[PATCH 1/2] mm: use kvzalloc for swap_info_struct allocation

[PATCH 1/2] mm: use kvzalloc for swap_info_struct allocation

[Vasily Averin]

commit a2468cc9bfdf ("swap: choose swap device according to numa node")
increased size of swap_info_struct up to 44 Kbytes, now it requires 4th order page.
Switch to kvzmalloc allows to avoid unexpected allocation failures.

Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
---
 mm/swapfile.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 644f746e167a..8688ae65ef58 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	unsigned int type;
 	int i;
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	p = kvzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
@@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	}
 	if (type >= MAX_SWAPFILES) {
 		spin_unlock(&swap_lock);
-		kfree(p);
+		kvfree(p);
 		return ERR_PTR(-EPERM);
 	}
 	if (type >= nr_swapfiles) {
@@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 		smp_wmb();
 		nr_swapfiles++;
 	} else {
-		kfree(p);
+		kvfree(p);
 		p = swap_info[type];
 		/*
 		 * Do not memset this entry: a racing procfs swap_next()
-- 
2.17.1

Re: [PATCH 1/2] mm: use kvzalloc for swap_info_struct allocation

[Huang, Ying]

Vasily Averin <vvs@virtuozzo.com> writes:

> commit a2468cc9bfdf ("swap: choose swap device according to numa node")
> increased size of swap_info_struct up to 44 Kbytes, now it requires
> 4th order page.

Why swap_info_struct could be so large?  Because MAX_NUMNODES could be
thousands so that 'avail_lists' field could be tens KB?  If so, I think
it's fair to use kvzalloc().  Can you add one line comment?  Because
struct swap_info_struct is quite small in default configuration.

Best Regards,
Huang, Ying

> Switch to kvzmalloc allows to avoid unexpected allocation failures.
>
> Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
> ---
>  mm/swapfile.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 644f746e167a..8688ae65ef58 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void)
>  	unsigned int type;
>  	int i;
>  
> -	p = kzalloc(sizeof(*p), GFP_KERNEL);
> +	p = kvzalloc(sizeof(*p), GFP_KERNEL);
>  	if (!p)
>  		return ERR_PTR(-ENOMEM);
>  
> @@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void)
>  	}
>  	if (type >= MAX_SWAPFILES) {
>  		spin_unlock(&swap_lock);
> -		kfree(p);
> +		kvfree(p);
>  		return ERR_PTR(-EPERM);
>  	}
>  	if (type >= nr_swapfiles) {
> @@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void)
>  		smp_wmb();
>  		nr_swapfiles++;
>  	} else {
> -		kfree(p);
> +		kvfree(p);
>  		p = swap_info[type];
>  		/*
>  		 * Do not memset this entry: a racing procfs swap_next()

Re: [PATCH 1/2] mm: use kvzalloc for swap_info_struct allocation

[Vasily Averin]

On 11/5/18 3:50 AM, Huang, Ying wrote:
> Vasily Averin <vvs@virtuozzo.com> writes:
> 
>> commit a2468cc9bfdf ("swap: choose swap device according to numa node")
>> increased size of swap_info_struct up to 44 Kbytes, now it requires
>> 4th order page.
> 
> Why swap_info_struct could be so large?  Because MAX_NUMNODES could be
> thousands so that 'avail_lists' field could be tens KB?  If so, I think
> it's fair to use kvzalloc().  Can you add one line comment?  Because
> struct swap_info_struct is quite small in default configuration.

I was incorrect not 44Kb but 40kb should be here.
We have found CONFIG_NODES_SHIFT=10 in new RHEL7 update 6 kernel,
default ubuntu kernels have the same setting too.

crash> struct swap_info_struct -o
struct swap_info_struct {
      [0] unsigned long flags;
      [8] short prio;
           ...
    [140] spinlock_t lock;
    [144] struct plist_node list;
    [184] struct plist_node avail_lists[1024]; <<<< here
  [41144] struct swap_cluster_info *cluster_info;
  [41152] struct swap_cluster_list free_clusters;
          ...
  [41224] spinlock_t cont_lock;
}
SIZE: 41232

struct swap_info_struct {
        ...
        RH_KABI_EXTEND(struct plist_node avail_lists[MAX_NUMNODES]) /* entry in swap_avail_head */
        ...
}

