Fixes for the D-Link DFE-580 card.

This is pretty much fixes any issue I can find:
     -  Watchdog timeouts were due to starting the TX DMA engine
        before we had a packet ready for it.  So the first packet
        sent never got out only if we sent more then one packet
        at a time did the others make it out and not blow up.
        Of course reseting the chip then caused us not to transmit
        the first packet again ie. catch-22.  This required logic changes.
     -  Combine interrupts on TX packets being queued up.
     -  Don't keep running around the RX ring since we might get
        out of sync so only go around once per receive
     -  Let the RX engine recover via the poll interface which is
        similar to the TX interface.  This way the chip wakes
        up with no effort when we read enough packets.
     -  Do better hand-shaking on RX & TX packets so they don't
        start of to soon.
     -  Force a duplex setting when the link comes up after
        an ste_init or it will default to half-duplex and be
        really slow.  This only happens on subsequent ste_init.
        The first one worked.
     -  Don't call stat_update for every overflow.  We only monitor
        the collisions so the tick interval is good enough for that.
        Just read in the collision stats to minimize bus reads.
     -  Don't read the miibus every tick since it uses delays and
        delays are not good for performance.
     -  Tie link events directly to the miibus code so the port
        gets set correctly if someone changes the port settings.
     -  Reduce the extreme number of {R,T}FD's.  They would consume
        130K of kernel memory for each NIC.
     -  Set the TX_THRESH to wait for the DMA engine to complete
        before running the TX FIFO.  This hurts peak TX performance
        but under bi-directional load the DMA engine can't keep up
        with the FIFO.  Testing shows that we end up in the case
        anyways (a la dc(4) issues but worse since the RX engine hogs
	everything).
     -  When stopping the card do a reset since the reset verifies the
	card has stopped.  Otherwise on heavy RX load the RX DMA engine
	is still stuffing packets into memory.  If that happens after
	we free the DMA area memory bits get scribled in memory and
	bad things happen.

This card still has seemingly unfixable issues under heavy RX load in
which the card takes over the PCI bus.

Sponsored by:	Vernier Networks
MFC after:	1 week

1 files changed, 15 insertions, 7 deletions

diff --git a/sys/pci/if_stereg.h b/sys/pci/if_stereg.h
index b369d6d..c55af97 100644
--- a/sys/pci/if_stereg.h
+++ b/sys/pci/if_stereg.h
@@ -93,6 +93,10 @@
 #define STE_MAR3		0x66
 #define STE_STATS		0x68
 
+#define STE_LATE_COLLS  0x75
+#define STE_MULTI_COLLS	0x76
+#define STE_SINGLE_COLLS 0x77	
+
 #define STE_DMACTL_RXDMA_STOPPED	0x00000001
 #define STE_DMACTL_TXDMA_CMPREQ		0x00000002
 #define STE_DMACTL_TXDMA_STOPPED	0x00000004
@@ -224,13 +228,13 @@
  * The number of bytes that must in present in the TX FIFO before
  * transmission begins. Value should be in increments of 4 bytes.
  */
-#define STE_TXSTART_THRESH		0x1FFF
+#define STE_TXSTART_THRESH		0x1FFC
 
 /*
  * Number of bytes that must be present in the RX FIFO before
  * an RX EARLY interrupt is generated.
  */
-#define STE_RXEARLY_THRESH		0x1FFF
+#define STE_RXEARLY_THRESH		0x1FFC
 
 #define STE_WAKEEVENT_WAKEPKT_ENB	0x01
 #define STE_WAKEEVENT_MAGICPKT_ENB	0x02
@@ -272,8 +276,9 @@
 #define STE_IMR_RX_DMADONE		0x0400
 
 #define STE_INTRS					\
-	(STE_IMR_RX_DMADONE|STE_IMR_TX_DMADONE|STE_IMR_STATS_OFLOW|	\
-	STE_IMR_TX_DONE|STE_IMR_HOSTERR|STE_IMR_RX_EARLY)
+	(STE_IMR_RX_DMADONE|STE_IMR_TX_DMADONE|	\
+	STE_IMR_TX_DONE|STE_IMR_HOSTERR| \
+        STE_IMR_LINKEVENT)
 
 #define STE_ISR_INTLATCH		0x0001
 #define STE_ISR_HOSTERR			0x0002
@@ -406,7 +411,7 @@ struct ste_frag {
 #define STE_FRAG_LAST		0x80000000
 #define STE_FRAG_LEN		0x00001FFF
 
-#define STE_MAXFRAGS	63
+#define STE_MAXFRAGS	8
 
 struct ste_desc {
 	u_int32_t		ste_next;
@@ -460,9 +465,10 @@ struct ste_desc_onefrag {
 #define STE_MIN_FRAMELEN	60
 #define STE_PACKET_SIZE		1536
 #define ETHER_ALIGN		2
-#define STE_RX_LIST_CNT		128
-#define STE_TX_LIST_CNT		256
+#define STE_RX_LIST_CNT		64
+#define STE_TX_LIST_CNT		64
 #define STE_INC(x, y)		(x) = (x + 1) % y
+#define STE_NEXT(x, y)		(x + 1) % y
 
 struct ste_type {
 	u_int16_t		ste_vid;
@@ -509,10 +515,12 @@ struct ste_softc {
 	void			*ste_intrhand;
 	struct ste_type		*ste_info;
 	device_t		ste_miibus;
+	device_t		ste_dev;
 	int			ste_unit;
 	int			ste_tx_thresh;
 	u_int8_t		ste_link;
 	int			ste_if_flags;
+	int			ste_tx_prev_idx;
 	struct ste_list_data	*ste_ldata;
 	struct ste_chain_data	ste_cdata;
 	struct callout_handle	ste_stat_ch;