diff mbox series

[bpf-next,v3,1/3] bpf: support input xdp_md context in BPF_PROG_TEST_RUN

Message ID 20210602190815.8096-2-zeffron@riotgames.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: support input xdp_md context in BPF_PROG_TEST_RUN | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 8 maintainers not CCed: netdev@vger.kernel.org yhs@fb.com kpsingh@kernel.org andrii@kernel.org kafai@fb.com john.fastabend@gmail.com songliubraving@fb.com kuba@kernel.org
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 10043 this patch: 10043
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 10457 this patch: 10457
netdev/header_inline success Link

Commit Message

Zvi Effron June 2, 2021, 7:08 p.m. UTC 
Support passing a xdp_md via ctx_in/ctx_out in bpf_attr for
BPF_PROG_TEST_RUN.

The intended use case is to pass some XDP meta data to the test runs of
XDP programs that are used as tail calls.

For programs that use bpf_prog_test_run_xdp, support xdp_md input and
output. Unlike with an actual xdp_md during a non-test run, data_meta must
be 0 because it must point to the start of the provided user data. From
the initial xdp_md, use data and data_end to adjust the pointers in the
generated xdp_buff. All other non-zero fields are prohibited (with
EINVAL). If the user has set ctx_out/ctx_size_out, copy the (potentially
different) xdp_md back to the userspace.

We require all fields of input xdp_md except the ones we explicitly
support to be set to zero. The expectation is that in the future we might
add support for more fields and we want to fail explicitly if the user
runs the program on the kernel where we don't yet support them.

Co-developed-by: Cody Haas <chaas@riotgames.com>
Signed-off-by: Cody Haas <chaas@riotgames.com>
Co-developed-by: Lisa Watanabe <lwatanabe@riotgames.com>
Signed-off-by: Lisa Watanabe <lwatanabe@riotgames.com>
Signed-off-by: Zvi Effron <zeffron@riotgames.com>
---
 include/uapi/linux/bpf.h |  3 --
 net/bpf/test_run.c       | 82 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 75 insertions(+), 10 deletions(-)

Comments

Martin KaFai Lau June 3, 2021, 4:34 a.m. UTC | #1 
On Wed, Jun 02, 2021 at 07:08:13PM +0000, Zvi Effron wrote:
[ ... ]

> diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
> index aa47af349ba8..ae8741dd2a54 100644
> --- a/net/bpf/test_run.c
> +++ b/net/bpf/test_run.c
> @@ -687,6 +687,43 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
>  	return ret;
>  }
>  
> +static int xdp_convert_md_to_buff(struct xdp_buff *xdp, struct xdp_md *xdp_md)
> +{
> +	void *data;
> +	u32 metalen;
> +
> +	if (!xdp_md)
> +		return 0;
> +
> +	if (xdp_md->egress_ifindex != 0)
> +		return -EINVAL;
> +
> +	metalen = xdp_md->data - xdp_md->data_meta;
Remove "- xdp_md->data_meta".  It is 0.

> +	data = xdp->data_meta + metalen;
> +	if (data > xdp->data_end)
This test and...

> +		return -EINVAL;
> +	xdp->data = data;
> +
> +	if (xdp_md->data_end - xdp_md->data != xdp->data_end - xdp->data)
this one.  It is because the user input "xdp_md->data_end" does not
match with kattr->test.data_size_in?  These tests are disconnected from
where the actual invalid input is.  How about direclty testing
xdp_md->data_end in bpf_prog_test_run_xdp() instead?

> +		return -EINVAL;
> +
> +	if (xdp_md->ingress_ifindex != 0 || xdp_md->rx_queue_index != 0)
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +
> +static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md)
> +{
> +	if (!xdp_md)
> +		return;
> +
> +	/* xdp_md->data_meta must always point to the start of the out buffer */
> +	xdp_md->data_meta = 0;
> +	xdp_md->data = xdp->data - xdp->data_meta;
> +	xdp_md->data_end = xdp->data_end - xdp->data_meta;
> +}
> +
>  int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
>  			  union bpf_attr __user *uattr)
>  {
> @@ -696,36 +733,68 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
>  	u32 repeat = kattr->test.repeat;
>  	struct netdev_rx_queue *rxqueue;
>  	struct xdp_buff xdp = {};
> +	struct xdp_md *ctx = NULL;
"= NULL" is not needed.

