Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 761 insertions, 14 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index c3c7db4..0a87a32 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -151,6 +151,45 @@ static int cim_la_show_3in1(struct seq_file *seq, void *v, int idx)
 	return 0;
 }
 
+static int cim_la_show_t6(struct seq_file *seq, void *v, int idx)
+{
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Status   Inst    Data      PC     LS0Stat  "
+			 "LS0Addr  LS0Data  LS1Stat  LS1Addr  LS1Data\n");
+	} else {
+		const u32 *p = v;
+
+		seq_printf(seq, "  %02x   %04x%04x %04x%04x %04x%04x %08x %08x %08x %08x %08x %08x\n",
+			   (p[9] >> 16) & 0xff,       /* Status */
+			   p[9] & 0xffff, p[8] >> 16, /* Inst */
+			   p[8] & 0xffff, p[7] >> 16, /* Data */
+			   p[7] & 0xffff, p[6] >> 16, /* PC */
+			   p[2], p[1], p[0],      /* LS0 Stat, Addr and Data */
+			   p[5], p[4], p[3]);     /* LS1 Stat, Addr and Data */
+	}
+	return 0;
+}
+
+static int cim_la_show_pc_t6(struct seq_file *seq, void *v, int idx)
+{
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Status   Inst    Data      PC\n");
+	} else {
+		const u32 *p = v;
+
+		seq_printf(seq, "  %02x   %08x %08x %08x\n",
+			   p[3] & 0xff, p[2], p[1], p[0]);
+		seq_printf(seq, "  %02x   %02x%06x %02x%06x %02x%06x\n",
+			   (p[6] >> 8) & 0xff, p[6] & 0xff, p[5] >> 8,
+			   p[5] & 0xff, p[4] >> 8, p[4] & 0xff, p[3] >> 8);
+		seq_printf(seq, "  %02x   %04x%04x %04x%04x %04x%04x\n",
+			   (p[9] >> 16) & 0xff, p[9] & 0xffff, p[8] >> 16,
+			   p[8] & 0xffff, p[7] >> 16, p[7] & 0xffff,
+			   p[6] >> 16);
+	}
+	return 0;
+}
+
 static int cim_la_open(struct inode *inode, struct file *file)
 {
 	int ret;
@@ -162,9 +201,18 @@ static int cim_la_open(struct inode *inode, struct file *file)
 	if (ret)
 		return ret;
 
-	p = seq_open_tab(file, adap->params.cim_la_size / 8, 8 * sizeof(u32), 1,
-			 cfg & UPDBGLACAPTPCONLY_F ?
-			 cim_la_show_3in1 : cim_la_show);
+	if (is_t6(adap->params.chip)) {
+		/* +1 to account for integer division of CIMLA_SIZE/10 */
+		p = seq_open_tab(file, (adap->params.cim_la_size / 10) + 1,
+				 10 * sizeof(u32), 1,
+				 cfg & UPDBGLACAPTPCONLY_F ?
+					cim_la_show_pc_t6 : cim_la_show_t6);
+	} else {
+		p = seq_open_tab(file, adap->params.cim_la_size / 8,
+				 8 * sizeof(u32), 1,
+				 cfg & UPDBGLACAPTPCONLY_F ? cim_la_show_3in1 :
+							     cim_la_show);
+	}
 	if (!p)
 		return -ENOMEM;
 
@@ -298,11 +346,11 @@ static int cim_qcfg_show(struct seq_file *seq, void *v)
 		if (is_t4(adap->params.chip)) {
 			i = t4_cim_read(adap, UP_OBQ_0_REALADDR_A,
 					ARRAY_SIZE(obq_wr_t4), obq_wr_t4);
-				wr = obq_wr_t4;
+			wr = obq_wr_t4;
 		} else {
 			i = t4_cim_read(adap, UP_OBQ_0_SHADOW_REALADDR_A,
 					ARRAY_SIZE(obq_wr_t5), obq_wr_t5);
-				wr = obq_wr_t5;
+			wr = obq_wr_t5;
 		}
 	}
 	if (i)
@@ -1153,6 +1201,299 @@ static const struct file_operations mbox_debugfs_fops = {
 	.write   = mbox_write
 };
 
+static int mps_trc_show(struct seq_file *seq, void *v)
+{
+	int enabled, i;
+	struct trace_params tp;
+	unsigned int trcidx = (uintptr_t)seq->private & 3;
+	struct adapter *adap = seq->private - trcidx;
+
+	t4_get_trace_filter(adap, &tp, trcidx, &enabled);
+	if (!enabled) {
+		seq_puts(seq, "tracer is disabled\n");
+		return 0;
+	}
+
+	if (tp.skip_ofst * 8 >= TRACE_LEN) {
+		dev_err(adap->pdev_dev, "illegal trace pattern skip offset\n");
+		return -EINVAL;
+	}
+	if (tp.port < 8) {
