提交 7d672345 编写于 作者: D Daniel Borkmann 提交者: David S. Miller

bpf: add generic bpf_csum_diff helper

For L4 checksums, we currently have bpf_l4_csum_replace() helper. It's
currently limited to handle 2 and 4 byte changes in a header and feeds the
from/to into inet_proto_csum_replace{2,4}() helpers of the kernel. When
working with IPv6, for example, this makes it rather cumbersome to deal
with, similarly when editing larger parts of a header.

Instead, extend the API in a more generic way: For bpf_l4_csum_replace(),
add a case for header field mask of 0 to change the checksum at a given
offset through inet_proto_csum_replace_by_diff(), and provide a helper
bpf_csum_diff() that can generically calculate a from/to diff for arbitrary
amounts of data.

This can be used in multiple ways: for the bpf_l4_csum_replace() only
part, this even provides us with the option to insert precalculated diffs
from user space f.e. from a map, or from bpf_csum_diff() during runtime.

bpf_csum_diff() has a optional from/to stack buffer input, so we can
calculate a diff by using a scratchbuffer for scenarios where we're
inserting (from is NULL), removing (to is NULL) or diffing (from/to buffers
don't need to be of equal size) data. Also, bpf_csum_diff() allows to
feed a previous csum into csum_partial(), so the function can also be
cascaded.
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 8e2fe1d9
...@@ -287,6 +287,17 @@ enum bpf_func_id { ...@@ -287,6 +287,17 @@ enum bpf_func_id {
* Return: >= 0 stackid on success or negative error * Return: >= 0 stackid on success or negative error
*/ */
BPF_FUNC_get_stackid, BPF_FUNC_get_stackid,
/**
* bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
* @from: raw from buffer
* @from_size: length of from buffer
* @to: raw to buffer
* @to_size: length of to buffer
* @seed: optional seed
* Return: csum result
*/
BPF_FUNC_csum_diff,
__BPF_FUNC_MAX_ID, __BPF_FUNC_MAX_ID,
}; };
......
...@@ -1491,6 +1491,12 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) ...@@ -1491,6 +1491,12 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
return -EFAULT; return -EFAULT;
switch (flags & BPF_F_HDR_FIELD_MASK) { switch (flags & BPF_F_HDR_FIELD_MASK) {
case 0:
if (unlikely(from != 0))
return -EINVAL;
inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo);
break;
case 2: case 2:
inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
break; break;
...@@ -1519,6 +1525,51 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = { ...@@ -1519,6 +1525,51 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = {
.arg5_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING,
}; };
struct bpf_csum_scratchpad {
__be32 diff[128];
};
static DEFINE_PER_CPU(struct bpf_csum_scratchpad, bpf_csum_sp);
static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed)
{
struct bpf_csum_scratchpad *sp = this_cpu_ptr(&bpf_csum_sp);
u64 diff_size = from_size + to_size;
__be32 *from = (__be32 *) (long) r1;
__be32 *to = (__be32 *) (long) r3;
int i, j = 0;
/* This is quite flexible, some examples:
*
* from_size == 0, to_size > 0, seed := csum --> pushing data
* from_size > 0, to_size == 0, seed := csum --> pulling data
* from_size > 0, to_size > 0, seed := 0 --> diffing data
*
* Even for diffing, from_size and to_size don't need to be equal.
*/
if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) ||
diff_size > sizeof(sp->diff)))
return -EINVAL;
for (i = 0; i < from_size / sizeof(__be32); i++, j++)
sp->diff[j] = ~from[i];
for (i = 0; i < to_size / sizeof(__be32); i++, j++)
sp->diff[j] = to[i];
return csum_partial(sp->diff, diff_size, seed);
}
const struct bpf_func_proto bpf_csum_diff_proto = {
.func = bpf_csum_diff,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_STACK,
.arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO,
.arg3_type = ARG_PTR_TO_STACK,
.arg4_type = ARG_CONST_STACK_SIZE_OR_ZERO,
.arg5_type = ARG_ANYTHING,
};
static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
{ {
struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2; struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2;
...@@ -1849,6 +1900,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) ...@@ -1849,6 +1900,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return &bpf_skb_store_bytes_proto; return &bpf_skb_store_bytes_proto;
case BPF_FUNC_skb_load_bytes: case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto; return &bpf_skb_load_bytes_proto;
case BPF_FUNC_csum_diff:
return &bpf_csum_diff_proto;
case BPF_FUNC_l3_csum_replace: case BPF_FUNC_l3_csum_replace:
return &bpf_l3_csum_replace_proto; return &bpf_l3_csum_replace_proto;
case BPF_FUNC_l4_csum_replace: case BPF_FUNC_l4_csum_replace:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册