>  	u32 retval, duration;
>  	u32 max_data_sz;
> +	u32 metalen;
>  	void *data;
>  	int ret;
>  
> -	if (kattr->test.ctx_in || kattr->test.ctx_out)
> -		return -EINVAL;
> +	ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
> +	if (IS_ERR(ctx))
> +		return PTR_ERR(ctx);
> +
> +	/* There can't be user provided data before the metadata */
> +	if (ctx) {
> +		if (ctx->data_meta != 0)
nit. "if (ctx->data_meta)".

> +			return -EINVAL;
> +		metalen = ctx->data - ctx->data_meta;
It is confusing.  "ctx->data_meta != 0" has just been checked.

> +		if (unlikely((metalen & (sizeof(__u32) - 1)) ||
> +			     metalen > 32))
> +			return -EINVAL;
> +		/* Metadata is allocated from the headroom */
> +		headroom -= metalen;
> +	}
>  
>  	/* XDP have extra tailroom as (most) drivers use full page */
>  	max_data_sz = 4096 - headroom - tailroom;
>  
>  	data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
> -	if (IS_ERR(data))
> +	if (IS_ERR(data)) {
> +		kfree(ctx);
>  		return PTR_ERR(data);
> +	}
>  
>  	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
>  	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
>  		      &rxqueue->xdp_rxq);
>  	xdp_prepare_buff(&xdp, data, headroom, size, true);
>  
> +	ret = xdp_convert_md_to_buff(&xdp, ctx);
> +	if (ret) {
> +		kfree(data);
> +		kfree(ctx);
> +		return ret;
> +	}
> +
>  	bpf_prog_change_xdp(NULL, prog);
>  	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
>  	if (ret)
>  		goto out;
> -	if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
> -		size = xdp.data_end - xdp.data;
> -	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
> +
> +	if (xdp.data_meta != data + headroom || xdp.data_end != xdp.data_meta + size)
> +		size = xdp.data_end - xdp.data_meta;
> +
> +	xdp_convert_buff_to_md(&xdp, ctx);
> +
> +	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval, duration);
> +	if (!ret)
> +		ret = bpf_ctx_finish(kattr, uattr, ctx,
> +				     sizeof(struct xdp_md));
>  out:
>  	bpf_prog_change_xdp(prog, NULL);
>  	kfree(data);
> +	kfree(ctx);
>  	return ret;
>  }
>  
> @@ -809,7 +878,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
>  	if (!ret)
>  		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
>  				     sizeof(struct bpf_flow_keys));
> -
>  out:
>  	kfree(user_ctx);
>  	kfree(data);
> -- 
> 2.31.1
>
Zvi Effron June 4, 2021, 6:55 p.m. UTC | #2 
On Wed, Jun 2, 2021 at 9:34 PM Martin KaFai Lau <kafai@fb.com> wrote:
>
> On Wed, Jun 02, 2021 at 07:08:13PM +0000, Zvi Effron wrote:
> > +     data = xdp->data_meta + metalen;
> > +     if (data > xdp->data_end)
> This test and...
>
> > +             return -EINVAL;
> > +     xdp->data = data;
> > +
> > +     if (xdp_md->data_end - xdp_md->data != xdp->data_end - xdp->data)
> this one.  It is because the user input "xdp_md->data_end" does not
> match with kattr->test.data_size_in?  These tests are disconnected from
> where the actual invalid input is.  How about direclty testing
> xdp_md->data_end in bpf_prog_test_run_xdp() instead?
>

The first test is required because it's possible that the user provided value
for `xdp_md->data` could be greater than the user provided value for
`xdp_md->data_end`. For example, a user could pass a struct xdp_md that looked
like this:
```
struct xdp_md {
    .data_meta = 0,
    .data = 12,
    .data_end = 8,
};
```
We're moving the test and making it more clear what it's testing for in our
next patch version.