+		i = adap->chan_map[tp.port & 3];
+		if (i >= MAX_NPORTS) {
+			dev_err(adap->pdev_dev, "tracer %u is assigned "
+				"to non-existing port\n", trcidx);
+			return -EINVAL;
+		}
+		seq_printf(seq, "tracer is capturing %s %s, ",
+			   adap->port[i]->name, tp.port < 4 ? "Rx" : "Tx");
+	} else
+		seq_printf(seq, "tracer is capturing loopback %d, ",
+			   tp.port - 8);
+	seq_printf(seq, "snap length: %u, min length: %u\n", tp.snap_len,
+		   tp.min_len);
+	seq_printf(seq, "packets captured %smatch filter\n",
+		   tp.invert ? "do not " : "");
+
+	if (tp.skip_ofst) {
+		seq_puts(seq, "filter pattern: ");
+		for (i = 0; i < tp.skip_ofst * 2; i += 2)
+			seq_printf(seq, "%08x%08x", tp.data[i], tp.data[i + 1]);
+		seq_putc(seq, '/');
+		for (i = 0; i < tp.skip_ofst * 2; i += 2)
+			seq_printf(seq, "%08x%08x", tp.mask[i], tp.mask[i + 1]);
+		seq_puts(seq, "@0\n");
+	}
+
+	seq_puts(seq, "filter pattern: ");
+	for (i = tp.skip_ofst * 2; i < TRACE_LEN / 4; i += 2)
+		seq_printf(seq, "%08x%08x", tp.data[i], tp.data[i + 1]);
+	seq_putc(seq, '/');
+	for (i = tp.skip_ofst * 2; i < TRACE_LEN / 4; i += 2)
+		seq_printf(seq, "%08x%08x", tp.mask[i], tp.mask[i + 1]);
+	seq_printf(seq, "@%u\n", (tp.skip_ofst + tp.skip_len) * 8);
+	return 0;
+}
+
+static int mps_trc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mps_trc_show, inode->i_private);
+}
+
+static unsigned int xdigit2int(unsigned char c)
+{
+	return isdigit(c) ? c - '0' : tolower(c) - 'a' + 10;
+}
+
+#define TRC_PORT_NONE 0xff
+#define TRC_RSS_ENABLE 0x33
+#define TRC_RSS_DISABLE 0x13
+
+/* Set an MPS trace filter.  Syntax is:
+ *
+ * disable
+ *
+ * to disable tracing, or
+ *
+ * interface qid=<qid no> [snaplen=<val>] [minlen=<val>] [not] [<pattern>]...
+ *
+ * where interface is one of rxN, txN, or loopbackN, N = 0..3, qid can be one
+ * of the NIC's response qid obtained from sge_qinfo and pattern has the form
+ *
+ * <pattern data>[/<pattern mask>][@<anchor>]
+ *
+ * Up to 2 filter patterns can be specified.  If 2 are supplied the first one
+ * must be anchored at 0.  An omited mask is taken as a mask of 1s, an omitted
+ * anchor is taken as 0.
+ */
+static ssize_t mps_trc_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *pos)
+{
+	int i, enable, ret;
+	u32 *data, *mask;
+	struct trace_params tp;
+	const struct inode *ino;
+	unsigned int trcidx;
+	char *s, *p, *word, *end;
+	struct adapter *adap;
+	u32 j;
+
+	ino = file_inode(file);
+	trcidx = (uintptr_t)ino->i_private & 3;
+	adap = ino->i_private - trcidx;
+
+	/* Don't accept input more than 1K, can't be anything valid except lots
+	 * of whitespace.  Well, use less.
+	 */
+	if (count > 1024)
+		return -EFBIG;
+	p = s = kzalloc(count + 1, GFP_USER);
+	if (!s)
+		return -ENOMEM;
+	if (copy_from_user(s, buf, count)) {
+		count = -EFAULT;
+		goto out;
+	}
+
+	if (s[count - 1] == '\n')
+		s[count - 1] = '\0';
+
+	enable = strcmp("disable", s) != 0;
+	if (!enable)
+		goto apply;
+
+	/* enable or disable trace multi rss filter */
+	if (adap->trace_rss)
+		t4_write_reg(adap, MPS_TRC_CFG_A, TRC_RSS_ENABLE);
+	else
+		t4_write_reg(adap, MPS_TRC_CFG_A, TRC_RSS_DISABLE);
+
+	memset(&tp, 0, sizeof(tp));
+	tp.port = TRC_PORT_NONE;
+	i = 0;	/* counts pattern nibbles */
+
+	while (p) {
+		while (isspace(*p))
+			p++;
+		word = strsep(&p, " ");
+		if (!*word)
+			break;
+
+		if (!strncmp(word, "qid=", 4)) {
+			end = (char *)word + 4;
+			ret = kstrtouint(end, 10, &j);
+			if (ret)
