Merge branch 'cxgb4-T6-update'

Hariprasad Shenai says:

====================
Update support for T6 adapters

This patch changes updates the various code changes related to
register, stats and hardware related changes for T6 family of
adapters.

This patch series has been created against net-next tree and includes
patches on cxgb4 and cxgb4vf driver.

We have included all the maintainers of respective drivers. Kindly review
the change and let us know in case of any review comments.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

@@ -301,6 +301,8 @@ struct devlog_params {
 /* Stores chip specific parameters */
 struct arch_specific_params {
 	u8 nchan;
+	u8 pm_stats_cnt;
+	u8 cng_ch_bits_log;		/* congestion channel map bits width */
 	u16 mps_rplc_size;
 	u16 vfcount;
 	u32 sge_fl_db;
@@ -1255,6 +1257,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver);
 int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op);
 int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 		  const u8 *fw_data, unsigned int size, int force);
+int t4_fl_pkt_align(struct adapter *adap);
 unsigned int t4_flash_cfg_addr(struct adapter *adapter);
 int t4_check_fw_version(struct adapter *adap);
 int t4_get_fw_version(struct adapter *adapter, u32 *vers);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c

@@ -757,8 +757,8 @@ static int pm_stats_show(struct seq_file *seq, void *v)
 	};
 
 	int i;
-	u32 tx_cnt[PM_NSTATS], rx_cnt[PM_NSTATS];
-	u64 tx_cyc[PM_NSTATS], rx_cyc[PM_NSTATS];
+	u32 tx_cnt[T6_PM_NSTATS], rx_cnt[T6_PM_NSTATS];
+	u64 tx_cyc[T6_PM_NSTATS], rx_cyc[T6_PM_NSTATS];
 	struct adapter *adap = seq->private;
 
 	t4_pmtx_get_stats(adap, tx_cnt, tx_cyc);
@@ -773,6 +773,32 @@ static int pm_stats_show(struct seq_file *seq, void *v)
 	for (i = 0; i < PM_NSTATS - 1; i++)
 		seq_printf(seq, "%-13s %10u  %20llu\n",
 			   rx_pm_stats[i], rx_cnt[i], rx_cyc[i]);
+
+	if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) {
+		/* In T5 the granularity of the total wait is too fine.
+		 * It is not useful as it reaches the max value too fast.
+		 * Hence display this Input FIFO wait for T6 onwards.
+		 */
+		seq_printf(seq, "%13s %10s  %20s\n",
+			   " ", "Total wait", "Total Occupancy");
+		seq_printf(seq, "Tx FIFO wait  %10u  %20llu\n",
+			   tx_cnt[i], tx_cyc[i]);
+		seq_printf(seq, "Rx FIFO wait  %10u  %20llu\n",
+			   rx_cnt[i], rx_cyc[i]);
+
+		/* Skip index 6 as there is nothing useful ihere */
+		i += 2;
+
+		/* At index 7, a new stat for read latency (count, total wait)
+		 * is added.
+		 */
+		seq_printf(seq, "%13s %10s  %20s\n",
+			   " ", "Reads", "Total wait");
+		seq_printf(seq, "Tx latency    %10u  %20llu\n",
+			   tx_cnt[i], tx_cyc[i]);
+		seq_printf(seq, "Rx latency    %10u  %20llu\n",
+			   rx_cnt[i], rx_cyc[i]);
+	}
 	return 0;
 }
 
@@ -1559,25 +1585,35 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 {
 	struct adapter *adap = seq->private;
 	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
-
 	if (v == SEQ_START_TOKEN) {
-		if (adap->params.arch.mps_rplc_size > 128)
+		if (chip_ver > CHELSIO_T5) {
 			seq_puts(seq, "Idx  Ethernet address     Mask     "
+				 "  VNI   Mask   IVLAN Vld "
+				 "DIP_Hit   Lookup  Port "
 				 "Vld Ports PF  VF                           "
 				 "Replication                                "
 				 "    P0 P1 P2 P3  ML\n");
-		else
-			seq_puts(seq, "Idx  Ethernet address     Mask     "
-				 "Vld Ports PF  VF              Replication"
-				 "	         P0 P1 P2 P3  ML\n");
+		} else {
+			if (adap->params.arch.mps_rplc_size > 128)
+				seq_puts(seq, "Idx  Ethernet address     Mask     "
+					 "Vld Ports PF  VF                           "
+					 "Replication                                "
+					 "    P0 P1 P2 P3  ML\n");
+			else
+				seq_puts(seq, "Idx  Ethernet address     Mask     "
+					 "Vld Ports PF  VF              Replication"
+					 "	         P0 P1 P2 P3  ML\n");
+		}
 	} else {
 		u64 mask;
 		u8 addr[ETH_ALEN];
-		bool replicate;
+		bool replicate, dip_hit = false, vlan_vld = false;
 		unsigned int idx = (uintptr_t)v - 2;
 		u64 tcamy, tcamx, val;
-		u32 cls_lo, cls_hi, ctl;
+		u32 cls_lo, cls_hi, ctl, data2, vnix = 0, vniy = 0;
 		u32 rplc[8] = {0};
+		u8 lookup_type = 0, port_num = 0;
+		u16 ivlan = 0;
 
