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, 133 insertions, 0 deletions

diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
new file mode 100644
index 000000000..ff7424bc4
--- /dev/null
+++ b/fs/nfs/getroot.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* getroot.c: get the root dentry for an NFS mount
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/vfs.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * get a root dentry from the root filehandle
+ */
+int nfs_get_root(struct super_block *s, struct fs_context *fc)
+{
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct nfs_server *server = NFS_SB(s), *clone_server;
+	struct nfs_fsinfo fsinfo;
+	struct dentry *root;
+	struct inode *inode;
+	char *name;
+	int error = -ENOMEM;
+	unsigned long kflags = 0, kflags_out = 0;
+
+	name = kstrdup(fc->source, GFP_KERNEL);
+	if (!name)
+		goto out;
+
+	/* get the actual root for this mount */
+	fsinfo.fattr = nfs_alloc_fattr_with_label(server);
+	if (fsinfo.fattr == NULL)
+		goto out_name;
+
+	error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		nfs_errorf(fc, "NFS: Couldn't getattr on root");
+		goto out_fattr;
+	}
+
+	inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		error = PTR_ERR(inode);
+		nfs_errorf(fc, "NFS: Couldn't get root inode");
+		goto out_fattr;
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	root = d_obtain_root(inode);
+	if (IS_ERR(root)) {
+		dprintk("nfs_get_root: get root dentry failed\n");
+		error = PTR_ERR(root);
+		nfs_errorf(fc, "NFS: Couldn't get root dentry");
+		goto out_fattr;
+	}
+
+	security_d_instantiate(root, inode);
+	spin_lock(&root->d_lock);
+	if (IS_ROOT(root) && !root->d_fsdata &&
+	    !(root->d_flags & DCACHE_NFSFS_RENAMED)) {
+		root->d_fsdata = name;
+		name = NULL;
+	}
+	spin_unlock(&root->d_lock);
+	if (!s->s_root)
+		s->s_root = dget(root);
+	fc->root = root;
+	if (server->caps & NFS_CAP_SECURITY_LABEL)
+		kflags |= SECURITY_LSM_NATIVE_LABELS;
+	if (ctx->clone_data.sb) {
+		if (d_inode(fc->root)->i_fop != &nfs_dir_operations) {
+			error = -ESTALE;
+			goto error_splat_root;
+		}
+		/* clone lsm security options from the parent to the new sb */
+		error = security_sb_clone_mnt_opts(ctx->clone_data.sb,
+						   s, kflags, &kflags_out);
+		if (error)
+			goto error_splat_root;
+		clone_server = NFS_SB(ctx->clone_data.sb);
+		server->has_sec_mnt_opts = clone_server->has_sec_mnt_opts;
+	} else {
+		error = security_sb_set_mnt_opts(s, fc->security,
+							kflags, &kflags_out);
+	}
+	if (error)
+		goto error_splat_root;
+	if (server->caps & NFS_CAP_SECURITY_LABEL &&
+		!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
+		server->caps &= ~NFS_CAP_SECURITY_LABEL;
+
+	nfs_setsecurity(inode, fsinfo.fattr);
+	error = 0;
+
+out_fattr:
+	nfs_free_fattr(fsinfo.fattr);
+out_name:
+	kfree(name);
+out:
+	return error;
+error_splat_root:
+	dput(fc->root);
+	fc->root = NULL;
+	goto out_fattr;
+}