+				goto out;
+			if (!adap->trace_rss) {
+				t4_write_reg(adap, MPS_T5_TRC_RSS_CONTROL_A, j);
+				continue;
+			}
+
+			switch (trcidx) {
+			case 0:
+				t4_write_reg(adap, MPS_TRC_RSS_CONTROL_A, j);
+				break;
+			case 1:
+				t4_write_reg(adap,
+					     MPS_TRC_FILTER1_RSS_CONTROL_A, j);
+				break;
+			case 2:
+				t4_write_reg(adap,
+					     MPS_TRC_FILTER2_RSS_CONTROL_A, j);
+				break;
+			case 3:
+				t4_write_reg(adap,
+					     MPS_TRC_FILTER3_RSS_CONTROL_A, j);
+				break;
+			}
+			continue;
+		}
+		if (!strncmp(word, "snaplen=", 8)) {
+			end = (char *)word + 8;
+			ret = kstrtouint(end, 10, &j);
+			if (ret || j > 9600) {
+inval:				count = -EINVAL;
+				goto out;
+			}
+			tp.snap_len = j;
+			continue;
+		}
+		if (!strncmp(word, "minlen=", 7)) {
+			end = (char *)word + 7;
+			ret = kstrtouint(end, 10, &j);
+			if (ret || j > TFMINPKTSIZE_M)
+				goto inval;
+			tp.min_len = j;
+			continue;
+		}
+		if (!strcmp(word, "not")) {
+			tp.invert = !tp.invert;
+			continue;
+		}
+		if (!strncmp(word, "loopback", 8) && tp.port == TRC_PORT_NONE) {
+			if (word[8] < '0' || word[8] > '3' || word[9])
+				goto inval;
+			tp.port = word[8] - '0' + 8;
+			continue;
+		}
+		if (!strncmp(word, "tx", 2) && tp.port == TRC_PORT_NONE) {
+			if (word[2] < '0' || word[2] > '3' || word[3])
+				goto inval;
+			tp.port = word[2] - '0' + 4;
+			if (adap->chan_map[tp.port & 3] >= MAX_NPORTS)
+				goto inval;
+			continue;
+		}
+		if (!strncmp(word, "rx", 2) && tp.port == TRC_PORT_NONE) {
+			if (word[2] < '0' || word[2] > '3' || word[3])
+				goto inval;
+			tp.port = word[2] - '0';
+			if (adap->chan_map[tp.port] >= MAX_NPORTS)
+				goto inval;
+			continue;
+		}
+		if (!isxdigit(*word))
+			goto inval;
+
+		/* we have found a trace pattern */
+		if (i) {                            /* split pattern */
+			if (tp.skip_len)            /* too many splits */
+				goto inval;
+			tp.skip_ofst = i / 16;
+		}
+
+		data = &tp.data[i / 8];
+		mask = &tp.mask[i / 8];
+		j = i;
+
+		while (isxdigit(*word)) {
+			if (i >= TRACE_LEN * 2) {
+				count = -EFBIG;
+				goto out;
+			}
+			*data = (*data << 4) + xdigit2int(*word++);
+			if (++i % 8 == 0)
+				data++;
+		}
+		if (*word == '/') {
+			word++;
+			while (isxdigit(*word)) {
+				if (j >= i)         /* mask longer than data */
+					goto inval;
+				*mask = (*mask << 4) + xdigit2int(*word++);
+				if (++j % 8 == 0)
+					mask++;
+			}
+			if (i != j)                 /* mask shorter than data */
+				goto inval;
+		} else {                            /* no mask, use all 1s */
+			for ( ; i - j >= 8; j += 8)
+				*mask++ = 0xffffffff;
+			if (i % 8)
+				*mask = (1 << (i % 8) * 4) - 1;
+		}
+		if (*word == '@') {
+			end = (char *)word + 1;
+			ret = kstrtouint(end, 10, &j);
+			if (*end && *end != '\n')
+				goto inval;
+			if (j & 7)          /* doesn't start at multiple of 8 */
+				goto inval;
+			j /= 8;
+			if (j < tp.skip_ofst)     /* overlaps earlier pattern */
+				goto inval;
+			if (j - tp.skip_ofst > 31)            /* skip too big */
+				goto inval;
+			tp.skip_len = j - tp.skip_ofst;
+		}
+		if (i % 8) {
+			*data <<= (8 - i % 8) * 4;
+			*mask <<= (8 - i % 8) * 4;
+			i = (i + 15) & ~15;         /* 8-byte align */
+		}
+	}
+
+	if (tp.port == TRC_PORT_NONE)
+		goto inval;
+
+apply:
+	i = t4_set_trace_filter(adap, &tp, trcidx, enable);
+	if (i)
+		count = i;
+out:
+	kfree(s);
+	return count;
+}
+
