[PATCH] mm: memcontrol: fix kernel stack account

[PATCH] mm: memcontrol: fix kernel stack account

[Muchun Song]

The alloc_thread_stack_node() cannot guarantee that allocated stack pages
are in the same node when CONFIG_VMAP_STACK. Because we do not specify
__GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
mod_lruvec_page_state() for each page one by one.

Fixes: 991e7673859e ("mm: memcontrol: account kernel stack per node")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 kernel/fork.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index d66cd1014211..6e2201feb524 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -379,14 +379,19 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 	void *stack = task_stack_page(tsk);
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 
+	if (vm) {
+		int i;
 
-	/* All stack pages are in the same node. */
-	if (vm)
-		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
-				      account * (THREAD_SIZE / 1024));
-	else
+		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
+			mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
+					      account * (PAGE_SIZE / 1024));
+	} else {
+		/* All stack pages are in the same node. */
 		mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
 				      account * (THREAD_SIZE / 1024));
+	}
 }
 
 static int memcg_charge_kernel_stack(struct task_struct *tsk)
-- 
2.11.0

Re: [PATCH] mm: memcontrol: fix kernel stack account

[Michal Hocko]

On Tue 02-03-21 15:37:33, Muchun Song wrote:
> The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> mod_lruvec_page_state() for each page one by one.

What is the actual problem you are trying to address by this patch?
991e7673859e has deliberately dropped the per page accounting. Can you
explain why that was incorrect? There surely is some imprecision
involved but does it matter and is it even observable?

> Fixes: 991e7673859e ("mm: memcontrol: account kernel stack per node")
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  kernel/fork.c | 15 ++++++++++-----
>  1 file changed, 10 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/fork.c b/kernel/fork.c
> index d66cd1014211..6e2201feb524 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -379,14 +379,19 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
>  	void *stack = task_stack_page(tsk);
>  	struct vm_struct *vm = task_stack_vm_area(tsk);
>  
> +	if (vm) {
> +		int i;
>  
> -	/* All stack pages are in the same node. */
> -	if (vm)
> -		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
> -				      account * (THREAD_SIZE / 1024));
> -	else
> +		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
> +
> +		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
> +			mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
> +					      account * (PAGE_SIZE / 1024));
> +	} else {
> +		/* All stack pages are in the same node. */
>  		mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
>  				      account * (THREAD_SIZE / 1024));
> +	}
>  }
>  
>  static int memcg_charge_kernel_stack(struct task_struct *tsk)
> -- 
> 2.11.0

-- 
Michal Hocko
SUSE Labs

Re: [External] Re: [PATCH] mm: memcontrol: fix kernel stack account

[Muchun Song]

On Tue, Mar 2, 2021 at 4:44 PM Michal Hocko <mhocko@suse.com> wrote:
>
> On Tue 02-03-21 15:37:33, Muchun Song wrote:
> > The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> > are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> > __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> > mod_lruvec_page_state() for each page one by one.
>
> What is the actual problem you are trying to address by this patch?
> 991e7673859e has deliberately dropped the per page accounting. Can you
> explain why that was incorrect? There surely is some imprecision
> involved but does it matter and is it even observable?

When I read the code of account_kernel_stack(), I see a comment that
says "All stack pages are in the same node". I am confused about this.
IIUC, there is no guarantee about this. Right? Yeah, imprecision may
not be a problem. But if this is what we did deliberately, I think that
it is better to add a comment there. Thanks.

>
> > Fixes: 991e7673859e ("mm: memcontrol: account kernel stack per node")
> > Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> > ---
> >  kernel/fork.c | 15 ++++++++++-----
> >  1 file changed, 10 insertions(+), 5 deletions(-)
> >
> > diff --git a/kernel/fork.c b/kernel/fork.c
> > index d66cd1014211..6e2201feb524 100644
> > --- a/kernel/fork.c
> > +++ b/kernel/fork.c
> > @@ -379,14 +379,19 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
> >       void *stack = task_stack_page(tsk);
> >       struct vm_struct *vm = task_stack_vm_area(tsk);
> >
> > +     if (vm) {
> > +             int i;
> >
> > -     /* All stack pages are in the same node. */
> > -     if (vm)
> > -             mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
> > -                                   account * (THREAD_SIZE / 1024));
> > -     else
> > +             BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
> > +
> > +             for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
> > +                     mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
> > +                                           account * (PAGE_SIZE / 1024));
> > +     } else {
> > +             /* All stack pages are in the same node. */
> >               mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
> >                                     account * (THREAD_SIZE / 1024));
> > +     }
> >  }
> >
> >  static int memcg_charge_kernel_stack(struct task_struct *tsk)
> > --
> > 2.11.0
>
> --
> Michal Hocko
> SUSE Labs

Re: [External] Re: [PATCH] mm: memcontrol: fix kernel stack account

[Michal Hocko]

On Tue 02-03-21 17:23:42, Muchun Song wrote:
> On Tue, Mar 2, 2021 at 4:44 PM Michal Hocko <mhocko@suse.com> wrote:
> >
> > On Tue 02-03-21 15:37:33, Muchun Song wrote:
> > > The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> > > are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> > > __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> > > mod_lruvec_page_state() for each page one by one.
> >
> > What is the actual problem you are trying to address by this patch?
> > 991e7673859e has deliberately dropped the per page accounting. Can you
> > explain why that was incorrect? There surely is some imprecision
> > involved but does it matter and is it even observable?
> 
> When I read the code of account_kernel_stack(), I see a comment that
> says "All stack pages are in the same node". I am confused about this.
> IIUC, there is no guarantee about this. Right?

