diff mbox series

[bpf-next] xsk: use kvcalloc to support large umems

Message ID 20210521083301.26921-1-magnus.karlsson@gmail.com
State New
Headers show
Series [bpf-next] xsk: use kvcalloc to support large umems | expand

Commit Message

Magnus Karlsson May 21, 2021, 8:33 a.m. UTC
From: Magnus Karlsson <magnus.karlsson@intel.com>

Use kvcalloc() instead of kcalloc() to support large umems with, on my
server, one million pages or more in the umem.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reported-by: Dan Siemon <dan@coverfire.com>
---
 net/xdp/xdp_umem.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)


base-commit: a49e72b3bda73d36664a084e47da9727a31b8095

Comments

Björn Töpel May 22, 2021, 2:12 p.m. UTC | #1
On Fri, 21 May 2021 at 10:33, Magnus Karlsson <magnus.karlsson@gmail.com> wrote:
>

> From: Magnus Karlsson <magnus.karlsson@intel.com>

>

> Use kvcalloc() instead of kcalloc() to support large umems with, on my

> server, one million pages or more in the umem.

>

> Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>

> Reported-by: Dan Siemon <dan@coverfire.com>


Nice!

Acked-by: Björn Töpel <bjorn@kernel.org>


> ---

>  net/xdp/xdp_umem.c | 7 +++----

>  1 file changed, 3 insertions(+), 4 deletions(-)

>

> diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c

> index 56a28a686988..f01ef6bda390 100644

> --- a/net/xdp/xdp_umem.c

> +++ b/net/xdp/xdp_umem.c

> @@ -27,7 +27,7 @@ static void xdp_umem_unpin_pages(struct xdp_umem *umem)

>  {

>         unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);

>

> -       kfree(umem->pgs);

> +       kvfree(umem->pgs);

>         umem->pgs = NULL;

>  }

>

> @@ -99,8 +99,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)

>         long npgs;

>         int err;

>

> -       umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs),

> -                           GFP_KERNEL | __GFP_NOWARN);

> +       umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN);

>         if (!umem->pgs)

>                 return -ENOMEM;

>

> @@ -123,7 +122,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)

>  out_pin:

>         xdp_umem_unpin_pages(umem);

>  out_pgs:

> -       kfree(umem->pgs);

> +       kvfree(umem->pgs);

>         umem->pgs = NULL;

>         return err;

>  }

>

> base-commit: a49e72b3bda73d36664a084e47da9727a31b8095

> --

> 2.29.0

>
John Fastabend May 24, 2021, 5:59 p.m. UTC | #2
Björn Töpel wrote:
> On Fri, 21 May 2021 at 10:33, Magnus Karlsson <magnus.karlsson@gmail.com> wrote:

> >

> > From: Magnus Karlsson <magnus.karlsson@intel.com>

> >

> > Use kvcalloc() instead of kcalloc() to support large umems with, on my

> > server, one million pages or more in the umem.

> >

> > Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>

> > Reported-by: Dan Siemon <dan@coverfire.com>

> 

> Nice!

> 

> Acked-by: Björn Töpel <bjorn@kernel.org>


LGTM as well. I scanned the driver side, thinking there might be
some complication there, but looks like it handles this fine.

Acked-by: John Fastabend <john.fastabend@gmail.com>
patchwork-bot+netdevbpf@kernel.org May 25, 2021, 11:30 a.m. UTC | #3
Hello:

This patch was applied to bpf/bpf-next.git (refs/heads/master):

On Fri, 21 May 2021 10:33:01 +0200 you wrote:
> From: Magnus Karlsson <magnus.karlsson@intel.com>

> 

> Use kvcalloc() instead of kcalloc() to support large umems with, on my

> server, one million pages or more in the umem.

> 

> Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>

> Reported-by: Dan Siemon <dan@coverfire.com>

> 

> [...]


Here is the summary with links:
  - [bpf-next] xsk: use kvcalloc to support large umems
    https://git.kernel.org/bpf/bpf-next/c/a720a2a0ad6c

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
diff mbox series

Patch

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 56a28a686988..f01ef6bda390 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -27,7 +27,7 @@  static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
 	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
 
-	kfree(umem->pgs);
+	kvfree(umem->pgs);
 	umem->pgs = NULL;
 }
 
@@ -99,8 +99,7 @@  static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
 	long npgs;
 	int err;
 
-	umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs),
-			    GFP_KERNEL | __GFP_NOWARN);
+	umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN);
 	if (!umem->pgs)
 		return -ENOMEM;
 
@@ -123,7 +122,7 @@  static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
 out_pin:
 	xdp_umem_unpin_pages(umem);
 out_pgs:
-	kfree(umem->pgs);
+	kvfree(umem->pgs);
 	umem->pgs = NULL;
 	return err;
 }