+static const struct file_operations mps_trc_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = mps_trc_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = single_release,
+	.write   = mps_trc_write
+};
+
 static ssize_t flash_read(struct file *file, char __user *buf, size_t count,
 			  loff_t *ppos)
 {
@@ -1895,13 +2236,13 @@ static int sge_qinfo_show(struct seq_file *seq, void *v)
 {
 	struct adapter *adap = seq->private;
 	int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
-	int toe_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4);
+	int iscsi_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4);
 	int rdma_entries = DIV_ROUND_UP(adap->sge.rdmaqs, 4);
 	int ciq_entries = DIV_ROUND_UP(adap->sge.rdmaciqs, 4);
 	int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
 	int i, r = (uintptr_t)v - 1;
-	int toe_idx = r - eth_entries;
-	int rdma_idx = toe_idx - toe_entries;
+	int iscsi_idx = r - eth_entries;
+	int rdma_idx = iscsi_idx - iscsi_entries;
 	int ciq_idx = rdma_idx - rdma_entries;
 	int ctrl_idx =  ciq_idx - ciq_entries;
 	int fq_idx =  ctrl_idx - ctrl_entries;
@@ -1917,8 +2258,12 @@ do { \
 		seq_putc(seq, '\n'); \
 } while (0)
 #define S(s, v) S3("s", s, v)
+#define T3(fmt_spec, s, v) S3(fmt_spec, s, tx[i].v)
 #define T(s, v) S3("u", s, tx[i].v)
+#define TL(s, v) T3("lu", s, v)
+#define R3(fmt_spec, s, v) S3(fmt_spec, s, rx[i].v)
 #define R(s, v) S3("u", s, rx[i].v)
+#define RL(s, v) R3("lu", s, v)
 
 	if (r < eth_entries) {
 		int base_qset = r * 4;
@@ -1957,12 +2302,30 @@ do { \
 		R("FL avail:", fl.avail);
 		R("FL PIDX:", fl.pidx);
 		R("FL CIDX:", fl.cidx);
-	} else if (toe_idx < toe_entries) {
-		const struct sge_ofld_rxq *rx = &adap->sge.ofldrxq[toe_idx * 4];
-		const struct sge_ofld_txq *tx = &adap->sge.ofldtxq[toe_idx * 4];
-		int n = min(4, adap->sge.ofldqsets - 4 * toe_idx);
+		RL("RxPackets:", stats.pkts);
+		RL("RxCSO:", stats.rx_cso);
+		RL("VLANxtract:", stats.vlan_ex);
+		RL("LROmerged:", stats.lro_merged);
+		RL("LROpackets:", stats.lro_pkts);
+		RL("RxDrops:", stats.rx_drops);
+		TL("TSO:", tso);
+		TL("TxCSO:", tx_cso);
+		TL("VLANins:", vlan_ins);
+		TL("TxQFull:", q.stops);
+		TL("TxQRestarts:", q.restarts);
+		TL("TxMapErr:", mapping_err);
+		RL("FLAllocErr:", fl.alloc_failed);
+		RL("FLLrgAlcErr:", fl.large_alloc_failed);
+		RL("FLStarving:", fl.starving);
+
+	} else if (iscsi_idx < iscsi_entries) {
+		const struct sge_ofld_rxq *rx =
+			&adap->sge.ofldrxq[iscsi_idx * 4];
+		const struct sge_ofld_txq *tx =
+			&adap->sge.ofldtxq[iscsi_idx * 4];
+		int n = min(4, adap->sge.ofldqsets - 4 * iscsi_idx);
 
-		S("QType:", "TOE");
+		S("QType:", "iSCSI");
 		T("TxQ ID:", q.cntxt_id);
 		T("TxQ size:", q.size);
 		T("TxQ inuse:", q.in_use);
@@ -1982,6 +2345,13 @@ do { \
 		R("FL avail:", fl.avail);
 		R("FL PIDX:", fl.pidx);
 		R("FL CIDX:", fl.cidx);
+		RL("RxPackets:", stats.pkts);
+		RL("RxImmPkts:", stats.imm);
+		RL("RxNoMem:", stats.nomem);
+		RL("FLAllocErr:", fl.alloc_failed);
+		RL("FLLrgAlcErr:", fl.large_alloc_failed);
+		RL("FLStarving:", fl.starving);
+
 	} else if (rdma_idx < rdma_entries) {
 		const struct sge_ofld_rxq *rx =
 				&adap->sge.rdmarxq[rdma_idx * 4];
@@ -2004,6 +2374,13 @@ do { \
 		R("FL avail:", fl.avail);
 		R("FL PIDX:", fl.pidx);
 		R("FL CIDX:", fl.cidx);
+		RL("RxPackets:", stats.pkts);
+		RL("RxImmPkts:", stats.imm);
+		RL("RxNoMem:", stats.nomem);
+		RL("FLAllocErr:", fl.alloc_failed);
+		RL("FLLrgAlcErr:", fl.large_alloc_failed);
