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, 154 insertions, 0 deletions

diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
new file mode 100644
index 000000000..487fbc51d
--- /dev/null
+++ b/fs/squashfs/zstd_wrapper.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * zstd_wrapper.c
+ */
+
+#include <linux/mutex.h>
+#include <linux/bio.h>
+#include <linux/slab.h>
+#include <linux/zstd.h>
+#include <linux/vmalloc.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs.h"
+#include "decompressor.h"
+#include "page_actor.h"
+
+struct workspace {
+	void *mem;
+	size_t mem_size;
+	size_t window_size;
+};
+
+static void *zstd_init(struct squashfs_sb_info *msblk, void *buff)
+{
+	struct workspace *wksp = kmalloc_obj(*wksp);
+
+	if (wksp == NULL)
+		goto failed;
+	wksp->window_size = max_t(size_t,
+			msblk->block_size, SQUASHFS_METADATA_SIZE);
+	wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size);
+	wksp->mem = vmalloc(wksp->mem_size);
+	if (wksp->mem == NULL)
+		goto failed;
+
+	return wksp;
+
+failed:
+	ERROR("Failed to allocate zstd workspace\n");
+	kfree(wksp);
+	return ERR_PTR(-ENOMEM);
+}
+
+
+static void zstd_free(void *strm)
+{
+	struct workspace *wksp = strm;
+
+	if (wksp)
+		vfree(wksp->mem);
+	kfree(wksp);
+}
+
+
+static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct bio *bio, int offset, int length,
+	struct squashfs_page_actor *output)
+{
+	struct workspace *wksp = strm;
+	zstd_dstream *stream;
+	size_t total_out = 0;
+	int error = 0;
+	zstd_in_buffer in_buf = { NULL, 0, 0 };
+	zstd_out_buffer out_buf = { NULL, 0, 0 };
+	struct bvec_iter_all iter_all = {};
+	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+
+	stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size);
+
+	if (!stream) {
+		ERROR("Failed to initialize zstd decompressor\n");
+		return -EIO;
+	}
+
+	out_buf.size = PAGE_SIZE;
+	out_buf.dst = squashfs_first_page(output);
+	if (IS_ERR(out_buf.dst)) {
+		error = PTR_ERR(out_buf.dst);
+		goto finish;
+	}
+
+	for (;;) {
+		size_t zstd_err;
+
+		if (in_buf.pos == in_buf.size) {
+			const void *data;
+			int avail;
+
+			if (!bio_next_segment(bio, &iter_all)) {
+				error = -EIO;
+				break;
+			}
+
+			avail = min(length, ((int)bvec->bv_len) - offset);
+			data = bvec_virt(bvec);
+			length -= avail;
+			in_buf.src = data + offset;
+			in_buf.size = avail;
+			in_buf.pos = 0;
+			offset = 0;
+		}
+
+		if (out_buf.pos == out_buf.size) {
+			out_buf.dst = squashfs_next_page(output);
+			if (IS_ERR(out_buf.dst)) {
+				error = PTR_ERR(out_buf.dst);
+				break;
+			} else if (out_buf.dst == NULL) {
+				/* Shouldn't run out of pages
+				 * before stream is done.
+				 */
+				error = -EIO;
+				break;
+			}
+			out_buf.pos = 0;
+			out_buf.size = PAGE_SIZE;
+		}
+
+		total_out -= out_buf.pos;
+		zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf);
+		total_out += out_buf.pos; /* add the additional data produced */
+		if (zstd_err == 0)
+			break;
+
+		if (zstd_is_error(zstd_err)) {
+			ERROR("zstd decompression error: %d\n",
+					(int)zstd_get_error_code(zstd_err));
+			error = -EIO;
+			break;
+		}
+	}
+
+finish:
+
+	squashfs_finish_page(output);
+
+	return error ? error : total_out;
+}
+
+const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+	.init = zstd_init,
+	.free = zstd_free,
+	.decompress = zstd_uncompress,
+	.id = ZSTD_COMPRESSION,
+	.name = "zstd",
+	.alloc_buffer = 1,
+	.supported = 1
+};