT_EMPTY_PATH) == -1) {
+		ksft_exit_fail_msg("linkat() error: Linking the temporary file: Fail %d\n", errno);
+		/* Ensure fd is closed on failure */
+		close(fd);
+	}
+	close(fd);
+
+	fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_TMPFILE, 0600);
+	if (fd == -1) {
+		ksft_exit_fail_msg("openat() error: Opening the second temporary file: Fail %d\n", errno);
+	}
+	ksft_test_result_pass(" ");
+	ksft_exit_pass();
+	return 0;
+}