sfc: fix XDP-redirect in this driver

XDP-redirect is broken in this driver sfc. XDP_REDIRECT requires
tailroom for skb_shared_info when creating an SKB based on the
redirected xdp_frame (both in cpumap and veth).

The fix requires some initial explaining. The driver uses RX page-split
when possible. It reserves the top 64 bytes in the RX-page for storing
dma_addr (struct efx_rx_page_state). It also have the XDP recommended
headroom of XDP_PACKET_HEADROOM (256 bytes). As it doesn't reserve any
tailroom, it can still fit two standard MTU (1500) frames into one page.

The sizeof struct skb_shared_info in 320 bytes. Thus drivers like ixgbe
and i40e, reduce their XDP headroom to 192 bytes, which allows them to
fit two frames with max 1536 bytes into a 4K page (192+1536+320=2048).

The fix is to reduce this drivers headroom to 128 bytes and add the 320
bytes tailroom. This account for reserved top 64 bytes in the page, and
still fit two frame in a page for normal MTUs.

We must never go below 128 bytes of headroom for XDP, as one cacheline
is for xdp_frame area and next cacheline is reserved for metadata area.

Fixes: eb9a36be7f3e ("sfc: perform XDP processing on received packets")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index b0d76bc..1799ff9 100644 (file)
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -200,11 +200,11 @@ void efx_link_status_changed(struct efx_nic *efx)
 unsigned int efx_xdp_max_mtu(struct efx_nic *efx)
 {
        /* The maximum MTU that we can fit in a single page, allowing for
-        * framing, overhead and XDP headroom.
+        * framing, overhead and XDP headroom + tailroom.
         */
        int overhead = EFX_MAX_FRAME_LEN(0) + sizeof(struct efx_rx_page_state) +
                       efx->rx_prefix_size + efx->type->rx_buffer_padding +
-                      efx->rx_ip_align + XDP_PACKET_HEADROOM;
+                      efx->rx_ip_align + EFX_XDP_HEADROOM + EFX_XDP_TAILROOM;
 
        return PAGE_SIZE - overhead;
 }
@@ -302,8 +302,9 @@ static void efx_start_datapath(struct efx_nic *efx)
        efx->rx_dma_len = (efx->rx_prefix_size +
                           EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
                           efx->type->rx_buffer_padding);
-       rx_buf_len = (sizeof(struct efx_rx_page_state) + XDP_PACKET_HEADROOM +
-                     efx->rx_ip_align + efx->rx_dma_len);
+       rx_buf_len = (sizeof(struct efx_rx_page_state)   + EFX_XDP_HEADROOM +
+                     efx->rx_ip_align + efx->rx_dma_len + EFX_XDP_TAILROOM);
+
        if (rx_buf_len <= PAGE_SIZE) {
                efx->rx_scatter = efx->type->always_rx_scatter;
                efx->rx_buffer_order = 0;

diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index b836315..b084e62 100644 (file)
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -91,6 +91,12 @@
 #define EFX_RX_BUF_ALIGNMENT   4
 #endif
 
+/* Non-standard XDP_PACKET_HEADROOM and tailroom to satisfy XDP_REDIRECT and
+ * still fit two standard MTU size packets into a single 4K page.
+ */
+#define EFX_XDP_HEADROOM       128
+#define EFX_XDP_TAILROOM       SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
+
 /* Forward declare Precision Time Protocol (PTP) support structure. */
 struct efx_ptp_data;
 struct hwtstamp_config;

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index a2042f1..260352d 100644 (file)
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -302,7 +302,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
               efx->rx_prefix_size);
 
        xdp.data = *ehp;
-       xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
+       xdp.data_hard_start = xdp.data - EFX_XDP_HEADROOM;
 
        /* No support yet for XDP metadata */
        xdp_set_data_meta_invalid(&xdp);

diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index ee8beb8..e10c238 100644 (file)
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -412,10 +412,10 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic)
                        index = rx_queue->added_count & rx_queue->ptr_mask;
                        rx_buf = efx_rx_buffer(rx_queue, index);
                        rx_buf->dma_addr = dma_addr + efx->rx_ip_align +
-                                          XDP_PACKET_HEADROOM;
+                                          EFX_XDP_HEADROOM;
                        rx_buf->page = page;
                        rx_buf->page_offset = page_offset + efx->rx_ip_align +
-                                             XDP_PACKET_HEADROOM;
+                                             EFX_XDP_HEADROOM;
                        rx_buf->len = efx->rx_dma_len;
                        rx_buf->flags = 0;
                        ++rx_queue->added_count;
@@ -433,7 +433,7 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic)
 void efx_rx_config_page_split(struct efx_nic *efx)
 {
        efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align +
-                                     XDP_PACKET_HEADROOM,
+                                     EFX_XDP_HEADROOM + EFX_XDP_TAILROOM,
                                      EFX_RX_BUF_ALIGNMENT);
        efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 :
                ((PAGE_SIZE - sizeof(struct efx_rx_page_state)) /