Overhaul re(4).

o Increased number of Rx/Tx descriptors to 256 for 8169 GigEs
  because it's hard to push the hardware to the limit with default
  64 descriptors.
  TSO requires large number of Tx descriptors to pass a full sized
  TCP segment(65535 bytes IP packet) to hardware. Previously it
  consumed 32 Tx descriptors, assuming MCLBYTES DMA segment size,
  to send the TCP segment which means re(4) couldn't queue more
  than two full sized IP packets.
  For 8139C+ it still uses 64 Rx/Tx descriptors due to its hardware
  limitations. With this changes there are (very) small waste of
  memory for 8139C+ users but I don't think it would affect 8139C+
  users for most cases.
o Various bus_dma(9) fixes.
   - The hardware supports DAC so allow 64bit DMA operations.
   - Removed BUS_DMA_ALLOC_NOW flag.
   - Increased DMA segment size to 4096 from MCLBYTES because TSO
     consumes too many descriptors with MCLBYTES DMA segment size.
   - Tx/Rx side bus_dmamap_load_mbuf_sg(9) support. With these
     changes the code is more readable than previous one and got a
     (slightly) better performance as it doesn't need to pass/
     decode arguments to/from callback function.
   - Removed unnecessary callback function re_dmamap_desc() and
     nuked rl_dmaload_arg structure which was used in the callback.
   - Additional protection for DMA map load failure. In case of
     failure reuse current map instead of returning a bogus DMA
     map.
  -  Deferred DMA map unloading/sync operation for maximum
     performance until we really need to load new DMA map. If we
     happen to reuse current map(e.g. input error) there is no need
     to sync/unload/load again.
  -  The number of allowable Tx DMA segments for a mbuf chains are
     now 32 instead of magic nseg value. If the number of available
     Tx descriptors are short enough to send highly fragmented mbuf
     chains an optimized re_defrag() is called to collapse mbuf
     chains which is supposed to be much faster than m_defrag(9).
     re_defrag() was borrowed from ath(4).
   - Separated Rx/Tx DMA tag from a common DMA tag such that Rx DMA
     tag correctly uses DMA maps that were created with DMA alignment
     restriction(8bytes alignments). Tx DMA tag does not have such
     alignment limitation.
   - Added additional sanity checks for DMA ring map load failure.
   - Added additional spare Rx DMA map for graceful handling of Rx
     DMA map load failure.
   - Fixed misused bus_dmamap_sync(9) and added missing
     bus_dmamap_sync(9) in re_encap()/re_txeof()/re_rxeof().
o Enabled TSO again as re(4) have reasonable number of Tx
  descriptors.
o Don't touch DMA address of a Tx descriptor in re_txeof(). It's
  not needed.
o Fix incorrect update of if_ierrors counter. For Rx buffer
  shortage it should update if_qdrops as the buffer is reused.
o Added checks for unsupported H/W revisions and return ENXIO for
  these hardwares. This is required to remove resource allocation
  code in re_probe as other drivers do in device probe routine.
o Modified descriptor index manipulation macros as it's now possible
  to have different number of descriptors for Rx/Tx.
o In re_start, to save a lock operation, use IFQ_DRV_IS_EMPTY before
  trying to invoke IFQ_DRV_DEQUEUE. Also don't blindly call re_encap
  since we already know the number of available Tx descriptors in
  advance.
o Removed RL_TX_DESC_THLD which was used to reserve RL_TX_DESC_THLD
  descriptors in Tx path. There is no such a limitation mentioned in
  8139C+/8169/8110/8168/8101/8111 datasheet and it seems to work ok
  without reserving RL_TX_DESC_THLD descriptors.
o Fix a comment for RL_GTXSTART. The register is 8bits register.
o Added comments for 8169/8139C+ hardware restrictions on descriptors.
o Removed forward declaration for "struct rl_softc", it's not needed.
o Added a new structure rl_txdesc for Tx descriptor managements and
  a structure rl_rxdesc for Rx descriptor managements.
o Removed unused member variable rl_intlock in driver softc. There are
  still several unused member variables which are supposed to be used
  to access hardware statistics counters. But it seems that accessing
  hardware counters were not implemented yet.

1 files changed, 37 insertions, 23 deletions

diff --git a/sys/pci/if_rlreg.h b/sys/pci/if_rlreg.h
index fbfb65b..5b63290 100644
--- a/sys/pci/if_rlreg.h
+++ b/sys/pci/if_rlreg.h
@@ -128,7 +128,7 @@
 #define RL_TBI_LPAR		0x006A
 #define RL_GMEDIASTAT		0x006C	/* 8 bits */
 #define RL_MAXRXPKTLEN		0x00DA	/* 16 bits, chip multiplies by 8 */
-#define RL_GTXSTART		0x0038	/* 16 bits */
+#define RL_GTXSTART		0x0038	/* 8 bits */
 
