diff mbox series

[bpf-next,v2,01/35] bpf: memcg-based memory accounting for bpf progs

Message ID 20200727184506.2279656-2-guro@fb.com
State Changes Requested
Delegated to: BPF Maintainers
Headers show
Series bpf: switch to memcg-based memory accounting | expand

Commit Message

Roman Gushchin July 27, 2020, 6:44 p.m. UTC
Include memory used by bpf programs into the memcg-based accounting.
This includes the memory used by programs itself, auxiliary data
and statistics.

Signed-off-by: Roman Gushchin <guro@fb.com>
---
 kernel/bpf/core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

Comments

Song Liu July 27, 2020, 10:11 p.m. UTC | #1
On Mon, Jul 27, 2020 at 12:20 PM Roman Gushchin <guro@fb.com> wrote:
>
> Include memory used by bpf programs into the memcg-based accounting.
> This includes the memory used by programs itself, auxiliary data
> and statistics.
>
> Signed-off-by: Roman Gushchin <guro@fb.com>
> ---
>  kernel/bpf/core.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index bde93344164d..daab8dcafbd4 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
>
>  struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
>  {
> -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
>         struct bpf_prog_aux *aux;
>         struct bpf_prog *fp;
>
> @@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
>         if (fp == NULL)
>                 return NULL;
>
> -       aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
> +       aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
>         if (aux == NULL) {
>                 vfree(fp);
>                 return NULL;
> @@ -104,7 +104,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
>
>  struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
>  {
> -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
>         struct bpf_prog *prog;
>         int cpu;
>
> @@ -217,7 +217,7 @@ void bpf_prog_free_linfo(struct bpf_prog *prog)
>  struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
>                                   gfp_t gfp_extra_flags)
>  {
> -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
>         struct bpf_prog *fp;
>         u32 pages, delta;
>         int ret;
> --

Do we need similar changes in

bpf_prog_array_copy()
bpf_prog_alloc_jited_linfo()
bpf_prog_clone_create()

and maybe a few more?

Thanks,
Song
Roman Gushchin July 28, 2020, 12:08 a.m. UTC | #2
On Mon, Jul 27, 2020 at 03:11:42PM -0700, Song Liu wrote:
> On Mon, Jul 27, 2020 at 12:20 PM Roman Gushchin <guro@fb.com> wrote:
> >
> > Include memory used by bpf programs into the memcg-based accounting.
> > This includes the memory used by programs itself, auxiliary data
> > and statistics.
> >
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> > ---
> >  kernel/bpf/core.c | 8 ++++----
> >  1 file changed, 4 insertions(+), 4 deletions(-)
> >
> > diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> > index bde93344164d..daab8dcafbd4 100644
> > --- a/kernel/bpf/core.c
> > +++ b/kernel/bpf/core.c
> > @@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
> >
> >  struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
> >  {
> > -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> > +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
> >         struct bpf_prog_aux *aux;
> >         struct bpf_prog *fp;
> >
> > @@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
> >         if (fp == NULL)
> >                 return NULL;
> >
> > -       aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
> > +       aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
> >         if (aux == NULL) {
> >                 vfree(fp);
> >                 return NULL;
> > @@ -104,7 +104,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
> >
> >  struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
> >  {
> > -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> > +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
> >         struct bpf_prog *prog;
> >         int cpu;
> >
> > @@ -217,7 +217,7 @@ void bpf_prog_free_linfo(struct bpf_prog *prog)
> >  struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
> >                                   gfp_t gfp_extra_flags)
> >  {
> > -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> > +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
> >         struct bpf_prog *fp;
> >         u32 pages, delta;
> >         int ret;
> > --

Hi Song!

Thank you for looking into the patchset!

> 
> Do we need similar changes in
> 
> bpf_prog_array_copy()
> bpf_prog_alloc_jited_linfo()
> bpf_prog_clone_create()
> 
> and maybe a few more?

