Initialize various DDP parameters in the main cxgbe(4) driver:

- Setup multiple DDP page sizes.  When the driver attempts DDP it will
  try to combine physically contiguous pages into regions of these sizes.

- Set the indicate size such that the payload carried in the indicate can
  be copied in the header mbuf (and the 16K rx buffer can be recycled).

- Set DDP threshold to the max payload that the chip will coalesce and
  deliver to the driver (this is ~16K by default, which is also why the
  offload rx queue is backed by 16K buffers).  If the chip is able to
  coalesce up to the max it's allowed to, it's a good sign that the peer
  is transmitting in bulk without any TCP PSH.

MFC after:	2 weeks

3 files changed, 19 insertions, 12 deletions

diff --git a/sys/dev/cxgbe/adapter.h b/sys/dev/cxgbe/adapter.h
index 2cd5226..71f0fe9 100644
--- a/sys/dev/cxgbe/adapter.h
+++ b/sys/dev/cxgbe/adapter.h
@@ -135,6 +135,7 @@ enum {
 #else
 	FL_BUF_SIZES = 3,	/* cluster, jumbo9k, jumbo16k */
 #endif
+	OFLD_BUF_SIZE = MJUM16BYTES,	/* size of fl buffer for TOE rxq */
 
 	CTRL_EQ_QSIZE = 128,
 
@@ -143,6 +144,12 @@ enum {
 	TX_WR_FLITS = SGE_MAX_WR_LEN / 8
 };
 
+#ifdef T4_PKT_TIMESTAMP
+#define RX_COPY_THRESHOLD (MINCLSIZE - 8)
+#else
+#define RX_COPY_THRESHOLD MINCLSIZE
+#endif
+
 enum {
 	/* adapter intr_type */
 	INTR_INTX	= (1 << 0),
diff --git a/sys/dev/cxgbe/t4_main.c b/sys/dev/cxgbe/t4_main.c
index 6cee055..bac5e8b 100644
--- a/sys/dev/cxgbe/t4_main.c
+++ b/sys/dev/cxgbe/t4_main.c
@@ -515,12 +515,16 @@ t4_attach(device_t dev)
 		goto done; /* error message displayed already */
 
 	if (sc->flags & MASTER_PF) {
+		uint16_t indsz = min(RX_COPY_THRESHOLD - 1, M_INDICATESIZE);
 
 		/* final tweaks to some settings */
 
 		t4_load_mtus(sc, sc->params.mtus, sc->params.a_wnd,
 		    sc->params.b_wnd);
-		t4_write_reg(sc, A_ULP_RX_TDDP_PSZ, V_HPZ0(PAGE_SHIFT - 12));
+		/* 4K, 16K, 64K, 256K DDP "page sizes" */
+		t4_write_reg(sc, A_ULP_RX_TDDP_PSZ, V_HPZ0(0) | V_HPZ1(2) |
+		    V_HPZ2(4) | V_HPZ3(6));
+		t4_set_reg_field(sc, A_ULP_RX_CTL, F_TDDPTAGTCB, F_TDDPTAGTCB);
 		t4_set_reg_field(sc, A_TP_PARA_REG3, F_TUNNELCNGDROP0 |
 		    F_TUNNELCNGDROP1 | F_TUNNELCNGDROP2 | F_TUNNELCNGDROP3,
 		    F_TUNNELCNGDROP0 | F_TUNNELCNGDROP1 | F_TUNNELCNGDROP2 |
@@ -528,7 +532,7 @@ t4_attach(device_t dev)
 		t4_set_reg_field(sc, A_TP_PARA_REG5,
 		    V_INDICATESIZE(M_INDICATESIZE) |
 		    F_REARMDDPOFFSET | F_RESETDDPOFFSET,
-		    V_INDICATESIZE(M_INDICATESIZE) |
+		    V_INDICATESIZE(indsz) |
 		    F_REARMDDPOFFSET | F_RESETDDPOFFSET);
 	} else {
 		/*
@@ -3228,10 +3232,13 @@ t4_sysctls(struct adapter *sc)
 		sc->tt.ddp = 0;
 		SYSCTL_ADD_INT(ctx, children, OID_AUTO, "ddp", CTLFLAG_RW,
 		    &sc->tt.ddp, 0, "DDP allowed");
-		sc->tt.indsz = M_INDICATESIZE;
+
+		sc->tt.indsz = G_INDICATESIZE(t4_read_reg(sc, A_TP_PARA_REG5));
 		SYSCTL_ADD_INT(ctx, children, OID_AUTO, "indsz", CTLFLAG_RW,
 		    &sc->tt.indsz, 0, "DDP max indicate size allowed");
-		sc->tt.ddp_thres = 3*4096;
+
+		sc->tt.ddp_thres =
+		    G_RXCOALESCESIZE(t4_read_reg(sc, A_TP_PARA_REG2));
 		SYSCTL_ADD_INT(ctx, children, OID_AUTO, "ddp_thres", CTLFLAG_RW,
 		    &sc->tt.ddp_thres, 0, "DDP threshold");
 	}
diff --git a/sys/dev/cxgbe/t4_sge.c b/sys/dev/cxgbe/t4_sge.c
index 8e0daac..811819f 100644
--- a/sys/dev/cxgbe/t4_sge.c
+++ b/sys/dev/cxgbe/t4_sge.c
@@ -627,7 +627,7 @@ t4_setup_port_queues(struct port_info *pi)
 
 		snprintf(name, sizeof(name), "%s ofld_rxq%d-fl",
 		    device_get_nameunit(pi->dev), i);
-		init_fl(&ofld_rxq->fl, pi->qsize_rxq / 8, MJUM16BYTES, name);
+		init_fl(&ofld_rxq->fl, pi->qsize_rxq / 8, OFLD_BUF_SIZE, name);
 
 		if (sc->flags & INTR_DIRECT ||
 		    (sc->intr_count > 1 && pi->nofldrxq > pi->nrxq)) {
@@ -1022,13 +1022,6 @@ service_iq(struct sge_iq *iq, int budget)
 	return (0);
 }
 
-
-#ifdef T4_PKT_TIMESTAMP
-#define RX_COPY_THRESHOLD (MINCLSIZE - 8)
-#else
-#define RX_COPY_THRESHOLD MINCLSIZE
-#endif
-
 static struct mbuf *
 get_fl_payload(struct adapter *sc, struct sge_fl *fl, uint32_t len_newbuf,
     int *fl_bufs_used)