Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1616659 > unrolled thread

[PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore}

Started byVlastimil Babka <vbabka@suse.cz>
First post2017-04-05 09:50 +0200
Last post2017-04-07 09:40 +0200
Articles 3 — 3 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore} Vlastimil Babka <vbabka@suse.cz> - 2017-04-05 09:50 +0200
    Re: [PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore} Michal Hocko <mhocko@kernel.org> - 2017-04-05 13:40 +0200
    Re: [PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore} "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2017-04-07 09:40 +0200

#1616659 — [PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore}

FromVlastimil Babka <vbabka@suse.cz>
Date2017-04-05 09:50 +0200
Subject[PATCH 2/4] mm: introduce memalloc_noreclaim_{save,restore}
Message-ID<tsNRv-89c-1@gated-at.bofh.it>
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>
---
 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

[toc] | [next] | [standalone]

#1616861

FromMichal Hocko <mhocko@kernel.org>
Date2017-04-05 13:40 +0200
Message-ID<tsRs6-22m-25@gated-at.bofh.it>
In reply to#1616659
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

[toc] | [prev] | [next] | [standalone]

#1618534

From"Hillf Danton" <hillf.zj@alibaba-inc.com>
Date2017-04-07 09:40 +0200
Message-ID<ttwEV-474-13@gated-at.bofh.it>
In reply to#1616659
On April 05, 2017 3:47 PM 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>
> ---

Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web