I've tried to follow the rlimit-based accounting, so those objects which were
skipped are mostly skipped now and vice versa. The main reason for that is
simple: I don't know many parts of bpf code well enough to decide whether
we need accounting or not.

In general with memcg-based accounting we can easily cover places which were
not covered previously: e.g. the memory used by the verifier. But I guess it's
better to do it case-by-case.

But if you're aware of any big objects which should be accounted for sure,
please, let me know.

Thanks!
Song Liu July 28, 2020, 4:42 a.m. UTC | #3
On Mon, Jul 27, 2020 at 5:08 PM Roman Gushchin <guro@fb.com> wrote:
>
> On Mon, Jul 27, 2020 at 03:11:42PM -0700, Song Liu wrote:
> > On Mon, Jul 27, 2020 at 12:20 PM Roman Gushchin <guro@fb.com> wrote:
> > >
> > > Include memory used by bpf programs into the memcg-based accounting.
> > > This includes the memory used by programs itself, auxiliary data
> > > and statistics.
> > >
> > > Signed-off-by: Roman Gushchin <guro@fb.com>
> > > ---
> > >  kernel/bpf/core.c | 8 ++++----
> > >  1 file changed, 4 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> > > index bde93344164d..daab8dcafbd4 100644
> > > --- a/kernel/bpf/core.c
> > > +++ b/kernel/bpf/core.c
> > > @@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
> > >
> > >  struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
> > >  {
> > > -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> > > +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
> > >         struct bpf_prog_aux *aux;
> > >         struct bpf_prog *fp;
> > >
> > > @@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
> > >         if (fp == NULL)
> > >                 return NULL;
> > >
> > > -       aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
> > > +       aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
> > >         if (aux == NULL) {
> > >                 vfree(fp);
> > >                 return NULL;
> > > @@ -104,7 +104,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
> > >
> > >  struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
> > >  {
> > > -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> > > +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
> > >         struct bpf_prog *prog;
> > >         int cpu;
> > >
> > > @@ -217,7 +217,7 @@ void bpf_prog_free_linfo(struct bpf_prog *prog)
> > >  struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
> > >                                   gfp_t gfp_extra_flags)
> > >  {
> > > -       gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
> > > +       gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
> > >         struct bpf_prog *fp;
> > >         u32 pages, delta;
> > >         int ret;
> > > --
>
> Hi Song!
>
> Thank you for looking into the patchset!
>
> >
> > Do we need similar changes in
> >
> > bpf_prog_array_copy()
> > bpf_prog_alloc_jited_linfo()
> > bpf_prog_clone_create()
> >
> > and maybe a few more?
>
> I've tried to follow the rlimit-based accounting, so those objects which were
> skipped are mostly skipped now and vice versa. The main reason for that is
> simple: I don't know many parts of bpf code well enough to decide whether
> we need accounting or not.
>
> In general with memcg-based accounting we can easily cover places which were
> not covered previously: e.g. the memory used by the verifier. But I guess it's
> better to do it case-by-case.
>
> But if you're aware of any big objects which should be accounted for sure,
> please, let me know.

Thanks for the explanation. I think we can do one-to-one migration to
memcg-based accounting for now.

Song
diff mbox series

Patch

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index bde93344164d..daab8dcafbd4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -77,7 +77,7 @@  void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 
 struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
 {
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog_aux *aux;
 	struct bpf_prog *fp;
 
@@ -86,7 +86,7 @@  struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	if (fp == NULL)
 		return NULL;
 
-	aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
+	aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
 	if (aux == NULL) {
 		vfree(fp);
 		return NULL;
@@ -104,7 +104,7 @@  struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 {
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog *prog;
 	int cpu;
 
@@ -217,7 +217,7 @@  void bpf_prog_free_linfo(struct bpf_prog *prog)
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags)
 {
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog *fp;
 	u32 pages, delta;
 	int ret;