netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [bpf-next PATCH] bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL
@ 2020-09-24 19:58 John Fastabend
  2020-09-25  8:56 ` Lorenz Bauer
  0 siblings, 1 reply; 2+ messages in thread
From: John Fastabend @ 2020-09-24 19:58 UTC (permalink / raw)
  To: yhs, andriin, ast, daniel; +Cc: netdev, john.fastabend, kafai, lmb

The meaning of PTR_TO_BTF_ID_OR_NULL differs slightly from other types
denoted with the *_OR_NULL type. For example the types PTR_TO_SOCKET
and PTR_TO_SOCKET_OR_NULL can be used for branch analysis because the
type PTR_TO_SOCKET is guaranteed to _not_ have a null value.

In contrast PTR_TO_BTF_ID and BTF_TO_BTF_ID_OR_NULL have slightly
different meanings. A PTR_TO_BTF_TO_ID may be a pointer to NULL value,
but it is safe to read this pointer in the program context because
the program context will handle any faults. The fallout is for
PTR_TO_BTF_ID the verifier can assume reads are safe, but can not
use the type in branch analysis. Additionally, authors need to be
extra careful when passing PTR_TO_BTF_ID into helpers. In general
helpers consuming type PTR_TO_BTF_ID will need to assume it may
be null.

Seeing the above is not obvious to readers without the back knowledge
lets add a comment in the type definition.

Editorial comment, as networking and tracing programs get closer
and more tightly merged we may need to consider a new type that we
can ensure is non-null for branch analysis and also passing into
helpers.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
 include/linux/bpf.h |   18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fc5c901c7542..dd765ba1c730 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -382,8 +382,22 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
-	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
-	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
+	/* PTR_TO_BTF_ID points to a kernel struct that does not need
+	 * to be null checked by the BPF program. This does not imply the
+	 * pointer is _not_ null and in practice this can easily be a null
+	 * pointer when reading pointer chains. The assumption is program
+	 * context will handle null pointer dereference typically via fault
+	 * handling. The verifier must keep this in mind and can make no
+	 * assumptions about null or non-null when doing branch analysis.
+	 * Further, when passed into helpers the helpers can not, without
+	 * additional context, assume the value is non-null.
+	 */
+	PTR_TO_BTF_ID,
+	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
+	 * been checked for null. Used primarily to inform the verifier
+	 * an explicit null check is required for this struct.
+	 */
+	PTR_TO_BTF_ID_OR_NULL,
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_MEM_OR_NULL,	 /* reg points to valid memory region or NULL */
 	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [bpf-next PATCH] bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL
  2020-09-24 19:58 [bpf-next PATCH] bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL John Fastabend
@ 2020-09-25  8:56 ` Lorenz Bauer
  0 siblings, 0 replies; 2+ messages in thread
From: Lorenz Bauer @ 2020-09-25  8:56 UTC (permalink / raw)
  To: John Fastabend
  Cc: Yonghong Song, Andrii Nakryiko, Alexei Starovoitov,
	Daniel Borkmann, Networking, Martin Lau

On Thu, 24 Sep 2020 at 20:58, John Fastabend <john.fastabend@gmail.com> wrote:
>
> The meaning of PTR_TO_BTF_ID_OR_NULL differs slightly from other types
> denoted with the *_OR_NULL type. For example the types PTR_TO_SOCKET
> and PTR_TO_SOCKET_OR_NULL can be used for branch analysis because the
> type PTR_TO_SOCKET is guaranteed to _not_ have a null value.
>
> In contrast PTR_TO_BTF_ID and BTF_TO_BTF_ID_OR_NULL have slightly
> different meanings. A PTR_TO_BTF_TO_ID may be a pointer to NULL value,
> but it is safe to read this pointer in the program context because
> the program context will handle any faults. The fallout is for
> PTR_TO_BTF_ID the verifier can assume reads are safe, but can not
> use the type in branch analysis. Additionally, authors need to be
> extra careful when passing PTR_TO_BTF_ID into helpers. In general
> helpers consuming type PTR_TO_BTF_ID will need to assume it may
> be null.
>
> Seeing the above is not obvious to readers without the back knowledge
> lets add a comment in the type definition.
>
> Editorial comment, as networking and tracing programs get closer
> and more tightly merged we may need to consider a new type that we
> can ensure is non-null for branch analysis and also passing into
> helpers.

Yeah, I was going back and forth with Martin on this as well. I think
we need better descriptions for possibly-NULL-at-runtime for the
purpose of helper call invariants, and possibly-NULL-at-verification
time.

>
> Signed-off-by: John Fastabend <john.fastabend@gmail.com>

Acked-by: Lorenz Bauer <lmb@cloudflare.com>

> ---
>  include/linux/bpf.h |   18 ++++++++++++++++--
>  1 file changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index fc5c901c7542..dd765ba1c730 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -382,8 +382,22 @@ enum bpf_reg_type {
>         PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
>         PTR_TO_TP_BUFFER,        /* reg points to a writable raw tp's buffer */
>         PTR_TO_XDP_SOCK,         /* reg points to struct xdp_sock */
> -       PTR_TO_BTF_ID,           /* reg points to kernel struct */
> -       PTR_TO_BTF_ID_OR_NULL,   /* reg points to kernel struct or NULL */
> +       /* PTR_TO_BTF_ID points to a kernel struct that does not need
> +        * to be null checked by the BPF program. This does not imply the
> +        * pointer is _not_ null and in practice this can easily be a null
> +        * pointer when reading pointer chains. The assumption is program
> +        * context will handle null pointer dereference typically via fault
> +        * handling. The verifier must keep this in mind and can make no
> +        * assumptions about null or non-null when doing branch analysis.
> +        * Further, when passed into helpers the helpers can not, without
> +        * additional context, assume the value is non-null.
> +        */
> +       PTR_TO_BTF_ID,
> +       /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
> +        * been checked for null. Used primarily to inform the verifier
> +        * an explicit null check is required for this struct.
> +        */
> +       PTR_TO_BTF_ID_OR_NULL,
>         PTR_TO_MEM,              /* reg points to valid memory region */
>         PTR_TO_MEM_OR_NULL,      /* reg points to valid memory region or NULL */
>         PTR_TO_RDONLY_BUF,       /* reg points to a readonly buffer */
>


-- 
Lorenz Bauer  |  Systems Engineer
6th Floor, County Hall/The Riverside Building, SE1 7PB, UK

www.cloudflare.com

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2020-09-25  8:56 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-24 19:58 [bpf-next PATCH] bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL John Fastabend
2020-09-25  8:56 ` Lorenz Bauer

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).