&xdp_buff and &xdp_frame are bound in a way that
xdp_buff->data_hard_start == xdp_frame
It's always the case and e.g. xdp_convert_buff_to_frame() relies on
this.
IOW, the following:
for (u32 i = 0; i < 0xdead; i++) {
xdpf = xdp_convert_buff_to_frame(&xdp);
xdp_convert_frame_to_buff(xdpf, &xdp);
}
shouldn't ever modify @xdpf's contents or the pointer itself.
However, "live packet" code wrongly treats &xdp_frame as part of its
context placed *before* the data_hard_start. With such flow,
data_hard_start is sizeof(*xdpf) off to the right and no longer points
to the XDP frame.
Instead of replacing `sizeof(ctx)` with `offsetof(ctx, xdpf)` in several
places and praying that there are no more miscalcs left somewhere in the
code, unionize ::frm with ::data in a flex array, so that both starts
pointing to the actual data_hard_start and the XDP frame actually starts
being a part of it, i.e. a part of the headroom, not the context.
A nice side effect is that the maximum frame size for this mode gets
increased by 40 bytes, as xdp_buff::frame_sz includes everything from
data_hard_start (-> includes xdpf already) to the end of XDP/skb shared
info.
Also update %MAX_PKT_SIZE accordingly in the selftests code. Leave it
hardcoded for 64 bit && 64-byte cacheline && 4k pages, it can be made
more flexible later on.
Minor: align `&head->data` with how `head->frm` is assigned for
consistency.
Minor #2: rename 'frm' to 'frame' in &xdp_page_head while at it for
clarity.
(was found while testing XDP traffic generator on ice, which calls
xdp_convert_frame_to_buff() for each XDP frame)
Fixes: b530e9e1063e ("bpf: Add "live packet" mode for XDP in BPF_PROG_RUN")
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Signed-off-by: Alexander Lobakin <[email protected]>
---
From v2[0]:
- update %MAX_PKT_SIZE in the selftests (Daniel, CI bots);
- add conditional static assert to avoid facing the same issue in future;
- pick one Acked-by (Toke).
From v1[1]:
- align `&head->data` with how `head->frm` is assigned for consistency
(Toke);
- rename 'frm' to 'frame' in &xdp_page_head (Jakub);
- no functional changes.
[0] https://lore.kernel.org/bpf/[email protected]
[1] https://lore.kernel.org/bpf/[email protected]
---
net/bpf/test_run.c | 23 ++++++++++++++-----
.../bpf/prog_tests/xdp_do_redirect.c | 4 ++--
2 files changed, 19 insertions(+), 8 deletions(-)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 2723623429ac..b9e77ab94b03 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -97,8 +97,11 @@ static bool bpf_test_timer_continue(struct bpf_test_timer *t, int iterations,
struct xdp_page_head {
struct xdp_buff orig_ctx;
struct xdp_buff ctx;
- struct xdp_frame frm;
- u8 data[];
+ union {
+ /* ::data_hard_start starts here */
+ DECLARE_FLEX_ARRAY(struct xdp_frame, frame);
+ DECLARE_FLEX_ARRAY(u8, data);
+ };
};
struct xdp_test_data {
@@ -116,6 +119,14 @@ struct xdp_test_data {
#define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head))
#define TEST_XDP_MAX_BATCH 256
+#if BITS_PER_LONG == 64 && SMP_CACHE_BYTES == 64 && PAGE_SIZE == SZ_4K
+/* tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c:%MAX_PKT_SIZE
+ * must be updated accordingly when any of these changes.
+ */
+static_assert(TEST_XDP_FRAME_SIZE - XDP_PACKET_HEADROOM -
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) == 3408);
+#endif
+
static void xdp_test_run_init_page(struct page *page, void *arg)
{
struct xdp_page_head *head = phys_to_virt(page_to_phys(page));
@@ -132,8 +143,8 @@ static void xdp_test_run_init_page(struct page *page, void *arg)
headroom -= meta_len;
new_ctx = &head->ctx;
- frm = &head->frm;
- data = &head->data;
+ frm = head->frame;
+ data = head->data;
memcpy(data + headroom, orig_ctx->data_meta, frm_len);
xdp_init_buff(new_ctx, TEST_XDP_FRAME_SIZE, &xdp->rxq);
@@ -223,7 +234,7 @@ static void reset_ctx(struct xdp_page_head *head)
head->ctx.data = head->orig_ctx.data;
head->ctx.data_meta = head->orig_ctx.data_meta;
head->ctx.data_end = head->orig_ctx.data_end;
- xdp_update_frame_from_buff(&head->ctx, &head->frm);
+ xdp_update_frame_from_buff(&head->ctx, head->frame);
}
static int xdp_recv_frames(struct xdp_frame **frames, int nframes,
@@ -285,7 +296,7 @@ static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog,
head = phys_to_virt(page_to_phys(page));
reset_ctx(head);
ctx = &head->ctx;
- frm = &head->frm;
+ frm = head->frame;
xdp->frame_cnt++;
act = bpf_prog_run_xdp(prog, ctx);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index a50971c6cf4a..0253070138b1 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -63,9 +63,9 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd)
}
/* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) -
- * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes
+ * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3408 bytes
*/
-#define MAX_PKT_SIZE 3368
+#define MAX_PKT_SIZE 3408
static void test_max_pkt_size(int fd)
{
char data[MAX_PKT_SIZE + 1] = {};
--
2.39.1
On 2/15/23 7:21 AM, Alexander Lobakin wrote:
> /* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) -
> - * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes
> + * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3408 bytes
> */
> -#define MAX_PKT_SIZE 3368
> +#define MAX_PKT_SIZE 3408
s390 has a different cache line size:
https://lore.kernel.org/all/[email protected]/
The above s390 fix is in bpf-next. It is better to target this patch for
bpf-next also such that the CI can test it in s390.
From: Martin Kafai Lau <[email protected]>
Date: Wed, 15 Feb 2023 10:04:51 -0800
> On 2/15/23 7:21 AM, Alexander Lobakin wrote:
>> /* The maximum permissible size is: PAGE_SIZE - sizeof(struct
>> xdp_page_head) -
>> - * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes
>> + * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3408 bytes
>> */
>> -#define MAX_PKT_SIZE 3368
>> +#define MAX_PKT_SIZE 3408
>
> s390 has a different cache line size:
>
> https://lore.kernel.org/all/[email protected]/
>
> The above s390 fix is in bpf-next. It is better to target this patch for
> bpf-next also such that the CI can test it in s390.
>
Oh, thanks for letting me know! Will do in a bit.
Thanks,
Olek