+		RL("FLStarving:", fl.starving);
+
 	} else if (ciq_idx < ciq_entries) {
 		const struct sge_ofld_rxq *rx = &adap->sge.rdmaciq[ciq_idx * 4];
 		int n = min(4, adap->sge.rdmaciqs - 4 * ciq_idx);
@@ -2019,6 +2396,9 @@ do { \
 		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
 		S3("u", "Intr pktcnt:",
 		   adap->sge.counter_val[rx[i].rspq.pktcnt_idx]);
+		RL("RxAN:", stats.an);
+		RL("RxNoMem:", stats.nomem);
+
 	} else if (ctrl_idx < ctrl_entries) {
 		const struct sge_ctrl_txq *tx = &adap->sge.ctrlq[ctrl_idx * 4];
 		int n = min(4, adap->params.nports - 4 * ctrl_idx);
@@ -2029,6 +2409,8 @@ do { \
 		T("TxQ inuse:", q.in_use);
 		T("TxQ CIDX:", q.cidx);
 		T("TxQ PIDX:", q.pidx);
+		TL("TxQFull:", q.stops);
+		TL("TxQRestarts:", q.restarts);
 	} else if (fq_idx == 0) {
 		const struct sge_rspq *evtq = &adap->sge.fw_evtq;
 
@@ -2044,10 +2426,14 @@ do { \
 			   adap->sge.counter_val[evtq->pktcnt_idx]);
 	}
 #undef R
+#undef RL
 #undef T
+#undef TL
 #undef S
+#undef R3
+#undef T3
 #undef S3
-return 0;
+	return 0;
 }
 
 static int sge_queue_entries(const struct adapter *adap)
@@ -2164,6 +2550,73 @@ static const struct file_operations mem_debugfs_fops = {
 	.llseek  = default_llseek,
 };
 
+static int tid_info_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adap = seq->private;
+	const struct tid_info *t = &adap->tids;
+	enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
+
+	if (t4_read_reg(adap, LE_DB_CONFIG_A) & HASHEN_F) {
+		unsigned int sb;
+
+		if (chip <= CHELSIO_T5)
+			sb = t4_read_reg(adap, LE_DB_SERVER_INDEX_A) / 4;
+		else
+			sb = t4_read_reg(adap, LE_DB_SRVR_START_INDEX_A);
+
+		if (sb) {
+			seq_printf(seq, "TID range: 0..%u/%u..%u", sb - 1,
+				   adap->tids.hash_base,
+				   t->ntids - 1);
+			seq_printf(seq, ", in use: %u/%u\n",
+				   atomic_read(&t->tids_in_use),
+				   atomic_read(&t->hash_tids_in_use));
+		} else if (adap->flags & FW_OFLD_CONN) {
+			seq_printf(seq, "TID range: %u..%u/%u..%u",
+				   t->aftid_base,
+				   t->aftid_end,
+				   adap->tids.hash_base,
+				   t->ntids - 1);
+			seq_printf(seq, ", in use: %u/%u\n",
+				   atomic_read(&t->tids_in_use),
+				   atomic_read(&t->hash_tids_in_use));
+		} else {
+			seq_printf(seq, "TID range: %u..%u",
+				   adap->tids.hash_base,
+				   t->ntids - 1);
+			seq_printf(seq, ", in use: %u\n",
+				   atomic_read(&t->hash_tids_in_use));
+		}
+	} else if (t->ntids) {
+		seq_printf(seq, "TID range: 0..%u", t->ntids - 1);
+		seq_printf(seq, ", in use: %u\n",
+			   atomic_read(&t->tids_in_use));
+	}
+
+	if (t->nstids)
+		seq_printf(seq, "STID range: %u..%u, in use: %u\n",
+			   (!t->stid_base &&
+			   (chip <= CHELSIO_T5)) ?
+			   t->stid_base + 1 : t->stid_base,
+			   t->stid_base + t->nstids - 1, t->stids_in_use);
+	if (t->natids)
+		seq_printf(seq, "ATID range: 0..%u, in use: %u\n",
+			   t->natids - 1, t->atids_in_use);
+	seq_printf(seq, "FTID range: %u..%u\n", t->ftid_base,
+		   t->ftid_base + t->nftids - 1);
+	if (t->nsftids)
+		seq_printf(seq, "SFTID range: %u..%u in use: %u\n",
+			   t->sftid_base, t->sftid_base + t->nsftids - 2,
+			   t->sftids_in_use);
+	if (t->ntids)
+		seq_printf(seq, "HW TID usage: %u IP users, %u IPv6 users\n",
+			   t4_read_reg(adap, LE_DB_ACT_CNT_IPV4_A),
+			   t4_read_reg(adap, LE_DB_ACT_CNT_IPV6_A));
+	return 0;
+}
+
+DEFINE_SIMPLE_DEBUGFS_FILE(tid_info);
+
 static void add_debugfs_mem(struct adapter *adap, const char *name,
