myri10ge: small rx_done refactoring

Avoid theoretical race condition regarding accessing dev->features
NETIF_F_LRO flag, which is illustrated below.

CPU1					CPU2

myri10ge_clean_rx_done():		myri10ge_set_flags():
					or
					myri10ge_set_rx_csum():

if (dev->features & NETIF_F_LRO)
        setup lro
					dev->features |= NETIF_F_LRO
					or
					dev->features &= ~NETIF_F_LRO;
if (dev->features & NETIF_F_LRO)
        flush lro

On the way reduce myri10ge_rx_done() number of arguments and calls by
moving mgp->small_bytes check into that function. That reduce code size

from:
   text	   data	    bss	    dec	    hex	filename
  36644	    248	    100	  36992	   9080	drivers/net/myri10ge/myri10ge.o

to:
   text	   data	    bss	    dec	    hex	filename
  36037	    247	    100	  36384	   8e20	drivers/net/myri10ge/myri10ge.o

on my i686 system, what should also make myri10ge_clean_rx_done()
being faster.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 1f4e8680a96a7c8b642e3e750d4132c0766ddc7e..673dc600c891fedabe7f63eaccd295b629c31364 100644 (file)
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -1312,17 +1312,26 @@ myri10ge_unmap_rx_page(struct pci_dev *pdev,
                                 * page into an skb */
 
 static inline int
-myri10ge_rx_done(struct myri10ge_slice_state *ss, struct myri10ge_rx_buf *rx,
-                int bytes, int len, __wsum csum)
+myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum,
+                int lro_enabled)
 {
        struct myri10ge_priv *mgp = ss->mgp;
        struct sk_buff *skb;
        struct skb_frag_struct rx_frags[MYRI10GE_MAX_FRAGS_PER_FRAME];
-       int i, idx, hlen, remainder;
+       struct myri10ge_rx_buf *rx;
+       int i, idx, hlen, remainder, bytes;
        struct pci_dev *pdev = mgp->pdev;
        struct net_device *dev = mgp->dev;
        u8 *va;
 
+       if (len <= mgp->small_bytes) {
+               rx = &ss->rx_small;
+               bytes = mgp->small_bytes;
+       } else {
+               rx = &ss->rx_big;
+               bytes = mgp->big_bytes;
+       }
+
        len += MXGEFW_PAD;
        idx = rx->cnt & rx->mask;
        va = page_address(rx->info[idx].page) + rx->info[idx].page_offset;
@@ -1341,7 +1350,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, struct myri10ge_rx_buf *rx,
                remainder -= MYRI10GE_ALLOC_SIZE;
        }
 
-       if (dev->features & NETIF_F_LRO) {
+       if (lro_enabled) {
                rx_frags[0].page_offset += MXGEFW_PAD;
                rx_frags[0].size -= MXGEFW_PAD;
                len -= MXGEFW_PAD;
@@ -1463,7 +1472,7 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
 {
        struct myri10ge_rx_done *rx_done = &ss->rx_done;
        struct myri10ge_priv *mgp = ss->mgp;
-       struct net_device *netdev = mgp->dev;
+
        unsigned long rx_bytes = 0;
        unsigned long rx_packets = 0;
        unsigned long rx_ok;
@@ -1474,18 +1483,18 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
        u16 length;
        __wsum checksum;
 
+       /*
+        * Prevent compiler from generating more than one ->features memory
+        * access to avoid theoretical race condition with functions that
+        * change NETIF_F_LRO flag at runtime.
+        */
+       bool lro_enabled = ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO;
+
        while (rx_done->entry[idx].length != 0 && work_done < budget) {
                length = ntohs(rx_done->entry[idx].length);
                rx_done->entry[idx].length = 0;
                checksum = csum_unfold(rx_done->entry[idx].checksum);
-               if (length <= mgp->small_bytes)
-                       rx_ok = myri10ge_rx_done(ss, &ss->rx_small,
-                                                mgp->small_bytes,
-                                                length, checksum);
-               else
-                       rx_ok = myri10ge_rx_done(ss, &ss->rx_big,
-                                                mgp->big_bytes,
-                                                length, checksum);
+               rx_ok = myri10ge_rx_done(ss, length, checksum, lro_enabled);
                rx_packets += rx_ok;
                rx_bytes += rx_ok * (unsigned long)length;
                cnt++;
@@ -1497,7 +1506,7 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
        ss->stats.rx_packets += rx_packets;
        ss->stats.rx_bytes += rx_bytes;
 
-       if (netdev->features & NETIF_F_LRO)
+       if (lro_enabled)
                lro_flush_all(&rx_done->lro_mgr);
 
        /* restock receive rings if needed */