- Tx side bus_dmamap_load_mbuf_sg(9) support. This reduces bookkeeping

  requiried to keep consistent softc state before/after callback function
  invocation and supposed to be sligntly faster than previous one as it
  wouldn't incur callback overhead. With this change callback function
  was gone.
- Decrease TI_MAXTXSEGS to 32 from 128. It seems that most mbuf chain
  length is less than 32 and it would be re-packed with m_defrag(9) if
  its chain length is larger than TI_MAXTXSEGS. This would protect ti(4)
  against possible kernel stack overflow when txsegs[] is put on stack.
  Alternatively, we can embed the txsegs[] into softc. However, that
  would waste memory and make Tx/Rx speration hard when we want to
  sperate Tx/Rx handlers to optimize locking.
- Fix dma map tracking used in Tx path. Previously it used the dma map
  of the last mbuf chain in ti_txeof() which was incorrect as ti(4)
  used dma map of the first mbuf chain when it loads a mbuf chain with
  bus_dmamap_load_mbuf(9). Correct the bug by introducing queues that
  keep track of active/inactive dma maps/mbuf chain.
- Use ti_txcnt to check whether driver need to set watchdog timer instead
  of blidnly clearing the timer in ti_txeof().
- Remove the 3rd arg. of ti_encap(). Since ti(4) now caches the last
  descriptor index(ti_tx_saved_prodidx) used in Tx there is no need to
  pass it as a fuction arg.
- Change data type of producer/consumer index to int from u_int16_t in
  order to remove implicit type conversions in Tx/Rx handlers.
- Check interface queue before getting a mbuf chain to reduce locking
  overhead.
- Check number of available Tx descriptores to be 16 or higher in
  ti_start(). This wouldn't protect Tx descriptor shortage but it would
  reduce number of bus_dmamap_unload(9) calls in ti_encap() when we are
  about to running out of Tx descriptors.
- Command NIC to send packets ony when the driver really has packets
  enqueued. Previously it always set TI_MB_SENDPROD_IDX which would
  command NIC to DMA Tx descriptors into NIC local memory regardless
  of Tx descriptor changes.

Reviewed by:	scottl

1 files changed, 20 insertions, 11 deletions

diff --git a/sys/dev/ti/if_tireg.h b/sys/dev/ti/if_tireg.h
index 97f7077..5f0bda9 100644
--- a/sys/dev/ti/if_tireg.h
+++ b/sys/dev/ti/if_tireg.h
@@ -399,7 +399,7 @@
 #define TI_MINI_RX_RING_CNT	1024
 #define TI_RETURN_RING_CNT	2048
 
-#define TI_MAXTXSEGS		128
+#define TI_MAXTXSEGS		32
 
 /*
  * Possible TX ring sizes.
@@ -904,6 +904,14 @@ struct ti_event_desc {
 #define TI_RESID (TI_JPAGESZ - (TI_JLEN * TI_JSLOTS) % TI_JPAGESZ)
 #define TI_JMEM ((TI_JLEN * TI_JSLOTS) + TI_RESID)
 
+struct ti_txdesc {
+	struct mbuf	*tx_m;
+	bus_dmamap_t	tx_dmamap;
+	STAILQ_ENTRY(ti_txdesc) tx_q;
+};
+
+STAILQ_HEAD(ti_txdq, ti_txdesc);
+
 /*
  * Ring structures. Most of these reside in host memory and we tell
  * the NIC where they are via the ring control blocks. The exceptions
@@ -942,8 +950,9 @@ struct ti_ring_data {
  * not the other way around.
  */
 struct ti_chain_data {
-	struct mbuf		*ti_tx_chain[TI_TX_RING_CNT];
-	bus_dmamap_t		ti_tx_maps[TI_TX_RING_CNT];
+	struct ti_txdesc	ti_txdesc[TI_TX_RING_CNT];
+	struct ti_txdq		ti_txfreeq;
+	struct ti_txdq		ti_txbusyq;
 	struct mbuf		*ti_rx_std_chain[TI_STD_RX_RING_CNT];
 	bus_dmamap_t		ti_rx_std_maps[TI_STD_RX_RING_CNT];
 	struct mbuf		*ti_rx_jumbo_chain[TI_JUMBO_RX_RING_CNT];
@@ -1009,14 +1018,14 @@ struct ti_softc {
 #define ti_ev_prodidx		ti_rdata->ti_ev_prodidx_r
 #define ti_return_prodidx	ti_rdata->ti_return_prodidx_r
 #define ti_tx_considx		ti_rdata->ti_tx_considx_r
-	u_int16_t		ti_tx_saved_prodidx;
-	u_int16_t		ti_tx_saved_considx;
-	u_int16_t		ti_rx_saved_considx;
-	u_int16_t		ti_ev_saved_considx;
-	u_int16_t		ti_cmd_saved_prodidx;
-	u_int16_t		ti_std;		/* current std ring head */
-	u_int16_t		ti_mini;	/* current mini ring head */
-	u_int16_t		ti_jumbo;	/* current jumo ring head */
+	int			ti_tx_saved_prodidx;
+	int			ti_tx_saved_considx;
+	int			ti_rx_saved_considx;
+	int			ti_ev_saved_considx;
+	int			ti_cmd_saved_prodidx;
+	int			ti_std;		/* current std ring head */
+	int			ti_mini;	/* current mini ring head */
+	int			ti_jumbo;	/* current jumo ring head */
 	SLIST_HEAD(__ti_mchead, ti_mc_entry)	ti_mc_listhead;
 	SLIST_HEAD(__ti_jfreehead, ti_jpool_entry)	ti_jfree_listhead;
 	SLIST_HEAD(__ti_jinusehead, ti_jpool_entry)	ti_jinuse_listhead;