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, 88 insertions, 0 deletions

diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
new file mode 100644
index 000000000..0f0f2d851
--- /dev/null
+++ b/arch/powerpc/lib/pmem.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2017 IBM Corporation. All rights reserved.
+ */
+
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <linux/libnvdimm.h>
+
+#include <asm/cacheflush.h>
+
+static inline void __clean_pmem_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		asm volatile(PPC_DCBSTPS(%0, %1): :"i"(0), "r"(addr): "memory");
+}
+
+static inline void __flush_pmem_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		asm volatile(PPC_DCBFPS(%0, %1): :"i"(0), "r"(addr): "memory");
+}
+
+static inline void clean_pmem_range(unsigned long start, unsigned long stop)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		return __clean_pmem_range(start, stop);
+}
+
+static inline void flush_pmem_range(unsigned long start, unsigned long stop)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		return __flush_pmem_range(start, stop);
+}
+
+/*
+ * CONFIG_ARCH_HAS_PMEM_API symbols
+ */
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	clean_pmem_range(start, start + size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	flush_pmem_range(start, start + size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+
+/*
+ * CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE symbols
+ */
+size_t copy_from_user_flushcache(void *dest, const void __user *src,
+				 size_t size)
+{
+	unsigned long not_copied, start = (unsigned long) dest;
+
+	src = mask_user_address(src);
+	not_copied = __copy_from_user(dest, src, size);
+	clean_pmem_range(start, start + size);
+
+	return not_copied;
+}
+
+void memcpy_flushcache(void *dest, const void *src, size_t size)
+{
+	unsigned long start = (unsigned long) dest;
+
+	memcpy(dest, src, size);
+	clean_pmem_range(start, start + size);
+}
+EXPORT_SYMBOL(memcpy_flushcache);