#define MAX_NUMNODES    (1 << NODES_SHIFT)

#ifdef CONFIG_NODES_SHIFT 
#define NODES_SHIFT     CONFIG_NODES_SHIFT
#else
#define NODES_SHIFT     0
#endif

/boot/config-4.15.0-38-generic:CONFIG_NODES_SHIFT=10

Re: [PATCH 1/2] mm: use kvzalloc for swap_info_struct allocation

[Huang, Ying]

Vasily Averin <vvs@virtuozzo.com> writes:

> On 11/5/18 3:50 AM, Huang, Ying wrote:
>> Vasily Averin <vvs@virtuozzo.com> writes:
>> 
>>> commit a2468cc9bfdf ("swap: choose swap device according to numa node")
>>> increased size of swap_info_struct up to 44 Kbytes, now it requires
>>> 4th order page.
>> 
>> Why swap_info_struct could be so large?  Because MAX_NUMNODES could be
>> thousands so that 'avail_lists' field could be tens KB?  If so, I think
>> it's fair to use kvzalloc().  Can you add one line comment?  Because
>> struct swap_info_struct is quite small in default configuration.
>
> I was incorrect not 44Kb but 40kb should be here.
> We have found CONFIG_NODES_SHIFT=10 in new RHEL7 update 6 kernel,
> default ubuntu kernels have the same setting too.
>
> crash> struct swap_info_struct -o
> struct swap_info_struct {
>       [0] unsigned long flags;
>       [8] short prio;
>            ...
>     [140] spinlock_t lock;
>     [144] struct plist_node list;
>     [184] struct plist_node avail_lists[1024]; <<<< here
>   [41144] struct swap_cluster_info *cluster_info;
>   [41152] struct swap_cluster_list free_clusters;
>           ...
>   [41224] spinlock_t cont_lock;
> }
> SIZE: 41232
>
> struct swap_info_struct {
>         ...
>         RH_KABI_EXTEND(struct plist_node avail_lists[MAX_NUMNODES]) /* entry in swap_avail_head */
>         ...
> }
>
> #define MAX_NUMNODES    (1 << NODES_SHIFT)
>
> #ifdef CONFIG_NODES_SHIFT 
> #define NODES_SHIFT     CONFIG_NODES_SHIFT
> #else
> #define NODES_SHIFT     0
> #endif
>
> /boot/config-4.15.0-38-generic:CONFIG_NODES_SHIFT=10

I see.  So this is a more practical issue than my original imagination.

But for default config, I mean

$ make defconfig

And it turns out,

CONFIG_NODES_SHIFT=6

Best Regards,
Huang, Ying

Re: [PATCH 1/2] mm: use kvzalloc for swap_info_struct allocation

[Aaron Lu]

On Mon, Nov 05, 2018 at 07:59:13AM +0300, Vasily Averin wrote:
> 
> 
> On 11/5/18 3:50 AM, Huang, Ying wrote:
> > Vasily Averin <vvs@virtuozzo.com> writes:
> > 
> >> commit a2468cc9bfdf ("swap: choose swap device according to numa node")
> >> increased size of swap_info_struct up to 44 Kbytes, now it requires
> >> 4th order page.
> > 
> > Why swap_info_struct could be so large?  Because MAX_NUMNODES could be
> > thousands so that 'avail_lists' field could be tens KB?  If so, I think
> > it's fair to use kvzalloc().  Can you add one line comment?  Because
> > struct swap_info_struct is quite small in default configuration.
> 
> I was incorrect not 44Kb but 40kb should be here.
> We have found CONFIG_NODES_SHIFT=10 in new RHEL7 update 6 kernel,
> default ubuntu kernels have the same setting too.
> 
> crash> struct swap_info_struct -o
> struct swap_info_struct {
>       [0] unsigned long flags;
>       [8] short prio;
>            ...
>     [140] spinlock_t lock;
>     [144] struct plist_node list;
>     [184] struct plist_node avail_lists[1024]; <<<< here

So every 'struct plist_node' takes 40 bytes and 1024 of them take a
total of 40960 bytes, which is 10 pages and need an order-4 page to host
them. It looks a little too much, especially consider most of the space
will left be unused since most systems have nodes <= 4. I didn't realize
this problem when developing this patch, thanks for pointing this out.

