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

2 files changed, 99 insertions, 0 deletions

diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
new file mode 100644
index 000000000..7425d2b99
--- /dev/null
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -0,0 +1,69 @@
+#
+# Feature name:          membarrier-sync-core
+#         Kconfig:       ARCH_HAS_MEMBARRIER_SYNC_CORE
+#         description:   arch supports core serializing membarrier
+#
+# Architecture requirements
+#
+# * arm/arm64/powerpc/s390
+#
+# Rely on implicit context synchronization as a result of exception return
+# when returning from IPI handler, and when returning to user-space.
+#
+# * riscv
+#
+# riscv uses xRET as return from interrupt and to return to user-space.
+#
+# Given that xRET is not core serializing, we rely on FENCE.I for providing
+# core serialization:
+#
+#  - by calling sync_core_before_usermode() on return from interrupt (cf.
+#    ipi_sync_core()),
+#
+#  - via switch_mm() and sync_core_before_usermode() (respectively, for
+#    uthread->uthread and kthread->uthread transitions) before returning
+#    to user-space.
+#
+#  The serialization in switch_mm() is activated by prepare_sync_core_cmd().
+#
+# * x86
+#
+# x86-32 uses IRET as return from interrupt, which takes care of the IPI.
+# However, it uses both IRET and SYSEXIT to go back to user-space. The IRET
+# instruction is core serializing, but not SYSEXIT.
+#
+# x86-64 uses IRET as return from interrupt, which takes care of the IPI.
+# However, it can return to user-space through either SYSRETL (compat code),
+# SYSRETQ, or IRET.
+#
+# Given that neither SYSRET{L,Q}, nor SYSEXIT, are core serializing, we rely
+# instead on write_cr3() performed by switch_mm() to provide core serialization
+# after changing the current mm, and deal with the special case of kthread ->
+# uthread (temporarily keeping current mm into active_mm) by issuing a
+# sync_core_before_usermode() in that specific case.
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |        csky: | TODO |
+    |     hexagon: | TODO |
+    |   loongarch: | TODO |
+    |        m68k: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |       riscv: |  ok  |
+    |        s390: |  ok  |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |          um: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/sched/numa-balancing/arch-support.txt b/Documentation/features/sched/numa-balancing/arch-support.txt
new file mode 100644
index 000000000..984601c7c
--- /dev/null
+++ b/Documentation/features/sched/numa-balancing/arch-support.txt
@@ -0,0 +1,30 @@
+#
+# Feature name:          numa-balancing
+#         Kconfig:       ARCH_SUPPORTS_NUMA_BALANCING
+#         description:   arch supports NUMA balancing
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ..  |
+    |         arm: |  ..  |
+    |       arm64: |  ok  |
+    |        csky: |  ..  |
+    |     hexagon: |  ..  |
+    |   loongarch: |  ok  |
+    |        m68k: |  ..  |
+    |  microblaze: |  ..  |
+    |        mips: | TODO |
+    |       nios2: |  ..  |
+    |    openrisc: |  ..  |
+    |      parisc: |  ..  |
+    |     powerpc: |  ok  |
+    |       riscv: |  ok  |
+    |        s390: |  ok  |
+    |          sh: |  ..  |
+    |       sparc: | TODO |
+    |          um: |  ..  |
+    |         x86: |  ok  |
+    |      xtensa: |  ..  |
+    -----------------------