 		if (chip_ver > CHELSIO_T5) {
 			/* CtlCmdType - 0: Read, 1: Write
@@ -1596,13 +1632,35 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 			val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A);
 			tcamy = DMACH_G(val) << 32;
 			tcamy |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A);
+			data2 = t4_read_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A);
+			lookup_type = DATALKPTYPE_G(data2);
+			/* 0 - Outer header, 1 - Inner header
+			 * [71:48] bit locations are overloaded for
+			 * outer vs. inner lookup types.
+			 */
+			if (lookup_type && (lookup_type != DATALKPTYPE_M)) {
+				/* Inner header VNI */
+				vniy = ((data2 & DATAVIDH2_F) << 23) |
+				       (DATAVIDH1_G(data2) << 16) | VIDL_G(val);
+				dip_hit = data2 & DATADIPHIT_F;
+			} else {
+				vlan_vld = data2 & DATAVIDH2_F;
+				ivlan = VIDL_G(val);
+			}
+			port_num = DATAPORTNUM_G(data2);
 
 			/* Read tcamx. Change the control param */
 			ctl |= CTLXYBITSEL_V(1);
 			t4_write_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A, ctl);
 			val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A);
 			tcamx = DMACH_G(val) << 32;
 			tcamx |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A);
+			data2 = t4_read_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A);
+			if (lookup_type && (lookup_type != DATALKPTYPE_M)) {
+				/* Inner header VNI mask */
+				vnix = ((data2 & DATAVIDH2_F) << 23) |
+				       (DATAVIDH1_G(data2) << 16) | VIDL_G(val);
+			}
 		} else {
 			tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx));
 			tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx));
@@ -1662,17 +1720,47 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 		}
 
 		tcamxy2valmask(tcamx, tcamy, addr, &mask);
-		if (chip_ver > CHELSIO_T5)
-			seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x "
-				   "%012llx%3c   %#x%4u%4d",
-				   idx, addr[0], addr[1], addr[2], addr[3],
-				   addr[4], addr[5], (unsigned long long)mask,
-				   (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N',
-				   PORTMAP_G(cls_hi),
-				   T6_PF_G(cls_lo),
-				   (cls_lo & T6_VF_VALID_F) ?
-				   T6_VF_G(cls_lo) : -1);
-		else
+		if (chip_ver > CHELSIO_T5) {
+			/* Inner header lookup */
+			if (lookup_type && (lookup_type != DATALKPTYPE_M)) {
+				seq_printf(seq,
+					   "%3u %02x:%02x:%02x:%02x:%02x:%02x "
+					   "%012llx %06x %06x    -    -   %3c"
+					   "      %3c  %4x   "
+					   "%3c   %#x%4u%4d", idx, addr[0],
+					   addr[1], addr[2], addr[3],
+					   addr[4], addr[5],
+					   (unsigned long long)mask,
+					   vniy, vnix, dip_hit ? 'Y' : 'N',
+					   lookup_type ? 'I' : 'O', port_num,
+					   (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N',
+					   PORTMAP_G(cls_hi),
+					   T6_PF_G(cls_lo),
+					   (cls_lo & T6_VF_VALID_F) ?
+					   T6_VF_G(cls_lo) : -1);
+			} else {
+				seq_printf(seq,
+					   "%3u %02x:%02x:%02x:%02x:%02x:%02x "
+					   "%012llx    -       -   ",
+					   idx, addr[0], addr[1], addr[2],
+					   addr[3], addr[4], addr[5],
+					   (unsigned long long)mask);
+
+				if (vlan_vld)
+					seq_printf(seq, "%4u   Y     ", ivlan);
+				else
+					seq_puts(seq, "  -    N     ");
+
+				seq_printf(seq,
+					   "-      %3c  %4x   %3c   %#x%4u%4d",
+					   lookup_type ? 'I' : 'O', port_num,
+					   (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N',
+					   PORTMAP_G(cls_hi),
+					   T6_PF_G(cls_lo),
+					   (cls_lo & T6_VF_VALID_F) ?
+					   T6_VF_G(cls_lo) : -1);
+			}
+		} else
 			seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x "
 				   "%012llx%3c   %#x%4u%4d",
 				   idx, addr[0], addr[1], addr[2], addr[3],

drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c

@@ -686,7 +686,7 @@ static int set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		lc->requested_fc |= PAUSE_TX;
 	if (netif_running(dev))
-		return t4_link_l1cfg(p->adapter, p->adapter->pf, p->tx_chan,
+		return t4_link_l1cfg(p->adapter, p->adapter->mbox, p->tx_chan,
 				     lc);
 	return 0;
 }