I think using kvzalloc() as is done by your patch is better here as it
can avoid possible failure of swapon.

Acked-by: Aaron Lu <aaron.lu@intel.com>

BTW, for systems with few swap devices this may not be a big deal, but
according to your description, your workload will create a lot of swap
devices and each of them will likely cause an order-4 unmovable pages
allocated(when kvzalloc() doesn't fallback). I was thinking maybe we
should convert avail_lists to a pointer in swap_info_struct and use
vzalloc() for it.

Thanks,
Aaron

>   [41144] struct swap_cluster_info *cluster_info;
>   [41152] struct swap_cluster_list free_clusters;
>           ...
>   [41224] spinlock_t cont_lock;
> }
> SIZE: 41232
> 
> struct swap_info_struct {
>         ...
>         RH_KABI_EXTEND(struct plist_node avail_lists[MAX_NUMNODES]) /* entry in swap_avail_head */
>         ...
> }
> 
> #define MAX_NUMNODES    (1 << NODES_SHIFT)
> 
> #ifdef CONFIG_NODES_SHIFT 
> #define NODES_SHIFT     CONFIG_NODES_SHIFT
> #else
> #define NODES_SHIFT     0
> #endif
> 
> /boot/config-4.15.0-38-generic:CONFIG_NODES_SHIFT=10
> 

[PATCH v2] mm: use kvzalloc for swap_info_struct allocation

[Vasily Averin]

commit a2468cc9bfdf ("swap: choose swap device according to numa node")
changed 'avail_lists' field of 'struct swap_info_struct' to an array.
In popular linux distros it increased size of swap_info_struct up to
40 Kbytes and now swap_info_struct allocation requires order-4 page.
Switch to kvzmalloc allows to avoid unexpected allocation failures.

Acked-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
---
 mm/swapfile.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 644f746e167a..8688ae65ef58 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	unsigned int type;
 	int i;
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	p = kvzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
@@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	}
 	if (type >= MAX_SWAPFILES) {
 		spin_unlock(&swap_lock);
-		kfree(p);
+		kvfree(p);
 		return ERR_PTR(-EPERM);
 	}
 	if (type >= nr_swapfiles) {
@@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 		smp_wmb();
 		nr_swapfiles++;
 	} else {
-		kfree(p);
+		kvfree(p);
 		p = swap_info[type];
 		/*
 		 * Do not memset this entry: a racing procfs swap_next()
-- 
2.17.1

Re: [PATCH v2] mm: use kvzalloc for swap_info_struct allocation

[Michal Hocko]

On Mon 05-11-18 14:17:01, Vasily Averin wrote:
> commit a2468cc9bfdf ("swap: choose swap device according to numa node")
> changed 'avail_lists' field of 'struct swap_info_struct' to an array.
> In popular linux distros it increased size of swap_info_struct up to
> 40 Kbytes and now swap_info_struct allocation requires order-4 page.
> Switch to kvzmalloc allows to avoid unexpected allocation failures.

While this fixes the most visible issue is this a good long term
solution? Aren't we wasting memory without a good reason? IIRC our limit
for swap files/devices is much smaller than potential NUMA nodes numbers
so we can safely expect that would be only few numa affine nodes. I am
not really familiar with the rework which has added numa node awareness
but I wouls assueme that we should either go with one global table with
a linked list of possible swap_info structure per numa node or use a
sparse array.

That being said I am not really objecting to this patch as it is simple
and backportable to older (stable kernels).
 
I would even dare to add
Fixes: a2468cc9bfdf ("swap: choose swap device according to numa node")

because not being able to add a swap space on a fragmented system looks
like a regression to me.

