summaryrefslogtreecommitdiffstats
path: root/net/bpf
diff options
context:
space:
mode:
authorStanislav Fomichev <sdf@google.com>2019-04-09 11:49:09 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2019-04-11 10:21:40 +0200
commitb0b9395d865e3060d97658fbc9ba3f77fecc8da1 (patch)
tree3571895a08ad678d81b782fa3f7b5eca33288107 /net/bpf
parent569b0c77735d1567963cb4601390877b30458be4 (diff)
downloadlinux-b0b9395d865e3060d97658fbc9ba3f77fecc8da1.tar.bz2
bpf: support input __sk_buff context in BPF_PROG_TEST_RUN
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). v4: * don't copy more than allowed in bpf_ctx_init [Martin] 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 Signed-off-by: Stanislav Fomichev <sdf@google.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Diffstat (limited to 'net/bpf')
-rw-r--r--net/bpf/test_run.c143
1 files changed, 135 insertions, 8 deletions
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fab142b796ef..cbd4fb65aa4f 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -123,12 +123,126 @@ 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);
+ }
+
+ size = min_t(u32, max_size, size);
+ if (copy_from_user(data, data_in, size)) {
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+ }
+ }
+ return data;
+}
+
+static int bpf_ctx_finish(const union bpf_attr *kattr,
+ union bpf_attr __user *uattr, const void *data,
+ u32 size)
+{
+ void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+ int err = -EFAULT;
+ u32 copy_size = size;
+
+ if (!data || !data_out)
+ return 0;
+
+ if (copy_size > kattr->test.ctx_size_out) {
+ copy_size = kattr->test.ctx_size_out;
+ err = -ENOSPC;
+ }
+
+ if (copy_to_user(data_out, data, copy_size))
+ goto out;
+ if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size)))
+ goto out;
+ if (err != -ENOSPC)
+ err = 0;
+out:
+ return err;
+}
+
+/**
+ * range_is_zero - test whether buffer is initialized
+ * @buf: buffer to check
+ * @from: check from this position
+ * @to: check up until (excluding) this position
+ *
+ * This function returns true if the there is a non-zero byte
+ * in the buf in the range [from,to).
+ */
+static inline bool range_is_zero(void *buf, size_t from, size_t to)
+{
+ return !memchr_inv((u8 *)buf + from, 0, to - from);
+}
+
+static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+ struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+ if (!__skb)
+ return 0;
+
+ /* make sure the fields we don't use are zeroed */
+ if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority)))
+ return -EINVAL;
+
+ /* priority is allowed */
+
+ if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
+ FIELD_SIZEOF(struct __sk_buff, priority),
+ offsetof(struct __sk_buff, cb)))
+ return -EINVAL;
+
+ /* cb is allowed */
+
+ if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
+ FIELD_SIZEOF(struct __sk_buff, cb),
+ sizeof(struct __sk_buff)))
+ return -EINVAL;
+
+ skb->priority = __skb->priority;
+ memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
+
+ return 0;
+}
+
+static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+ struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+ if (!__skb)
+ return;
+
+ __skb->priority = skb->priority;
+ memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
+}
+
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
bool is_l2 = false, is_direct_pkt_access = false;
u32 size = kattr->test.data_size_in;
u32 repeat = kattr->test.repeat;
+ struct __sk_buff *ctx = NULL;
u32 retval, duration;
int hh_len = ETH_HLEN;
struct sk_buff *skb;
@@ -141,6 +255,12 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
if (IS_ERR(data))
return PTR_ERR(data);
+ ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
+ if (IS_ERR(ctx)) {
+ kfree(data);
+ return PTR_ERR(ctx);
+ }
+
switch (prog->type) {
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
@@ -158,6 +278,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
sk = kzalloc(sizeof(struct sock), GFP_USER);
if (!sk) {
kfree(data);
+ kfree(ctx);
return -ENOMEM;
}
sock_net_set(sk, current->nsproxy->net_ns);
@@ -166,6 +287,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
skb = build_skb(data, 0);
if (!skb) {
kfree(data);
+ kfree(ctx);
kfree(sk);
return -ENOMEM;
}
@@ -180,32 +302,37 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
__skb_push(skb, hh_len);
if (is_direct_pkt_access)
bpf_compute_data_pointers(skb);
+ ret = convert___skb_to_skb(skb, ctx);
+ if (ret)
+ goto out;
ret = bpf_test_run(prog, skb, repeat, &retval, &duration);
- if (ret) {
- kfree_skb(skb);
- kfree(sk);
- return ret;
- }
+ if (ret)
+ goto out;
if (!is_l2) {
if (skb_headroom(skb) < hh_len) {
int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
- kfree_skb(skb);
- kfree(sk);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
}
memset(__skb_push(skb, hh_len), 0, hh_len);
}
+ convert_skb_to___skb(skb, ctx);
size = skb->len;
/* bpf program can never convert linear skb to non-linear */
if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
size = skb_headlen(skb);
ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+ if (!ret)
+ ret = bpf_ctx_finish(kattr, uattr, ctx,
+ sizeof(struct __sk_buff));
+out:
kfree_skb(skb);
kfree(sk);
+ kfree(ctx);
return ret;
}