Re: [PATCH bpf-next v3 1/3] bpf: support input __sk_buff context in BPF_PROG_TEST_RUN

[Stanislav Fomichev <sdf@fomichev.me>]

On 04/09, Martin Lau wrote:
> On Tue, Apr 09, 2019 at 10:27:37AM -0700, Stanislav Fomichev wrote:
> > Add new set of arguments to bpf_attr for BPF_PROG_TEST_RUN:
> > * ctx_in/ctx_size_in - input context
> > * ctx_out/ctx_size_out - output context
> > 
> > The intended use case is to pass some meta data to the test runs that
> > operate on skb (this has being brought up on recent LPC).
> > 
> > For programs that use bpf_prog_test_run_skb, support __sk_buff input and
> > output. Initially, from input __sk_buff, copy _only_ cb and priority into
> > skb, all other non-zero fields are prohibited (with EINVAL).
> > If the user has set ctx_out/ctx_size_out, copy the potentially modified
> > __sk_buff back to the userspace.
> > 
> > We require all fields of input __sk_buff 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.
> > 
> > The API is intentionally vague (i.e. we don't explicitly add __sk_buff
> > to bpf_attr, but ctx_in) to potentially let other test_run types use
> > this interface in the future (this can be xdp_md for xdp types for
> > example).
> > 
> > v3:
> >   * handle case where ctx_in is NULL, but ctx_out is not [Martin]
> >   * convert size==0 checks to ptr==NULL checks and add some extra ptr
> >     checks [Martin]
> > 
> > v2:
> >   * Addressed comments from Martin Lau
> > 
> > Cc: Martin Lau <kafai@fb.com>
> > Signed-off-by: Stanislav Fomichev <sdf@google.com>
> > ---
> >  include/uapi/linux/bpf.h |   7 ++
> >  kernel/bpf/syscall.c     |  10 ++-
> >  net/bpf/test_run.c       | 142 ++++++++++++++++++++++++++++++++++++---
> >  3 files changed, 150 insertions(+), 9 deletions(-)
> > 
> > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> > index 837024512baf..8e96f99cebf8 100644
> > --- a/include/uapi/linux/bpf.h
> > +++ b/include/uapi/linux/bpf.h
> > @@ -396,6 +396,13 @@ union bpf_attr {
> >  		__aligned_u64	data_out;
> >  		__u32		repeat;
> >  		__u32		duration;
> > +		__u32		ctx_size_in;	/* input: len of ctx_in */
> > +		__u32		ctx_size_out;	/* input/output: len of ctx_out
> > +						 *   returns ENOSPC if ctx_out
> > +						 *   is too small.
> > +						 */
> > +		__aligned_u64	ctx_in;
> > +		__aligned_u64	ctx_out;
> >  	} test;
> >  
> >  	struct { /* anonymous struct used by BPF_*_GET_*_ID */
> > diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> > index 1d65e56594db..5bb963e8f9b0 100644
> > --- a/kernel/bpf/syscall.c
> > +++ b/kernel/bpf/syscall.c
> > @@ -1949,7 +1949,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
> >  	return cgroup_bpf_prog_query(attr, uattr);
> >  }
> >  
> > -#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
> > +#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
> >  
> >  static int bpf_prog_test_run(const union bpf_attr *attr,
> >  			     union bpf_attr __user *uattr)
> > @@ -1962,6 +1962,14 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
> >  	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
> >  		return -EINVAL;
> >  
> > +	if ((attr->test.ctx_size_in && !attr->test.ctx_in) ||
> > +	    (!attr->test.ctx_size_in && attr->test.ctx_in))
> > +		return -EINVAL;
> > +
> > +	if ((attr->test.ctx_size_out && !attr->test.ctx_out) ||
> > +	    (!attr->test.ctx_size_out && attr->test.ctx_out))
> > +		return -EINVAL;
> > +
> >  	prog = bpf_prog_get(attr->test.prog_fd);
> >  	if (IS_ERR(prog))
> >  		return PTR_ERR(prog);
> > diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
> > index fab142b796ef..2023d8841c6d 100644
> > --- a/net/bpf/test_run.c
> > +++ b/net/bpf/test_run.c
> > @@ -123,12 +123,125 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
> >  	return data;
> >  }
> >  
> > +static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
> > +{
> > +	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
> > +	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
> > +	u32 size = kattr->test.ctx_size_in;
> > +	void *data;
> > +	int err;
> > +
> > +	if (!data_in && !data_out)
> > +		return NULL;
> > +
> > +	data = kzalloc(max_size, GFP_USER);
> > +	if (!data)
> > +		return ERR_PTR(-ENOMEM);
> > +
> > +	if (data_in) {
> > +		err = bpf_check_uarg_tail_zero(data_in, max_size, size);
> > +		if (err) {
> > +			kfree(data);
> > +			return ERR_PTR(err);
> > +		}
> > +
> > +		if (copy_from_user(data, data_in, size)) {
> A min_t is needed:
> 		size = min_t(u32, max_size, size);
> 		if (copy_from_user(data, data_in, size)) {
Ah, sorry about that, good catch! Will respin shortly.

> Others lgtm,
> 
> Acked-by: Martin KaFai Lau <kafai@fb.com>
Thank you for a review!

> > +			kfree(data);
> > +			return ERR_PTR(-EFAULT);
> > +		}
> > +	}
> > +	return data;
> > +}