> Acked-by: Aaron Lu <aaron.lu@intel.com>
> Signed-off-by: Vasily Averin <vvs@virtuozzo.com>

Acked-by: Michal Hocko <mhocko@suse.com>
> ---
>  mm/swapfile.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 644f746e167a..8688ae65ef58 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void)
>  	unsigned int type;
>  	int i;
>  
> -	p = kzalloc(sizeof(*p), GFP_KERNEL);
> +	p = kvzalloc(sizeof(*p), GFP_KERNEL);
>  	if (!p)
>  		return ERR_PTR(-ENOMEM);
>  
> @@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void)
>  	}
>  	if (type >= MAX_SWAPFILES) {
>  		spin_unlock(&swap_lock);
> -		kfree(p);
> +		kvfree(p);
>  		return ERR_PTR(-EPERM);
>  	}
>  	if (type >= nr_swapfiles) {
> @@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void)
>  		smp_wmb();
>  		nr_swapfiles++;
>  	} else {
> -		kfree(p);
> +		kvfree(p);
>  		p = swap_info[type];
>  		/*
>  		 * Do not memset this entry: a racing procfs swap_next()
> -- 
> 2.17.1

-- 
Michal Hocko
SUSE Labs

Re: [PATCH v2] mm: use kvzalloc for swap_info_struct allocation

[Aaron Lu]

On Mon, Nov 05, 2018 at 03:11:56PM +0100, Michal Hocko wrote:
> On Mon 05-11-18 14:17:01, Vasily Averin wrote:
> > commit a2468cc9bfdf ("swap: choose swap device according to numa node")
> > changed 'avail_lists' field of 'struct swap_info_struct' to an array.
> > In popular linux distros it increased size of swap_info_struct up to
> > 40 Kbytes and now swap_info_struct allocation requires order-4 page.
> > Switch to kvzmalloc allows to avoid unexpected allocation failures.
> 
> While this fixes the most visible issue is this a good long term
> solution? Aren't we wasting memory without a good reason? IIRC our limit

That's right, we need a better way of handling this in the long term.

> for swap files/devices is much smaller than potential NUMA nodes numbers
> so we can safely expect that would be only few numa affine nodes. I am
> not really familiar with the rework which has added numa node awareness
> but I wouls assueme that we should either go with one global table with
> a linked list of possible swap_info structure per numa node or use a
> sparse array.

There is a per-numa-node plist of available swap devices, so every swap
device needs an entry on those per-numa-node plist.

I think we can convert avail_lists from array to pointer and use vzalloc
to allocate the needed memory. MAX_NUMANODES can be used for a simple
implementation, or use the precise online node number but then we will
need to handle node online/offline events.

sparse array sounds promising, I'll take a look, thanks for the pointer.

> That being said I am not really objecting to this patch as it is simple
> and backportable to older (stable kernels).
>  
> I would even dare to add
> Fixes: a2468cc9bfdf ("swap: choose swap device according to numa node")
> 
> because not being able to add a swap space on a fragmented system looks
> like a regression to me.

Agree, especially it used to work.

Regards,
Aaron

> > Acked-by: Aaron Lu <aaron.lu@intel.com>
> > Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
> 
> Acked-by: Michal Hocko <mhocko@suse.com>
> > ---
> >  mm/swapfile.c | 6 +++---
> >  1 file changed, 3 insertions(+), 3 deletions(-)
> > 
> > diff --git a/mm/swapfile.c b/mm/swapfile.c
> > index 644f746e167a..8688ae65ef58 100644
> > --- a/mm/swapfile.c
> > +++ b/mm/swapfile.c
> > @@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void)
> >  	unsigned int type;
> >  	int i;
> >  
> > -	p = kzalloc(sizeof(*p), GFP_KERNEL);
> > +	p = kvzalloc(sizeof(*p), GFP_KERNEL);
> >  	if (!p)
> >  		return ERR_PTR(-ENOMEM);
> >  
> > @@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void)
> >  	}
> >  	if (type >= MAX_SWAPFILES) {
> >  		spin_unlock(&swap_lock);
> > -		kfree(p);
> > +		kvfree(p);
> >  		return ERR_PTR(-EPERM);
> >  	}
> >  	if (type >= nr_swapfiles) {
> > @@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void)
> >  		smp_wmb();
> >  		nr_swapfiles++;
> >  	} else {
> > -		kfree(p);
> > +		kvfree(p);
> >  		p = swap_info[type];
> >  		/*
> >  		 * Do not memset this entry: a racing procfs swap_next()
> > -- 
> > 2.17.1
> 
> -- 
> Michal Hocko
> SUSE Labs
>