Staging: Octeon Ethernet: Enable scatter-gather.

Octeon ethernet hardware can handle NETIF_F_SG, so we enable it.

A gather list of up to six fragments will fit in the SKB's CB
structure, so no extra memory is required.  If a SKB has more than six
fragments, we must linearize it.

Signed-off-by: David Daney <ddaney@caviumnetworks.com>
To: linux-mips@linux-mips.org
To: gregkh@suse.de
Patchwork: http://patchwork.linux-mips.org/patch/838/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index 05b58f8b58fd97bfb5dd20d7048612920e9d572b..bc67e416e4214f6e5ec4d391758a06147a76a6b4 100644 (file)
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -53,6 +53,8 @@
 
 #include "cvmx-gmxx-defs.h"
 
+#define CVM_OCT_SKB_CB(skb)    ((u64 *)((skb)->cb))
+
 /*
  * You can define GET_SKBUFF_QOS() to override how the skbuff output
  * function determines which output queue is used. The default
@@ -121,6 +123,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
        uint64_t old_scratch;
        uint64_t old_scratch2;
        int qos;
+       int i;
        enum {QUEUE_CORE, QUEUE_HW, QUEUE_DROP} queue_type;
        struct octeon_ethernet *priv = netdev_priv(dev);
        struct sk_buff *to_free_list;
@@ -170,6 +173,28 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
                                               MAX_SKB_TO_FREE);
        }
 
+       /*
+        * We have space for 6 segment pointers, If there will be more
+        * than that, we must linearize.
+        */
+       if (unlikely(skb_shinfo(skb)->nr_frags > 5)) {
+               if (unlikely(__skb_linearize(skb))) {
+                       queue_type = QUEUE_DROP;
+                       if (USE_ASYNC_IOBDMA) {
+                               /* Get the number of skbuffs in use by the hardware */
+                               CVMX_SYNCIOBDMA;
+                               skb_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
+                       } else {
+                               /* Get the number of skbuffs in use by the hardware */
+                               skb_to_free = cvmx_fau_fetch_and_add32(priv->fau + qos * 4,
+                                                                      MAX_SKB_TO_FREE);
+                       }
+                       skb_to_free = cvm_oct_adjust_skb_to_free(skb_to_free, priv->fau + qos * 4);
+                       spin_lock_irqsave(&priv->tx_free_list[qos].lock, flags);
+                       goto skip_xmit;
+               }
+       }
+
        /*
         * The CN3XXX series of parts has an errata (GMX-401) which
         * causes the GMX block to hang if a collision occurs towards
@@ -198,13 +223,6 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
                }
        }
 
-       /* Build the PKO buffer pointer */
-       hw_buffer.u64 = 0;
-       hw_buffer.s.addr = cvmx_ptr_to_phys(skb->data);
-       hw_buffer.s.pool = 0;
-       hw_buffer.s.size =
-           (unsigned long)skb_end_pointer(skb) - (unsigned long)skb->head;
-
        /* Build the PKO command */
        pko_command.u64 = 0;
        pko_command.s.n2 = 1;   /* Don't pollute L2 with the outgoing packet */
@@ -215,6 +233,31 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 
        pko_command.s.dontfree = 1;
        pko_command.s.reg0 = priv->fau + qos * 4;
+
+       /* Build the PKO buffer pointer */
+       hw_buffer.u64 = 0;
+       if (skb_shinfo(skb)->nr_frags == 0) {
+               hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)skb->data);
+               hw_buffer.s.pool = 0;
+               hw_buffer.s.size = skb->len;
+       } else {
+               hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)skb->data);
+               hw_buffer.s.pool = 0;
+               hw_buffer.s.size = skb_headlen(skb);
+               CVM_OCT_SKB_CB(skb)[0] = hw_buffer.u64;
+               for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+                       struct skb_frag_struct *fs = skb_shinfo(skb)->frags + i;
+                       hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)(page_address(fs->page) + fs->page_offset));
+                       hw_buffer.s.size = fs->size;
+                       CVM_OCT_SKB_CB(skb)[i + 1] = hw_buffer.u64;
+               }
+               hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)CVM_OCT_SKB_CB(skb));
+               hw_buffer.s.size = skb_shinfo(skb)->nr_frags + 1;
+               pko_command.s.segs = skb_shinfo(skb)->nr_frags + 1;
+               pko_command.s.gather = 1;
+               goto dont_put_skbuff_in_hw;
+       }
+
        /*
         * See if we can put this skb in the FPA pool. Any strange
         * behavior from the Linux networking stack will most likely

diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c
index 9f5b7419e777d9a6fafb8cee1ea9f94f9b89f34e..9d632020b9ee6afa5b0f6cae893f28dba63d0a3a 100644 (file)
--- a/drivers/staging/octeon/ethernet.c
+++ b/drivers/staging/octeon/ethernet.c
@@ -484,8 +484,11 @@ int cvm_oct_common_init(struct net_device *dev)
            && (always_use_pow || strstr(pow_send_list, dev->name)))
                priv->queue = -1;
 
-       if (priv->queue != -1 && USE_HW_TCPUDP_CHECKSUM)
-               dev->features |= NETIF_F_IP_CSUM;
+       if (priv->queue != -1) {
+               dev->features |= NETIF_F_SG;
+               if (USE_HW_TCPUDP_CHECKSUM)
+                       dev->features |= NETIF_F_IP_CSUM;
+       }
 
        /* We do our own locking, Linux doesn't need to */
        dev->features |= NETIF_F_LLTX;