 			    unsigned int idx, unsigned int size_mb)
 {
@@ -2227,6 +2680,290 @@ static const struct file_operations blocked_fl_fops = {
 	.llseek  = generic_file_llseek,
 };
 
+struct mem_desc {
+	unsigned int base;
+	unsigned int limit;
+	unsigned int idx;
+};
+
+static int mem_desc_cmp(const void *a, const void *b)
+{
+	return ((const struct mem_desc *)a)->base -
+	       ((const struct mem_desc *)b)->base;
+}
+
+static void mem_region_show(struct seq_file *seq, const char *name,
+			    unsigned int from, unsigned int to)
+{
+	char buf[40];
+
+	string_get_size((u64)to - from + 1, 1, STRING_UNITS_2, buf,
+			sizeof(buf));
+	seq_printf(seq, "%-15s %#x-%#x [%s]\n", name, from, to, buf);
+}
+
+static int meminfo_show(struct seq_file *seq, void *v)
+{
+	static const char * const memory[] = { "EDC0:", "EDC1:", "MC:",
+					"MC0:", "MC1:"};
+	static const char * const region[] = {
+		"DBQ contexts:", "IMSG contexts:", "FLM cache:", "TCBs:",
+		"Pstructs:", "Timers:", "Rx FL:", "Tx FL:", "Pstruct FL:",
+		"Tx payload:", "Rx payload:", "LE hash:", "iSCSI region:",
+		"TDDP region:", "TPT region:", "STAG region:", "RQ region:",
+		"RQUDP region:", "PBL region:", "TXPBL region:",
+		"DBVFIFO region:", "ULPRX state:", "ULPTX state:",
+		"On-chip queues:"
+	};
+
+	int i, n;
+	u32 lo, hi, used, alloc;
+	struct mem_desc avail[4];
+	struct mem_desc mem[ARRAY_SIZE(region) + 3];      /* up to 3 holes */
+	struct mem_desc *md = mem;
+	struct adapter *adap = seq->private;
+
+	for (i = 0; i < ARRAY_SIZE(mem); i++) {
+		mem[i].limit = 0;
+		mem[i].idx = i;
+	}
+
+	/* Find and sort the populated memory ranges */
+	i = 0;
+	lo = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
+	if (lo & EDRAM0_ENABLE_F) {
+		hi = t4_read_reg(adap, MA_EDRAM0_BAR_A);
+		avail[i].base = EDRAM0_BASE_G(hi) << 20;
+		avail[i].limit = avail[i].base + (EDRAM0_SIZE_G(hi) << 20);
+		avail[i].idx = 0;
+		i++;
+	}
+	if (lo & EDRAM1_ENABLE_F) {
+		hi = t4_read_reg(adap, MA_EDRAM1_BAR_A);
+		avail[i].base = EDRAM1_BASE_G(hi) << 20;
+		avail[i].limit = avail[i].base + (EDRAM1_SIZE_G(hi) << 20);
+		avail[i].idx = 1;
+		i++;
+	}
+
+	if (is_t5(adap->params.chip)) {
+		if (lo & EXT_MEM0_ENABLE_F) {
+			hi = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A);
+			avail[i].base = EXT_MEM0_BASE_G(hi) << 20;
+			avail[i].limit =
+				avail[i].base + (EXT_MEM0_SIZE_G(hi) << 20);
+			avail[i].idx = 3;
+			i++;
+		}
+		if (lo & EXT_MEM1_ENABLE_F) {
+			hi = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
+			avail[i].base = EXT_MEM1_BASE_G(hi) << 20;
+			avail[i].limit =
+				avail[i].base + (EXT_MEM1_SIZE_G(hi) << 20);
+			avail[i].idx = 4;
+			i++;
+		}
+	} else {
+		if (lo & EXT_MEM_ENABLE_F) {
+			hi = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A);
+			avail[i].base = EXT_MEM_BASE_G(hi) << 20;
+			avail[i].limit =
+				avail[i].base + (EXT_MEM_SIZE_G(hi) << 20);
+			avail[i].idx = 2;
+			i++;
+		}
+	}
+	if (!i)                                    /* no memory available */
+		return 0;
+	sort(avail, i, sizeof(struct mem_desc), mem_desc_cmp, NULL);
+
+	(md++)->base = t4_read_reg(adap, SGE_DBQ_CTXT_BADDR_A);
+	(md++)->base = t4_read_reg(adap, SGE_IMSG_CTXT_BADDR_A);
+	(md++)->base = t4_read_reg(adap, SGE_FLM_CACHE_BADDR_A);
+	(md++)->base = t4_read_reg(adap, TP_CMM_TCB_BASE_A);
+	(md++)->base = t4_read_reg(adap, TP_CMM_MM_BASE_A);
+	(md++)->base = t4_read_reg(adap, TP_CMM_TIMER_BASE_A);