 /*
  * TX config register bits
@@ -636,24 +636,35 @@ struct rl_stats {
 /*
  * Rx/Tx descriptor parameters (8139C+ and 8169 only)
  *
- * Tx/Rx count must be equal.  Shared code like re_dma_map_desc assumes this.
- * Buffers must be a multiple of 8 bytes.  Currently limit to 64 descriptors
- * due to the 8139C+.  We need to put the number of descriptors in the ring
- * structure and use that value instead.
+ * 8139C+
+ *  Number of descriptors supported : up to 64
+ *  Descriptor alignment : 256 bytes
+ *  Tx buffer : At least 4 bytes in length.
+ *  Rx buffer : At least 8 bytes in length and 8 bytes alignment required.
+ *  
+ * 8169
+ *  Number of descriptors supported : up to 1024
+ *  Descriptor alignment : 256 bytes
+ *  Tx buffer : At least 4 bytes in length.
+ *  Rx buffer : At least 8 bytes in length and 8 bytes alignment required.
  */
 #ifndef	__NO_STRICT_ALIGNMENT
 #define RE_FIXUP_RX	1
 #endif
 
-#define RL_TX_DESC_CNT		64
-#define RL_TX_DESC_THLD		4
-#define RL_RX_DESC_CNT		RL_TX_DESC_CNT
+#define RL_8169_TX_DESC_CNT	256
+#define RL_8169_RX_DESC_CNT	256
+#define RL_8139_TX_DESC_CNT	64
+#define RL_8139_RX_DESC_CNT	64
+#define RL_TX_DESC_CNT		RL_8169_TX_DESC_CNT
+#define RL_RX_DESC_CNT		RL_8169_RX_DESC_CNT
+#define	RL_NTXSEGS		32
 
-#define RL_RX_LIST_SZ		(RL_RX_DESC_CNT * sizeof(struct rl_desc))
-#define RL_TX_LIST_SZ		(RL_TX_DESC_CNT * sizeof(struct rl_desc))
 #define RL_RING_ALIGN		256
 #define RL_IFQ_MAXLEN		512
-#define RL_DESC_INC(x)		(x = (x + 1) % RL_TX_DESC_CNT)
+#define RL_TX_DESC_NXT(sc,x)	((x + 1) & ((sc)->rl_ldata.rl_tx_desc_cnt - 1))
+#define RL_TX_DESC_PRV(sc,x)	((x - 1) & ((sc)->rl_ldata.rl_tx_desc_cnt - 1))
+#define RL_RX_DESC_NXT(sc,x)	((x + 1) & ((sc)->rl_ldata.rl_rx_desc_cnt - 1))
 #define RL_OWN(x)		(le32toh((x)->rl_cmdstat) & RL_RDESC_STAT_OWN)
 #define RL_RXBYTES(x)		(le32toh((x)->rl_cmdstat) & sc->rl_rxlenmask)
 #define RL_PKTSZ(x)		((x)/* >> 3*/)
@@ -674,25 +685,29 @@ struct rl_stats {
 #define RL_JUMBO_FRAMELEN	7440
 #define RL_JUMBO_MTU		(RL_JUMBO_FRAMELEN-ETHER_HDR_LEN-ETHER_CRC_LEN)
 
-struct rl_softc;
+struct rl_txdesc {
+	struct mbuf		*tx_m;
+	bus_dmamap_t		tx_dmamap;
+};
 
-struct rl_dmaload_arg {
-	int			rl_idx;
-	int			rl_maxsegs;
-	uint32_t		rl_flags;
-	struct rl_desc		*rl_ring;
+struct rl_rxdesc {
+	struct mbuf		*rx_m;
+	bus_dmamap_t		rx_dmamap;
+	bus_size_t		rx_size;
 };
 
 struct rl_list_data {
-	struct mbuf		*rl_tx_mbuf[RL_TX_DESC_CNT];
-	struct mbuf		*rl_rx_mbuf[RL_RX_DESC_CNT];
+	struct rl_txdesc	rl_tx_desc[RL_TX_DESC_CNT];
+	struct rl_rxdesc	rl_rx_desc[RL_RX_DESC_CNT];
+	int			rl_tx_desc_cnt;
+	int			rl_rx_desc_cnt;
 	int			rl_tx_prodidx;
 	int			rl_rx_prodidx;
 	int			rl_tx_considx;
 	int			rl_tx_free;
-	bus_dmamap_t		rl_tx_dmamap[RL_TX_DESC_CNT];
-	bus_dmamap_t		rl_rx_dmamap[RL_RX_DESC_CNT];
-	bus_dma_tag_t		rl_mtag;	/* mbuf mapping tag */
+	bus_dma_tag_t		rl_tx_mtag;	/* mbuf TX mapping tag */
+	bus_dma_tag_t		rl_rx_mtag;	/* mbuf RX mapping tag */
+	bus_dmamap_t		rl_rx_sparemap;
 	bus_dma_tag_t		rl_stag;	/* stats mapping tag */
 	bus_dmamap_t		rl_smap;	/* stats map */
 	struct rl_stats		*rl_stats;
@@ -742,7 +757,6 @@ struct rl_softc {
 	struct task		rl_txtask;
 	struct task		rl_inttask;
 
-	struct mtx		rl_intlock;
 	int			rl_txstart;
 	int			rl_link;
 	int			rl_msi;