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, 96 insertions, 0 deletions

diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
new file mode 100644
index 000000000..81a0f3f6f
--- /dev/null
+++ b/drivers/block/zram/zcomp.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _ZCOMP_H_
+#define _ZCOMP_H_
+
+#include <linux/mutex.h>
+
+#define ZCOMP_PARAM_NOT_SET	INT_MIN
+
+struct deflate_params {
+	s32 winbits;
+};
+
+/*
+ * Immutable driver (backend) parameters. The driver may attach private
+ * data to it (e.g. driver representation of the dictionary, etc.).
+ *
+ * This data is kept per-comp and is shared among execution contexts.
+ */
+struct zcomp_params {
+	void *dict;
+	size_t dict_sz;
+	s32 level;
+	union {
+		struct deflate_params deflate;
+	};
+
+	void *drv_data;
+};
+
+/*
+ * Run-time driver context - scratch buffers, etc. It is modified during
+ * request execution (compression/decompression), cannot be shared, so
+ * it's in per-CPU area.
+ */
+struct zcomp_ctx {
+	void *context;
+};
+
+struct zcomp_strm {
+	struct mutex lock;
+	/* compression buffer */
+	void *buffer;
+	/* local copy of handle memory */
+	void *local_copy;
+	struct zcomp_ctx ctx;
+};
+
+struct zcomp_req {
+	const unsigned char *src;
+	const size_t src_len;
+
+	unsigned char *dst;
+	size_t dst_len;
+};
+
+struct zcomp_ops {
+	int (*compress)(struct zcomp_params *params, struct zcomp_ctx *ctx,
+			struct zcomp_req *req);
+	int (*decompress)(struct zcomp_params *params, struct zcomp_ctx *ctx,
+			  struct zcomp_req *req);
+
+	int (*create_ctx)(struct zcomp_params *params, struct zcomp_ctx *ctx);
+	void (*destroy_ctx)(struct zcomp_ctx *ctx);
+
+	int (*setup_params)(struct zcomp_params *params);
+	void (*release_params)(struct zcomp_params *params);
+
+	const char *name;
+};
+
+/* dynamic per-device compression frontend */
+struct zcomp {
+	struct zcomp_strm __percpu *stream;
+	const struct zcomp_ops *ops;
+	struct zcomp_params *params;
+	struct hlist_node node;
+};
+
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node);
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node);
+ssize_t zcomp_available_show(const char *comp, char *buf, ssize_t at);
+const char *zcomp_lookup_backend_name(const char *comp);
+
+struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params);
+void zcomp_destroy(struct zcomp *comp);
+
+struct zcomp_strm *zcomp_stream_get(struct zcomp *comp);
+void zcomp_stream_put(struct zcomp_strm *zstrm);
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		   const void *src, unsigned int *dst_len);
+int zcomp_decompress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		     const void *src, unsigned int src_len, void *dst);
+
+#endif /* _ZCOMP_H_ */