+	(md++)->base = t4_read_reg(adap, TP_CMM_MM_RX_FLST_BASE_A);
+	(md++)->base = t4_read_reg(adap, TP_CMM_MM_TX_FLST_BASE_A);
+	(md++)->base = t4_read_reg(adap, TP_CMM_MM_PS_FLST_BASE_A);
+
+	/* the next few have explicit upper bounds */
+	md->base = t4_read_reg(adap, TP_PMM_TX_BASE_A);
+	md->limit = md->base - 1 +
+		    t4_read_reg(adap, TP_PMM_TX_PAGE_SIZE_A) *
+		    PMTXMAXPAGE_G(t4_read_reg(adap, TP_PMM_TX_MAX_PAGE_A));
+	md++;
+
+	md->base = t4_read_reg(adap, TP_PMM_RX_BASE_A);
+	md->limit = md->base - 1 +
+		    t4_read_reg(adap, TP_PMM_RX_PAGE_SIZE_A) *
+		    PMRXMAXPAGE_G(t4_read_reg(adap, TP_PMM_RX_MAX_PAGE_A));
+	md++;
+
+	if (t4_read_reg(adap, LE_DB_CONFIG_A) & HASHEN_F) {
+		if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) {
+			hi = t4_read_reg(adap, LE_DB_TID_HASHBASE_A) / 4;
+			md->base = t4_read_reg(adap, LE_DB_HASH_TID_BASE_A);
+		 } else {
+			hi = t4_read_reg(adap, LE_DB_HASH_TID_BASE_A);
+			md->base = t4_read_reg(adap,
+					       LE_DB_HASH_TBL_BASE_ADDR_A);
+		}
+		md->limit = 0;
+	} else {
+		md->base = 0;
+		md->idx = ARRAY_SIZE(region);  /* hide it */
+	}
+	md++;
+
+#define ulp_region(reg) do { \
+	md->base = t4_read_reg(adap, ULP_ ## reg ## _LLIMIT_A);\
+	(md++)->limit = t4_read_reg(adap, ULP_ ## reg ## _ULIMIT_A); \
+} while (0)
+
+	ulp_region(RX_ISCSI);
+	ulp_region(RX_TDDP);
+	ulp_region(TX_TPT);
+	ulp_region(RX_STAG);
+	ulp_region(RX_RQ);
+	ulp_region(RX_RQUDP);
+	ulp_region(RX_PBL);
+	ulp_region(TX_PBL);
+#undef ulp_region
+	md->base = 0;
+	md->idx = ARRAY_SIZE(region);
+	if (!is_t4(adap->params.chip)) {
+		u32 size = 0;
+		u32 sge_ctrl = t4_read_reg(adap, SGE_CONTROL2_A);
+		u32 fifo_size = t4_read_reg(adap, SGE_DBVFIFO_SIZE_A);
+
+		if (is_t5(adap->params.chip)) {
+			if (sge_ctrl & VFIFO_ENABLE_F)
+				size = DBVFIFO_SIZE_G(fifo_size);
+		} else {
+			size = T6_DBVFIFO_SIZE_G(fifo_size);
+		}
+
+		if (size) {
+			md->base = BASEADDR_G(t4_read_reg(adap,
+					SGE_DBVFIFO_BADDR_A));
+			md->limit = md->base + (size << 2) - 1;
+		}
+	}
+
+	md++;
+
+	md->base = t4_read_reg(adap, ULP_RX_CTX_BASE_A);
+	md->limit = 0;
+	md++;
+	md->base = t4_read_reg(adap, ULP_TX_ERR_TABLE_BASE_A);
+	md->limit = 0;
+	md++;
+
+	md->base = adap->vres.ocq.start;
+	if (adap->vres.ocq.size)
+		md->limit = md->base + adap->vres.ocq.size - 1;
+	else
+		md->idx = ARRAY_SIZE(region);  /* hide it */
+	md++;
+
+	/* add any address-space holes, there can be up to 3 */
+	for (n = 0; n < i - 1; n++)
+		if (avail[n].limit < avail[n + 1].base)
+			(md++)->base = avail[n].limit;
+	if (avail[n].limit)
+		(md++)->base = avail[n].limit;
+
+	n = md - mem;
+	sort(mem, n, sizeof(struct mem_desc), mem_desc_cmp, NULL);
+
+	for (lo = 0; lo < i; lo++)
+		mem_region_show(seq, memory[avail[lo].idx], avail[lo].base,
+				avail[lo].limit - 1);
+
+	seq_putc(seq, '\n');
+	for (i = 0; i < n; i++) {
+		if (mem[i].idx >= ARRAY_SIZE(region))
+			continue;                        /* skip holes */
+		if (!mem[i].limit)
+			mem[i].limit = i < n - 1 ? mem[i + 1].base - 1 : ~0;
+		mem_region_show(seq, region[mem[i].idx], mem[i].base,
+				mem[i].limit);
+	}
+
+	seq_putc(seq, '\n');
+	lo = t4_read_reg(adap, CIM_SDRAM_BASE_ADDR_A);
+	hi = t4_read_reg(adap, CIM_SDRAM_ADDR_SIZE_A) + lo - 1;
+	mem_region_show(seq, "uP RAM:", lo, hi);
+
+	lo = t4_read_reg(adap, CIM_EXTMEM2_BASE_ADDR_A);
+	hi = t4_read_reg(adap, CIM_EXTMEM2_ADDR_SIZE_A) + lo - 1;
+	mem_region_show(seq, "uP Extmem2:", lo, hi);
+
+	lo = t4_read_reg(adap, TP_PMM_RX_MAX_PAGE_A);
