Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
Date:   Fri, 15 Apr 2022 11:34:56 -0700
From:   Andrew Morton <akpm@linux-foundation.org>
To:     Zqiang <qiang1.zhang@intel.com>
Cc:     ryabinin.a.a@gmail.com, glider@google.com, andreyknvl@gmail.com,
        dvyukov@google.com, bigeasy@linutronix.de,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH v2] kasan: Fix sleeping function called from invalid
 context on RT kernel
Message-Id: <20220415113456.2f24660a610e4f35fd72970a@linux-foundation.org>
In-Reply-To: <20220401134649.2222485-1-qiang1.zhang@intel.com>
References: <20220401134649.2222485-1-qiang1.zhang@intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Precedence: bulk

On Fri,  1 Apr 2022 21:46:49 +0800 Zqiang <qiang1.zhang@intel.com> wrote:

> When the kmem_cache_shrink() be 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 lock is
> replaced with sleepbale rt-spinlock, so the above problem is triggered.
> fix it by move the qlist_free_allfrom() the IPI interrupt context
> to the task context when PREEMPT_RT is enabled.

This patch is rather ifdeffy so I propose the below cleanup.  Please
review and test?

Note that it incorporates the changes from your
https://lkml.kernel.org/r/20220414025925.2423818-1-qiang1.zhang@intel.com

btw, how are we supposed to test PREEMPT_RT builds?  I had to patch
arch/Kconfig.

--- a/mm/kasan/quarantine.c~kasan-fix-sleeping-function-called-from-invalid-context-on-rt-kernel-fix
+++ a/mm/kasan/quarantine.c
@@ -319,28 +319,37 @@ static void qlist_move_cache(struct qlis
 	}
 }
 
-static void per_cpu_remove_cache(void *arg)
+#ifndef CONFIG_PREEMPT_RT
+static void __per_cpu_remove_cache(struct qlist_head *q, void *arg)
 {
 	struct kmem_cache *cache = arg;
-	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
-	if (READ_ONCE(q->offline))
-		return;
+
 	qlist_move_cache(q, &to_free, cache);
 	qlist_free_all(&to_free, cache);
+}
 #else
+static void __per_cpu_remove_cache(struct qlist_head *q, void *arg)
+{
+	struct kmem_cache *cache = arg;
+	unsigned long flags;
+	struct cpu_shrink_qlist *sq;
+
 	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
+
+static void per_cpu_remove_cache(void *arg)
+{
+	struct qlist_head *q;
+
+	q = this_cpu_ptr(&cpu_quarantine);
+	if (READ_ONCE(q->offline))
+		return;
+	__per_cpu_remove_cache(q, arg);
 }
 
 /* Free all quarantined objects belonging to cache. */
@@ -348,10 +357,6 @@ void kasan_quarantine_remove_cache(struc
 {
 	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
@@ -363,13 +368,18 @@ void kasan_quarantine_remove_cache(struc
 	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);
+	{
+		int cpu;
+		struct cpu_shrink_qlist *sq;
+
+		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);
 	}
-	qlist_free_all(&to_free, cache);
 #endif
 
 	raw_spin_lock_irqsave(&quarantine_lock, flags);
_