mvneta: Add XDP frame size to driver

This marvell driver mvneta uses PAGE_SIZE frames, which makes it
really easy to convert.  Driver updates rxq and now frame_sz
once per NAPI call.

This driver takes advantage of page_pool PP_FLAG_DMA_SYNC_DEV that
can help reduce the number of cache-lines that need to be flushed
when doing DMA sync for_device. Due to xdp_adjust_tail can grow the
area accessible to the by the CPU (can possibly write into), then max
sync length *after* bpf_prog_run_xdp() needs to be taken into account.

For XDP_TX action the driver is smart and does DMA-sync. When growing
tail this is still safe, because page_pool have DMA-mapped the entire
page size.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Cc: thomas.petazzoni@bootlin.com
Link: https://lore.kernel.org/bpf/158945335786.97035.12714388304493736747.stgit@firesoul

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e0e9e56..41d2a0e 100644 (file)
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2148,12 +2148,17 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
               struct bpf_prog *prog, struct xdp_buff *xdp,
               struct mvneta_stats *stats)
 {
-       unsigned int len;
+       unsigned int len, sync;
+       struct page *page;
        u32 ret, act;
 
        len = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
        act = bpf_prog_run_xdp(prog, xdp);
 
+       /* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
+       sync = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
+       sync = max(sync, len);
+
        switch (act) {
        case XDP_PASS:
                stats->xdp_pass++;
@@ -2164,9 +2169,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
                err = xdp_do_redirect(pp->dev, xdp, prog);
                if (unlikely(err)) {
                        ret = MVNETA_XDP_DROPPED;
-                       page_pool_put_page(rxq->page_pool,
-                                          virt_to_head_page(xdp->data), len,
-                                          true);
+                       page = virt_to_head_page(xdp->data);
+                       page_pool_put_page(rxq->page_pool, page, sync, true);
                } else {
                        ret = MVNETA_XDP_REDIR;
                        stats->xdp_redirect++;
@@ -2175,10 +2179,10 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
        }
        case XDP_TX:
                ret = mvneta_xdp_xmit_back(pp, xdp);
-               if (ret != MVNETA_XDP_TX)
-                       page_pool_put_page(rxq->page_pool,
-                                          virt_to_head_page(xdp->data), len,
-                                          true);
+               if (ret != MVNETA_XDP_TX) {
+                       page = virt_to_head_page(xdp->data);
+                       page_pool_put_page(rxq->page_pool, page, sync, true);
+               }
                break;
        default:
                bpf_warn_invalid_xdp_action(act);
@@ -2187,8 +2191,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
                trace_xdp_exception(pp->dev, prog, act);
                /* fall through */
        case XDP_DROP:
-               page_pool_put_page(rxq->page_pool,
-                                  virt_to_head_page(xdp->data), len, true);
+               page = virt_to_head_page(xdp->data);
+               page_pool_put_page(rxq->page_pool, page, sync, true);
                ret = MVNETA_XDP_DROPPED;
                stats->xdp_drop++;
                break;
@@ -2320,6 +2324,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
        rcu_read_lock();
        xdp_prog = READ_ONCE(pp->xdp_prog);
        xdp_buf.rxq = &rxq->xdp_rxq;
+       xdp_buf.frame_sz = PAGE_SIZE;
 
        /* Fairness NAPI loop */
        while (rx_proc < budget && rx_proc < rx_todo) {