+	seq_printf(seq, "\n%u Rx pages of size %uKiB for %u channels\n",
+		   PMRXMAXPAGE_G(lo),
+		   t4_read_reg(adap, TP_PMM_RX_PAGE_SIZE_A) >> 10,
+		   (lo & PMRXNUMCHN_F) ? 2 : 1);
+
+	lo = t4_read_reg(adap, TP_PMM_TX_MAX_PAGE_A);
+	hi = t4_read_reg(adap, TP_PMM_TX_PAGE_SIZE_A);
+	seq_printf(seq, "%u Tx pages of size %u%ciB for %u channels\n",
+		   PMTXMAXPAGE_G(lo),
+		   hi >= (1 << 20) ? (hi >> 20) : (hi >> 10),
+		   hi >= (1 << 20) ? 'M' : 'K', 1 << PMTXNUMCHN_G(lo));
+	seq_printf(seq, "%u p-structs\n\n",
+		   t4_read_reg(adap, TP_CMM_MM_MAX_PSTRUCT_A));
+
+	for (i = 0; i < 4; i++) {
+		if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5)
+			lo = t4_read_reg(adap, MPS_RX_MAC_BG_PG_CNT0_A + i * 4);
+		else
+			lo = t4_read_reg(adap, MPS_RX_PG_RSV0_A + i * 4);
+		if (is_t5(adap->params.chip)) {
+			used = T5_USED_G(lo);
+			alloc = T5_ALLOC_G(lo);
+		} else {
+			used = USED_G(lo);
+			alloc = ALLOC_G(lo);
+		}
+		/* For T6 these are MAC buffer groups */
+		seq_printf(seq, "Port %d using %u pages out of %u allocated\n",
+			   i, used, alloc);
+	}
+	for (i = 0; i < adap->params.arch.nchan; i++) {
+		if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5)
+			lo = t4_read_reg(adap,
+					 MPS_RX_LPBK_BG_PG_CNT0_A + i * 4);
+		else
+			lo = t4_read_reg(adap, MPS_RX_PG_RSV4_A + i * 4);
+		if (is_t5(adap->params.chip)) {
+			used = T5_USED_G(lo);
+			alloc = T5_ALLOC_G(lo);
+		} else {
+			used = USED_G(lo);
+			alloc = ALLOC_G(lo);
+		}
+		/* For T6 these are MAC buffer groups */
+		seq_printf(seq,
+			   "Loopback %d using %u pages out of %u allocated\n",
+			   i, used, alloc);
+	}
+	return 0;
+}
+
+static int meminfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, meminfo_show, inode->i_private);
+}
+
+static const struct file_operations meminfo_fops = {
+	.owner   = THIS_MODULE,
+	.open    = meminfo_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = single_release,
+};
 /* Add an array of Debug FS files.
  */
 void add_debugfs_files(struct adapter *adap,
@@ -2264,6 +3001,10 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "mbox5", &mbox_debugfs_fops, S_IRUSR | S_IWUSR, 5 },
 		{ "mbox6", &mbox_debugfs_fops, S_IRUSR | S_IWUSR, 6 },
 		{ "mbox7", &mbox_debugfs_fops, S_IRUSR | S_IWUSR, 7 },
+		{ "trace0", &mps_trc_debugfs_fops, S_IRUSR | S_IWUSR, 0 },
+		{ "trace1", &mps_trc_debugfs_fops, S_IRUSR | S_IWUSR, 1 },
+		{ "trace2", &mps_trc_debugfs_fops, S_IRUSR | S_IWUSR, 2 },
+		{ "trace3", &mps_trc_debugfs_fops, S_IRUSR | S_IWUSR, 3 },
 		{ "l2t", &t4_l2t_fops, S_IRUSR, 0},
 		{ "mps_tcam", &mps_tcam_debugfs_fops, S_IRUSR, 0 },
 		{ "rss", &rss_debugfs_fops, S_IRUSR, 0 },
@@ -2293,7 +3034,9 @@ int t4_setup_debugfs(struct adapter *adap)
 #if IS_ENABLED(CONFIG_IPV6)
 		{ "clip_tbl", &clip_tbl_debugfs_fops, S_IRUSR, 0 },
 #endif
+		{ "tids", &tid_info_debugfs_fops, S_IRUSR, 0},
 		{ "blocked_fl", &blocked_fl_fops, S_IRUSR | S_IWUSR, 0 },
+		{ "meminfo", &meminfo_fops, S_IRUSR, 0 },
 	};
 
 	/* Debug FS nodes common to all T5 and later adapters.
@@ -2341,6 +3084,10 @@ int t4_setup_debugfs(struct adapter *adap)
 
 	de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap,
 				      &flash_debugfs_fops, adap->params.sf_size);
+	debugfs_create_bool("use_backdoor", S_IWUSR | S_IRUSR,
+			    adap->debugfs_root, &adap->use_bd);
+	debugfs_create_bool("trace_rss", S_IWUSR | S_IRUSR,
+			    adap->debugfs_root, &adap->trace_rss);
 
 	return 0;
 }