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -4855,8 +4855,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* configure SGE_STAT_CFG_A to read WC stats */
 	if (!is_t4(adapter->params.chip))
-		t4_write_reg(adapter, SGE_STAT_CFG_A,
-			     STATSOURCE_T5_V(7) | STATMODE_V(0));
+		t4_write_reg(adapter, SGE_STAT_CFG_A, STATSOURCE_T5_V(7) |
+			     (is_t5(adapter->params.chip) ? STATMODE_V(0) :
+			      T6_STATMODE_V(0)));
 
 	for_each_port(adapter, i) {
 		struct net_device *netdev;

drivers/net/ethernet/chelsio/cxgb4/sge.c

@@ -2670,8 +2670,9 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	 * simple (and hopefully less wrong).
 	 */
 	if (!is_t4(adap->params.chip) && cong >= 0) {
-		u32 param, val;
+		u32 param, val, ch_map = 0;
 		int i;
+		u16 cng_ch_bits_log = adap->params.arch.cng_ch_bits_log;
 
 		param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
 			 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_CONM_CTXT) |
@@ -2683,9 +2684,9 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 			    CONMCTXT_CNGTPMODE_V(CONMCTXT_CNGTPMODE_CHANNEL_X);
 			for (i = 0; i < 4; i++) {
 				if (cong & (1 << i))
-					val |=
-					     CONMCTXT_CNGCHMAP_V(1 << (i << 2));
+					ch_map |= 1 << (i << cng_ch_bits_log);
 			}
+			val |= CONMCTXT_CNGCHMAP_V(ch_map);
 		}
 		ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1,
 				    &param, &val);
@@ -3173,8 +3174,7 @@ static int t4_sge_init_soft(struct adapter *adap)
 int t4_sge_init(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
-	u32 sge_control, sge_control2, sge_conm_ctrl;
-	unsigned int ingpadboundary, ingpackboundary;
+	u32 sge_control, sge_conm_ctrl;
 	int ret, egress_threshold;
 
 	/*
@@ -3185,35 +3185,7 @@ int t4_sge_init(struct adapter *adap)
 	s->pktshift = PKTSHIFT_G(sge_control);
 	s->stat_len = (sge_control & EGRSTATUSPAGESIZE_F) ? 128 : 64;
 
-	/* T4 uses a single control field to specify both the PCIe Padding and
-	 * Packing Boundary.  T5 introduced the ability to specify these
-	 * separately.  The actual Ingress Packet Data alignment boundary
-	 * within Packed Buffer Mode is the maximum of these two
-	 * specifications.  (Note that it makes no real practical sense to
-	 * have the Pading Boudary be larger than the Packing Boundary but you
-	 * could set the chip up that way and, in fact, legacy T4 code would
-	 * end doing this because it would initialize the Padding Boundary and
-	 * leave the Packing Boundary initialized to 0 (16 bytes).)
-	 */
-	ingpadboundary = 1 << (INGPADBOUNDARY_G(sge_control) +
-			       INGPADBOUNDARY_SHIFT_X);
-	if (is_t4(adap->params.chip)) {
-		s->fl_align = ingpadboundary;
-	} else {
-		/* T5 has a different interpretation of one of the PCIe Packing
-		 * Boundary values.
-		 */
-		sge_control2 = t4_read_reg(adap, SGE_CONTROL2_A);
-		ingpackboundary = INGPACKBOUNDARY_G(sge_control2);
-		if (ingpackboundary == INGPACKBOUNDARY_16B_X)
-			ingpackboundary = 16;
-		else
-			ingpackboundary = 1 << (ingpackboundary +
-						INGPACKBOUNDARY_SHIFT_X);
-
-		s->fl_align = max(ingpadboundary, ingpackboundary);
-	}
-
+	s->fl_align = t4_fl_pkt_align(adap);
 	ret = t4_sge_init_soft(adap);
 	if (ret < 0)
 		return ret;
@@ -3231,10 +3203,21 @@ int t4_sge_init(struct adapter *adap)
 	 * buffers.
 	 */
 	sge_conm_ctrl = t4_read_reg(adap, SGE_CONM_CTRL_A);
-	if (is_t4(adap->params.chip))
+	switch (CHELSIO_CHIP_VERSION(adap->params.chip)) {
+	case CHELSIO_T4:
 		egress_threshold = EGRTHRESHOLD_G(sge_conm_ctrl);
-	else
+		break;
+	case CHELSIO_T5:
 		egress_threshold = EGRTHRESHOLDPACKING_G(sge_conm_ctrl);
+		break;
+	case CHELSIO_T6:
+		egress_threshold = T6_EGRTHRESHOLDPACKING_G(sge_conm_ctrl);
+		break;
+	default:
+		dev_err(adap->pdev_dev, "Unsupported Chip version %d\n",
+			CHELSIO_CHIP_VERSION(adap->params.chip));
+		return -EINVAL;
+	}
 	s->fl_starve_thres = 2*egress_threshold + 1;
 
 	t4_idma_monitor_init(adap, &s->idma_monitor);