kasan: fix sleeping function called from invalid context on RT kernel

BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0
preempt_count: 1, expected: 0
...........
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.1-rt16-yocto-preempt-rt #22
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009),
BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x60/0x8c
dump_stack+0x10/0x12
 __might_resched.cold+0x13b/0x173
rt_spin_lock+0x5b/0xf0
 ___cache_free+0xa5/0x180
qlist_free_all+0x7a/0x160
per_cpu_remove_cache+0x5f/0x70
smp_call_function_many_cond+0x4c4/0x4f0
on_each_cpu_cond_mask+0x49/0xc0
kasan_quarantine_remove_cache+0x54/0xf0
kasan_cache_shrink+0x9/0x10
kmem_cache_shrink+0x13/0x20
acpi_os_purge_cache+0xe/0x20
acpi_purge_cached_objects+0x21/0x6d
acpi_initialize_objects+0x15/0x3b
acpi_init+0x130/0x5ba
do_one_initcall+0xe5/0x5b0
kernel_init_freeable+0x34f/0x3ad
kernel_init+0x1e/0x140
ret_from_fork+0x22/0x30

When the kmem_cache_shrink() was called, the IPI was triggered, the
___cache_free() is called in IPI interrupt context, the local-lock or
spin-lock will be acquired.  On PREEMPT_RT kernel, these locks are
replaced with sleepbale rt-spinlock, so the above problem is triggered.
Fix it by moving the qlist_free_allfrom() from IPI interrupt context to
task context when PREEMPT_RT is enabled.

Link: https://lkml.kernel.org/r/20220401134649.2222485-1-qiang1.zhang@intel.com
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 08291ed33e93af757e436b8e2efbe626d50c1f79..0e33d30abb8d2035f1db8023d78c1a5fe0e66733 100644 (file)
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -99,6 +99,17 @@ static unsigned long quarantine_size;
 static DEFINE_RAW_SPINLOCK(quarantine_lock);
 DEFINE_STATIC_SRCU(remove_cache_srcu);
 
+#ifdef CONFIG_PREEMPT_RT
+struct cpu_shrink_qlist {
+       raw_spinlock_t lock;
+       struct qlist_head qlist;
+};
+
+static DEFINE_PER_CPU(struct cpu_shrink_qlist, shrink_qlist) = {
+       .lock = __RAW_SPIN_LOCK_UNLOCKED(shrink_qlist.lock),
+};
+#endif
+
 /* Maximum size of the global queue. */
 static unsigned long quarantine_max_size;
 
@@ -311,12 +322,23 @@ static void qlist_move_cache(struct qlist_head *from,
 static void per_cpu_remove_cache(void *arg)
 {
        struct kmem_cache *cache = arg;
-       struct qlist_head to_free = QLIST_INIT;
        struct qlist_head *q;
-
+#ifndef CONFIG_PREEMPT_RT
+       struct qlist_head to_free = QLIST_INIT;
+#else
+       unsigned long flags;
+       struct cpu_shrink_qlist *sq;
+#endif
        q = this_cpu_ptr(&cpu_quarantine);
+#ifndef CONFIG_PREEMPT_RT
        qlist_move_cache(q, &to_free, cache);
        qlist_free_all(&to_free, cache);
+#else
+       sq = this_cpu_ptr(&shrink_qlist);
+       raw_spin_lock_irqsave(&sq->lock, flags);
+       qlist_move_cache(q, &sq->qlist, cache);
+       raw_spin_unlock_irqrestore(&sq->lock, flags);
+#endif
 }
 
 /* Free all quarantined objects belonging to cache. */
@@ -324,6 +346,10 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache)
 {
        unsigned long flags, i;
        struct qlist_head to_free = QLIST_INIT;
+#ifdef CONFIG_PREEMPT_RT
+       int cpu;
+       struct cpu_shrink_qlist *sq;
+#endif
 
        /*
         * Must be careful to not miss any objects that are being moved from
@@ -334,6 +360,16 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache)
         */
        on_each_cpu(per_cpu_remove_cache, cache, 1);
 
+#ifdef CONFIG_PREEMPT_RT
+       for_each_online_cpu(cpu) {
+               sq = per_cpu_ptr(&shrink_qlist, cpu);
+               raw_spin_lock_irqsave(&sq->lock, flags);
+               qlist_move_cache(&sq->qlist, &to_free, cache);
+               raw_spin_unlock_irqrestore(&sq->lock, flags);
+       }
+       qlist_free_all(&to_free, cache);
+#endif
+
        raw_spin_lock_irqsave(&quarantine_lock, flags);
        for (i = 0; i < QUARANTINE_BATCHES; i++) {
                if (qlist_empty(&global_quarantine[i]))