Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Michal Hocko <mhocko@kernel.org>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	Mel Gorman <mgorman@techsingularity.net>,
	Johannes Weiner <hannes@cmpxchg.org>,
	linux-block@vger.kernel.org, nbd-general@lists.sourceforge.net,
	open-iscsi@googlegroups.com, linux-scsi@vger.kernel.org,
	netdev@vger.kernel.org
Subject: Re: [PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore}
Date: Wed, 5 Apr 2017 13:28:18 +0200
Message-ID: <20170405112817.GK6035@dhcp22.suse.cz> (raw)
In-Reply-To: <20170405074700.29871-3-vbabka@suse.cz>

On Wed 05-04-17 09:46:58, Vlastimil Babka wrote:
> The previous patch has shown that simply setting and clearing PF_MEMALLOC in
> current->flags can result in wrongly clearing a pre-existing PF_MEMALLOC flag
> and potentially lead to recursive reclaim. Let's introduce helpers that support
> proper nesting by saving the previous stat of the flag, similar to the existing
> memalloc_noio_* and memalloc_nofs_* helpers. Convert existing setting/clearing
> of PF_MEMALLOC within mm to the new helpers.
> 
> There are no known issues with the converted code, but the change makes it more
> robust.
> 
> Suggested-by: Michal Hocko <mhocko@suse.com>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

One could argue that tsk_restore_flags() could be extended to provide
tsk_set_flags() and use it for all allocation related PF flags. I do not
have a strong opinion on that but explicit API sounds a bit better to me
because is easier to follow (at least for me). If others think that
generic API would be better then I won't have any objections. Anyway
this looks good to me.
Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  include/linux/sched/mm.h | 12 ++++++++++++
>  mm/page_alloc.c          | 11 ++++++-----
>  mm/vmscan.c              | 17 +++++++++++------
>  3 files changed, 29 insertions(+), 11 deletions(-)
> 
> diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
> index 9daabe138c99..2b24a6974847 100644
> --- a/include/linux/sched/mm.h
> +++ b/include/linux/sched/mm.h
> @@ -191,4 +191,16 @@ static inline void memalloc_nofs_restore(unsigned int flags)
>  	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
>  }
>  
> +static inline unsigned int memalloc_noreclaim_save(void)
> +{
> +	unsigned int flags = current->flags & PF_MEMALLOC;
> +	current->flags |= PF_MEMALLOC;
> +	return flags;
> +}
> +
> +static inline void memalloc_noreclaim_restore(unsigned int flags)
> +{
> +	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
> +}
> +
>  #endif /* _LINUX_SCHED_MM_H */
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index b84e6ffbe756..037e32dccd7a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3288,15 +3288,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
>  		enum compact_priority prio, enum compact_result *compact_result)
>  {
>  	struct page *page;
> -	unsigned int noreclaim_flag = current->flags & PF_MEMALLOC;
> +	unsigned int noreclaim_flag;
>  
>  	if (!order)
>  		return NULL;
>  
> -	current->flags |= PF_MEMALLOC;
> +	noreclaim_flag = memalloc_noreclaim_save();
>  	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
>  									prio);
> -	current->flags = (current->flags & ~PF_MEMALLOC) | noreclaim_flag;
> +	memalloc_noreclaim_restore(noreclaim_flag);
>  
>  	if (*compact_result <= COMPACT_INACTIVE)
>  		return NULL;
> @@ -3443,12 +3443,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
>  {
>  	struct reclaim_state reclaim_state;
>  	int progress;
> +	unsigned int noreclaim_flag;
>  
>  	cond_resched();
>  
>  	/* We now go into synchronous reclaim */
>  	cpuset_memory_pressure_bump();
> -	current->flags |= PF_MEMALLOC;
> +	noreclaim_flag = memalloc_noreclaim_save();
>  	lockdep_set_current_reclaim_state(gfp_mask);
>  	reclaim_state.reclaimed_slab = 0;
>  	current->reclaim_state = &reclaim_state;
> @@ -3458,7 +3459,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
>  
>  	current->reclaim_state = NULL;
>  	lockdep_clear_current_reclaim_state();
> -	current->flags &= ~PF_MEMALLOC;
> +	memalloc_noreclaim_restore(noreclaim_flag);
>  
>  	cond_resched();
>  
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 58615bb27f2f..ff63b91a0f48 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2992,6 +2992,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
>  	struct zonelist *zonelist;
>  	unsigned long nr_reclaimed;
>  	int nid;
> +	unsigned int noreclaim_flag;
>  	struct scan_control sc = {
>  		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
>  		.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
> @@ -3018,9 +3019,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
>  					    sc.gfp_mask,
>  					    sc.reclaim_idx);
>  
> -	current->flags |= PF_MEMALLOC;
> +	noreclaim_flag = memalloc_noreclaim_save();
>  	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
> -	current->flags &= ~PF_MEMALLOC;
> +	memalloc_noreclaim_restore(noreclaim_flag);
>  
>  	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
>  
> @@ -3544,8 +3545,9 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
>  	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
>  	struct task_struct *p = current;
>  	unsigned long nr_reclaimed;
> +	unsigned int noreclaim_flag;
>  
> -	p->flags |= PF_MEMALLOC;
> +	noreclaim_flag = memalloc_noreclaim_save();
>  	lockdep_set_current_reclaim_state(sc.gfp_mask);
>  	reclaim_state.reclaimed_slab = 0;
>  	p->reclaim_state = &reclaim_state;
> @@ -3554,7 +3556,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
>  
>  	p->reclaim_state = NULL;
>  	lockdep_clear_current_reclaim_state();
> -	p->flags &= ~PF_MEMALLOC;
> +	memalloc_noreclaim_restore(noreclaim_flag);
>  
>  	return nr_reclaimed;
>  }
> @@ -3719,6 +3721,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
>  	struct task_struct *p = current;
>  	struct reclaim_state reclaim_state;
>  	int classzone_idx = gfp_zone(gfp_mask);
> +	unsigned int noreclaim_flag;
>  	struct scan_control sc = {
>  		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
>  		.gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)),
> @@ -3736,7 +3739,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
>  	 * and we also need to be able to write out pages for RECLAIM_WRITE
>  	 * and RECLAIM_UNMAP.
>  	 */
> -	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
> +	noreclaim_flag = memalloc_noreclaim_save();
> +	p->flags |= PF_SWAPWRITE;
>  	lockdep_set_current_reclaim_state(gfp_mask);
>  	reclaim_state.reclaimed_slab = 0;
>  	p->reclaim_state = &reclaim_state;
> @@ -3752,7 +3756,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
>  	}
>  
>  	p->reclaim_state = NULL;
> -	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
> +	current->flags &= ~PF_SWAPWRITE;
> +	memalloc_noreclaim_restore(noreclaim_flag);
>  	lockdep_clear_current_reclaim_state();
>  	return sc.nr_reclaimed >= nr_pages;
>  }
> -- 
> 2.12.2

