MFC: r295906

Fix and clean up usage of DMA and TSO segments:
- At Intel it is believed that most of their products support "only"
  40 DMA segments so lower {EM,IGB}_MAX_SCATTER accordingly. Actually,
  40 is more than plenty to handle full size TSO packets so it doesn't
  make sense to further distinguish between MAC variants that really
  can do 64 DMA segments. Moreover, capping at 40 DMA segments limits
  the stack usage of {em,igb}_xmit() that - given the rare use of more
  than these - previously hardly was justifiable, while still being
  sufficient to avoid the problems seen with em(4) and EM_MAX_SCATTER
  set to 32.
- In igb(4), pass the actually supported TSO parameters up the stack.
  Previously, the defaults set in if_attach_internal() were applied,
  i. e. a maximum of 35 TSO segments, which made supporting more than
  these in the driver pointless. However, this might explain why no
  problems were seen with IGB_MAX_SCATTER at 64.
- In em(4), take the 5 m_pullup(9) invocations performed by em_xmit()
  in the TSO case into account when reporting TSO parameters upwards.
  In the worst case, each of these calls will add another mbuf and,
  thus, the requirement for an additional DMA segment. So for best
  performance, it doesn't make sense to advertize a maximum of TSO
  segments that typically will require defragmentation in em_xmit().
  Again, this leaves enough room to handle full size TSO packets.
- Drop TSO macros from if_lem.h given that corresponding MACS don't
  support TSO in the first place.

Reviewed by:	erj, sbruno, jeffrey.e.pieper_intel.com
Approved by:	re (gjb)

sys/dev/e1000/if_em.c

@@ -3237,9 +3237,11 @@ em_setup_interface(device_t dev, struct adapter *adapter)
 	ifp->if_softc = adapter;
 	ifp->if_flags = IFF_BROADCAST | IFF_SIMPLEX | IFF_MULTICAST;
 	ifp->if_ioctl = em_ioctl;
+
 	/* TSO parameters */
 	ifp->if_hw_tsomax = IP_MAXPACKET;
-	ifp->if_hw_tsomaxsegcount = EM_MAX_SCATTER;
+	/* Take m_pullup(9)'s in em_xmit() w/ TSO into acount. */
+	ifp->if_hw_tsomaxsegcount = EM_MAX_SCATTER - 5;
 	ifp->if_hw_tsomaxsegsize = EM_TSO_SEG_SIZE;
 
 #ifdef EM_MULTIQUEUE

sys/dev/e1000/if_em.h

@@ -269,7 +269,7 @@
 #define HW_DEBUGOUT1(S, A)          if (DEBUG_HW) printf(S "\n", A)
 #define HW_DEBUGOUT2(S, A, B)       if (DEBUG_HW) printf(S "\n", A, B)
 
-#define EM_MAX_SCATTER		64
+#define EM_MAX_SCATTER		40
 #define EM_VFTA_SIZE		128
 #define EM_TSO_SIZE		(65535 + sizeof(struct ether_vlan_header))
 #define EM_TSO_SEG_SIZE		4096	/* Max dma segment size */

sys/dev/e1000/if_igb.c

@@ -3043,6 +3043,12 @@ igb_setup_interface(device_t dev, struct adapter *adapter)
 	ifp->if_softc = adapter;
 	ifp->if_flags = IFF_BROADCAST | IFF_SIMPLEX | IFF_MULTICAST;
 	ifp->if_ioctl = igb_ioctl;
+
+	/* TSO parameters */
+	ifp->if_hw_tsomax = IP_MAXPACKET;
+	ifp->if_hw_tsomaxsegcount = IGB_MAX_SCATTER;
+	ifp->if_hw_tsomaxsegsize = IGB_TSO_SEG_SIZE;
+
 #ifndef IGB_LEGACY_TX
 	ifp->if_transmit = igb_mq_start;
 	ifp->if_qflush = igb_qflush;

sys/dev/e1000/if_igb.h

@@ -278,7 +278,7 @@
 #define HW_DEBUGOUT1(S, A)          if (DEBUG_HW) printf(S "\n", A)
 #define HW_DEBUGOUT2(S, A, B)       if (DEBUG_HW) printf(S "\n", A, B)
 
-#define IGB_MAX_SCATTER		64
+#define IGB_MAX_SCATTER		40
 #define IGB_VFTA_SIZE		128
 #define IGB_BR_SIZE		4096	/* ring buf size */
 #define IGB_TSO_SIZE		(65535 + sizeof(struct ether_vlan_header))

sys/dev/e1000/if_lem.h

@@ -236,10 +236,8 @@
 #define HW_DEBUGOUT1(S, A)          if (DEBUG_HW) printf(S "\n", A)
 #define HW_DEBUGOUT2(S, A, B)       if (DEBUG_HW) printf(S "\n", A, B)
 
-#define EM_MAX_SCATTER		64
+#define EM_MAX_SCATTER		40
 #define EM_VFTA_SIZE		128
-#define EM_TSO_SIZE		(65535 + sizeof(struct ether_vlan_header))
-#define EM_TSO_SEG_SIZE		4096	/* Max dma segment size */
 #define EM_MSIX_MASK		0x01F00000 /* For 82574 use */
 #define ETH_ZLEN		60
 #define ETH_ADDR_LEN		6