Yes there is no guarantee indeed. Please always make sure to describe
the underlying reasoning for the patch. Subject of this patch refers to
a fix without explaining the actual problem. If a change is motivated by
code reading then make it explicit. Also if you are refering to a
different commit by Fixes: tag then it would be really helpful to
explicitly mention why that commit is incorrect or cause a visible
problems.

> Yeah, imprecision may
> not be a problem. But if this is what we did deliberately, I think that
> it is better to add a comment there. Thanks.

Yes the comment is quite confusing. I suspect it meant to say
	/* All stack pages are accounted to the same node */

-- 
Michal Hocko
SUSE Labs

Re: [External] Re: [PATCH] mm: memcontrol: fix kernel stack account

[Muchun Song]

On Tue, Mar 2, 2021 at 5:34 PM Michal Hocko <mhocko@suse.com> wrote:
>
> On Tue 02-03-21 17:23:42, Muchun Song wrote:
> > On Tue, Mar 2, 2021 at 4:44 PM Michal Hocko <mhocko@suse.com> wrote:
> > >
> > > On Tue 02-03-21 15:37:33, Muchun Song wrote:
> > > > The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> > > > are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> > > > __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> > > > mod_lruvec_page_state() for each page one by one.
> > >
> > > What is the actual problem you are trying to address by this patch?
> > > 991e7673859e has deliberately dropped the per page accounting. Can you
> > > explain why that was incorrect? There surely is some imprecision
> > > involved but does it matter and is it even observable?
> >
> > When I read the code of account_kernel_stack(), I see a comment that
> > says "All stack pages are in the same node". I am confused about this.
> > IIUC, there is no guarantee about this. Right?
>
> Yes there is no guarantee indeed. Please always make sure to describe
> the underlying reasoning for the patch. Subject of this patch refers to
> a fix without explaining the actual problem. If a change is motivated by
> code reading then make it explicit. Also if you are refering to a
> different commit by Fixes: tag then it would be really helpful to
> explicitly mention why that commit is incorrect or cause a visible
> problems.

Got it. Thanks for your teaching.

>
> > Yeah, imprecision may
> > not be a problem. But if this is what we did deliberately, I think that
> > it is better to add a comment there. Thanks.
>
> Yes the comment is quite confusing. I suspect it meant to say
>         /* All stack pages are accounted to the same node */
>
> --
> Michal Hocko
> SUSE Labs

Re: [External] Re: [PATCH] mm: memcontrol: fix kernel stack account

[Shakeel Butt]

On Tue, Mar 2, 2021 at 1:34 AM Michal Hocko <mhocko@suse.com> wrote:
>
[snip]
> > Yeah, imprecision may
> > not be a problem. But if this is what we did deliberately, I think that
> > it is better to add a comment there. Thanks.
>
> Yes the comment is quite confusing. I suspect it meant to say
>         /* All stack pages are accounted to the same node */
>

Most probably I meant to say "For simplicity let's just assume all
stack pages are on the same node." but we can easily make this more
accurate.

Re: [PATCH] mm: memcontrol: fix kernel stack account

[Shakeel Butt]

On Mon, Mar 1, 2021 at 11:52 PM Muchun Song <songmuchun@bytedance.com> wrote:
>
> The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> __GFP_THISNODE to __vmalloc_node_range().

Instead of __GFP_THISNODE, mention that the kernel_clone() passes
NUMA_NO_NODE which is being used for __vmalloc_node_range().

> Fix it by caling

calling

> mod_lruvec_page_state() for each page one by one.
>
> Fixes: 991e7673859e ("mm: memcontrol: account kernel stack per node")
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>

Please follow Michal's suggestion to update the commit message.