-- 
Michal Hocko
SUSE Labs

  reply index

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-05  7:46 [PATCH 0/4] more robust PF_MEMALLOC handling Vlastimil Babka
2017-04-05  7:46 ` [PATCH 1/4] mm: prevent potential recursive reclaim due to clearing PF_MEMALLOC Vlastimil Babka
2017-04-05 11:21   ` Michal Hocko
2017-04-05 11:40   ` Andrey Ryabinin
2017-04-07  9:21     ` Vlastimil Babka
2017-04-07  7:33   ` Hillf Danton
2017-04-05  7:46 ` [PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore} Vlastimil Babka
2017-04-05 11:28   ` Michal Hocko [this message]
2017-04-07  7:38   ` Hillf Danton
2017-04-05  7:46 ` [PATCH 3/4] treewide: convert PF_MEMALLOC manipulations to new helpers Vlastimil Babka
2017-04-05 11:30   ` Michal Hocko
2017-04-06  6:38     ` [Nbd] " Wouter Verhelst
2017-04-06 11:25       ` Mel Gorman
2017-04-05  7:47 ` [PATCH 4/4] mtd: nand: nandsim: convert to memalloc_noreclaim_*() Vlastimil Babka
2017-04-05 11:31   ` Michal Hocko
2017-04-05 11:36     ` Richard Weinberger
2017-04-05 11:39       ` Vlastimil Babka
2017-04-05 12:09         ` Michal Hocko
2017-04-06  6:33         ` Adrian Hunter
2017-04-06  7:27           ` Michal Hocko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170405112817.GK6035@dhcp22.suse.cz \
    --to=mhocko@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=nbd-general@lists.sourceforge.net \
    --cc=netdev@vger.kernel.org \
    --cc=open-iscsi@googlegroups.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org
	public-inbox-index linux-block

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git