Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 15 Jun 2022 21:05:10 -0600
From:   Yu Zhao <yuzhao@google.com>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Marek Szyprowski <m.szyprowski@samsung.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Nicolas Saenz Julienne <nsaenzju@redhat.com>,
        Marcelo Tosatti <mtosatti@redhat.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Michal Hocko <mhocko@kernel.org>,
        Hugh Dickins <hughd@google.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Linux-MM <linux-mm@kvack.org>
Subject: Re: [PATCH 7/7] mm/page_alloc: Replace local_lock with normal
 spinlock
Message-ID: <Yqqd5nHeAT77C4D0@google.com>
References: <20220613125622.18628-1-mgorman@techsingularity.net>
 <20220613125622.18628-8-mgorman@techsingularity.net>
 <CGME20220615224855eucas1p1ea6d90c23ec9423dfe04b267f6dddd2a@eucas1p1.samsung.com>
 <e1c73640-3f29-bf57-b98d-84b1800cf4e3@samsung.com>
 <20220615160446.be1f75fd256d67e57b27a9fc@linux-foundation.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220615160446.be1f75fd256d67e57b27a9fc@linux-foundation.org>
Precedence: bulk

On Wed, Jun 15, 2022 at 04:04:46PM -0700, Andrew Morton wrote:
> On Thu, 16 Jun 2022 00:48:55 +0200 Marek Szyprowski <m.szyprowski@samsung.com> wrote:
> 
> > In the logs I see lots of errors like:
> > 
> > BUG: sleeping function called from invalid context at 
> > ./include/linux/sched/mm.h:274
> > 
> > BUG: scheduling while atomic: systemd-udevd/288/0x00000002
> > 
> > BUG: sleeping function called from invalid context at mm/filemap.c:2647
> > 
> > however there are also a fatal ones like:
> > 
> > Unable to handle kernel paging request at virtual address 00000000017a87b4
> > 
> > 
> > The issues seems to be a bit random. Looks like memory trashing. 
> > Reverting $subject on top of current linux-next fixes all those issues.
> > 
> > 
> 
> This?
> 
> --- a/mm/page_alloc.c~mm-page_alloc-replace-local_lock-with-normal-spinlock-fix
> +++ a/mm/page_alloc.c
> @@ -183,8 +183,10 @@ static DEFINE_MUTEX(pcp_batch_high_lock)
>  	type *_ret;							\
>  	pcpu_task_pin();						\
>  	_ret = this_cpu_ptr(ptr);					\
> -	if (!spin_trylock_irqsave(&_ret->member, flags))		\
> +	if (!spin_trylock_irqsave(&_ret->member, flags)) {		\
> +		pcpu_task_unpin();					\
>  		_ret = NULL;						\
> +	}								\
>  	_ret;								\
>  })
>  
> 
> I'll drop Mel's patch for next -next.

While we are at it, please consider this cleanup:

 mm/page_alloc.c | 48 +++++++++---------------------------------------
 1 file changed, 9 insertions(+), 39 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e538dde2c1c0..a1b76d5fdf75 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -160,61 +160,31 @@ static DEFINE_MUTEX(pcp_batch_high_lock);
  * Generic helper to lookup and a per-cpu variable with an embedded spinlock.
  * Return value should be used with equivalent unlock helper.
  */
-#define pcpu_spin_lock(type, member, ptr)				\
-({									\
-	type *_ret;							\
-	pcpu_task_pin();						\
-	_ret = this_cpu_ptr(ptr);					\
-	spin_lock(&_ret->member);					\
-	_ret;								\
-})
-
-#define pcpu_spin_lock_irqsave(type, member, ptr, flags)		\
-({									\
-	type *_ret;							\
-	pcpu_task_pin();						\
-	_ret = this_cpu_ptr(ptr);					\
-	spin_lock_irqsave(&_ret->member, flags);			\
-	_ret;								\
-})
-
-#define pcpu_spin_trylock_irqsave(type, member, ptr, flags)		\
-({									\
-	type *_ret;							\
-	pcpu_task_pin();						\
-	_ret = this_cpu_ptr(ptr);					\
-	if (!spin_trylock_irqsave(&_ret->member, flags))		\
-		_ret = NULL;						\
-	_ret;								\
-})
-
-#define pcpu_spin_unlock(member, ptr)					\
-({									\
-	spin_unlock(&ptr->member);					\
-	pcpu_task_unpin();						\
-})
-
-#define pcpu_spin_unlock_irqrestore(member, ptr, flags)			\
-({									\
-	spin_unlock_irqrestore(&ptr->member, flags);			\
-	pcpu_task_unpin();						\
-})
-
-/* struct per_cpu_pages specific helpers. */
-#define pcp_spin_lock(ptr)						\
-	pcpu_spin_lock(struct per_cpu_pages, lock, ptr)
-
 #define pcp_spin_lock_irqsave(ptr, flags)				\
-	pcpu_spin_lock_irqsave(struct per_cpu_pages, lock, ptr, flags)
+({									\
+	struct per_cpu_pages *_ret;					\
+	pcpu_task_pin();						\
+	_ret = this_cpu_ptr(ptr);					\
+	spin_lock_irqsave(&_ret->lock, flags);				\
+	_ret;								\
+})
 
 #define pcp_spin_trylock_irqsave(ptr, flags)				\
-	pcpu_spin_trylock_irqsave(struct per_cpu_pages, lock, ptr, flags)
-
-#define pcp_spin_unlock(ptr)						\
-	pcpu_spin_unlock(lock, ptr)
+({									\
+	struct per_cpu_pages *_ret;					\
+	pcpu_task_pin();						\
+	_ret = this_cpu_ptr(ptr);					\
+	if (!spin_trylock_irqsave(&_ret->lock, flags))			\
+		_ret = NULL;						\
+	_ret;								\
+})
 
 #define pcp_spin_unlock_irqrestore(ptr, flags)				\
-	pcpu_spin_unlock_irqrestore(lock, ptr, flags)
+({									\
+	spin_unlock_irqrestore(&ptr->lock, flags);			\
+	pcpu_task_unpin();						\
+})
+
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -3488,7 +3458,7 @@ void free_unref_page(struct page *page, unsigned int order)
 
 	zone = page_zone(page);
 	pcp_trylock_prepare(UP_flags);
-	pcp = pcpu_spin_trylock_irqsave(struct per_cpu_pages, lock, zone->per_cpu_pageset, flags);
+	pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags);
 	if (pcp) {
 		free_unref_page_commit(pcp, zone, page, migratetype, order);
 		pcp_spin_unlock_irqrestore(pcp, flags);