After that:

Reviewed-by: Shakeel Butt <shakeelb@google.com>

> ---
>  kernel/fork.c | 15 ++++++++++-----
>  1 file changed, 10 insertions(+), 5 deletions(-)
>
> diff --git a/kernel/fork.c b/kernel/fork.c
> index d66cd1014211..6e2201feb524 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -379,14 +379,19 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
>         void *stack = task_stack_page(tsk);
>         struct vm_struct *vm = task_stack_vm_area(tsk);
>
> +       if (vm) {
> +               int i;
>
> -       /* All stack pages are in the same node. */
> -       if (vm)
> -               mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
> -                                     account * (THREAD_SIZE / 1024));
> -       else
> +               BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
> +
> +               for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
> +                       mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
> +                                             account * (PAGE_SIZE / 1024));
> +       } else {
> +               /* All stack pages are in the same node. */
>                 mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
>                                       account * (THREAD_SIZE / 1024));
> +       }
>  }
>
>  static int memcg_charge_kernel_stack(struct task_struct *tsk)
> --
> 2.11.0
>

Re: [PATCH] mm: memcontrol: fix kernel stack account

[Michal Hocko]

On Tue 02-03-21 06:02:14, Shakeel Butt wrote:
> On Mon, Mar 1, 2021 at 11:52 PM Muchun Song <songmuchun@bytedance.com> wrote:
> >
> > The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> > are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> > __GFP_THISNODE to __vmalloc_node_range().
> 
> Instead of __GFP_THISNODE, mention that the kernel_clone() passes
> NUMA_NO_NODE which is being used for __vmalloc_node_range().

If we really want to do this then I would recommend reasoning in the
following line:

"
For simplification 991e7673859e ("mm: memcontrol: account kernel stack
per node") has changed the per zone vmalloc backed stack pages accounting
to per node. By doing that we have lost a certain precision because
those pages might live in different NUMA nodes. In the end
NR_KERNEL_STACK_KB exported to the userspace might be over estimated on
some nodes while underestimated on others.

	< some examples would go here ideally >

This doesn't impose any real problem to correctnes of the kernel
behavior as the counter is not used for any internal processing but it
can cause some confusion to the userspace.

Address the problem by accounting each vmalloc backing page to its own
node.
"

-- 
Michal Hocko
SUSE Labs

Re: [PATCH] mm: memcontrol: fix kernel stack account

[Roman Gushchin]

On Tue, Mar 02, 2021 at 03:37:33PM +0800, Muchun Song wrote:
> The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> mod_lruvec_page_state() for each page one by one.

Hm, I actually wonder if it makes any sense to split the stack over multiple
nodes? Maybe we should fix this instead?

> 
> Fixes: 991e7673859e ("mm: memcontrol: account kernel stack per node")
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  kernel/fork.c | 15 ++++++++++-----
>  1 file changed, 10 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/fork.c b/kernel/fork.c
> index d66cd1014211..6e2201feb524 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -379,14 +379,19 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
>  	void *stack = task_stack_page(tsk);
>  	struct vm_struct *vm = task_stack_vm_area(tsk);
>  
> +	if (vm) {
> +		int i;
>  
> -	/* All stack pages are in the same node. */
> -	if (vm)
> -		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
> -				      account * (THREAD_SIZE / 1024));
> -	else
> +		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
> +
> +		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
> +			mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
> +					      account * (PAGE_SIZE / 1024));
> +	} else {
> +		/* All stack pages are in the same node. */
>  		mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
>  				      account * (THREAD_SIZE / 1024));
> +	}
>  }
>  
>  static int memcg_charge_kernel_stack(struct task_struct *tsk)
> -- 
> 2.11.0
> 

Re: [PATCH] mm: memcontrol: fix kernel stack account

[Michal Hocko]

On Tue 02-03-21 10:50:32, Roman Gushchin wrote:
> On Tue, Mar 02, 2021 at 03:37:33PM +0800, Muchun Song wrote:
> > The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> > are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> > __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> > mod_lruvec_page_state() for each page one by one.
> 
> Hm, I actually wonder if it makes any sense to split the stack over multiple
> nodes? Maybe we should fix this instead?

While this is not really ideal I am not really sure it is an actual
problem worth complicating the code. I am pretty sure this would grow
into more tricky problem quite quickly (e.g. proper memory policy
handling).
-- 
Michal Hocko
SUSE Labs

Re: [PATCH] mm: memcontrol: fix kernel stack account

[Roman Gushchin]

On Tue, Mar 02, 2021 at 08:33:20PM +0100, Michal Hocko wrote:
> On Tue 02-03-21 10:50:32, Roman Gushchin wrote:
> > On Tue, Mar 02, 2021 at 03:37:33PM +0800, Muchun Song wrote:
> > > The alloc_thread_stack_node() cannot guarantee that allocated stack pages
> > > are in the same node when CONFIG_VMAP_STACK. Because we do not specify
> > > __GFP_THISNODE to __vmalloc_node_range(). Fix it by caling
> > > mod_lruvec_page_state() for each page one by one.
> > 
> > Hm, I actually wonder if it makes any sense to split the stack over multiple
> > nodes? Maybe we should fix this instead?
> 
> While this is not really ideal I am not really sure it is an actual
> problem worth complicating the code. I am pretty sure this would grow
> into more tricky problem quite quickly (e.g. proper memory policy
> handling).

I'd agree and IMO accounting a couple of pages to a different node
is even a smaller problem.