The second test can be eliminated by moving the test for xdp_md->data_end
against kattr->test.data_size_in as you suggest, which also allows simplifying
the surrounding code. We're updating that in our next patch version.

We're also addressing your other feedback in our next patch version.
diff mbox series

Patch

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2c1ba70abbf1..a9dcf3d8c85a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -324,9 +324,6 @@  union bpf_iter_link_info {
  *		**BPF_PROG_TYPE_SK_LOOKUP**
  *			*data_in* and *data_out* must be NULL.
  *
- *		**BPF_PROG_TYPE_XDP**
- *			*ctx_in* and *ctx_out* must be NULL.
- *
  *		**BPF_PROG_TYPE_RAW_TRACEPOINT**,
  *		**BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
  *
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aa47af349ba8..ae8741dd2a54 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -687,6 +687,43 @@  int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	return ret;
 }
 
+static int xdp_convert_md_to_buff(struct xdp_buff *xdp, struct xdp_md *xdp_md)
+{
+	void *data;
+	u32 metalen;
+
+	if (!xdp_md)
+		return 0;
+
+	if (xdp_md->egress_ifindex != 0)
+		return -EINVAL;
+
+	metalen = xdp_md->data - xdp_md->data_meta;
+	data = xdp->data_meta + metalen;
+	if (data > xdp->data_end)
+		return -EINVAL;
+	xdp->data = data;
+
+	if (xdp_md->data_end - xdp_md->data != xdp->data_end - xdp->data)
+		return -EINVAL;
+
+	if (xdp_md->ingress_ifindex != 0 || xdp_md->rx_queue_index != 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md)
+{
+	if (!xdp_md)
+		return;
+
+	/* xdp_md->data_meta must always point to the start of the out buffer */
+	xdp_md->data_meta = 0;
+	xdp_md->data = xdp->data - xdp->data_meta;
+	xdp_md->data_end = xdp->data_end - xdp->data_meta;
+}
+
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
@@ -696,36 +733,68 @@  int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 repeat = kattr->test.repeat;
 	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
+	struct xdp_md *ctx = NULL;
 	u32 retval, duration;
 	u32 max_data_sz;
+	u32 metalen;
 	void *data;
 	int ret;
 
-	if (kattr->test.ctx_in || kattr->test.ctx_out)
-		return -EINVAL;
+	ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	/* There can't be user provided data before the metadata */
+	if (ctx) {
+		if (ctx->data_meta != 0)
+			return -EINVAL;
+		metalen = ctx->data - ctx->data_meta;
+		if (unlikely((metalen & (sizeof(__u32) - 1)) ||
+			     metalen > 32))
+			return -EINVAL;
+		/* Metadata is allocated from the headroom */
+		headroom -= metalen;
+	}
 
 	/* XDP have extra tailroom as (most) drivers use full page */
 	max_data_sz = 4096 - headroom - tailroom;
 
 	data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
-	if (IS_ERR(data))
+	if (IS_ERR(data)) {
+		kfree(ctx);
 		return PTR_ERR(data);
+	}
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
 		      &rxqueue->xdp_rxq);
 	xdp_prepare_buff(&xdp, data, headroom, size, true);
 
+	ret = xdp_convert_md_to_buff(&xdp, ctx);
+	if (ret) {
+		kfree(data);
+		kfree(ctx);
+		return ret;
+	}
+
 	bpf_prog_change_xdp(NULL, prog);
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
 	if (ret)
 		goto out;
-	if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
-		size = xdp.data_end - xdp.data;
-	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+
+	if (xdp.data_meta != data + headroom || xdp.data_end != xdp.data_meta + size)
+		size = xdp.data_end - xdp.data_meta;
+
+	xdp_convert_buff_to_md(&xdp, ctx);
+
+	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval, duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, ctx,
+				     sizeof(struct xdp_md));
 out:
 	bpf_prog_change_xdp(prog, NULL);
 	kfree(data);
+	kfree(ctx);
 	return ret;
 }
 
@@ -809,7 +878,6 @@  int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
 				     sizeof(struct bpf_flow_keys));
-
 out:
 	kfree(user_ctx);
 	kfree(data);