bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES

&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 && 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: b530e9e1 ("bpf: Add "live packet" mode for XDP in BPF_PROG_RUN")
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20230224163607.2994755-1-aleksander.lobakin@intel.comSigned-off-by: Martin KaFai Lau <martin.lau@kernel.org>

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 {
@@ -113,6 +116,10 @@ struct xdp_test_data {
 	u32 frame_cnt;
 };
 
+/* tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c:%MAX_PKT_SIZE
+ * must be updated accordingly this gets changed, otherwise BPF selftests
+ * will fail.
+ */
 #define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head))
 #define TEST_XDP_MAX_BATCH 256
 
@@ -132,8 +139,8 @@ 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 +230,7 @@ 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 +292,7 @@ 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);

tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c

@@ -65,12 +65,13 @@ 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
+ * SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) - XDP_PACKET_HEADROOM =
+ * 3408 bytes for 64-byte cacheline and 3216 for 256-byte one.
  */
 #if defined(__s390x__)
-#define MAX_PKT_SIZE 3176
+#define MAX_PKT_SIZE 3216
 #else
-#define MAX_PKT_SIZE 3368
+#define MAX_PKT_SIZE 3408
 #endif
 static void test_max_pkt_size(int fd)
 {