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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 42 insertions, 21 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index cef866c37648..de69e719dc9d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -57,6 +57,7 @@ static const char mlxsw_pci_driver_name[] = "mlxsw_pci";
 
 static const struct pci_device_id mlxsw_pci_id_table[] = {
 	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHX2), 0},
+	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
 	{0, }
 };
 
@@ -67,6 +68,8 @@ static const char *mlxsw_pci_device_kind_get(const struct pci_device_id *id)
 	switch (id->device) {
 	case PCI_DEVICE_ID_MELLANOX_SWITCHX2:
 		return MLXSW_DEVICE_KIND_SWITCHX2;
+	case PCI_DEVICE_ID_MELLANOX_SPECTRUM:
+		return MLXSW_DEVICE_KIND_SPECTRUM;
 	default:
 		BUG();
 	}
@@ -171,8 +174,8 @@ struct mlxsw_pci {
 	struct msix_entry msix_entry;
 	struct mlxsw_core *core;
 	struct {
-		u16 num_pages;
 		struct mlxsw_pci_mem_item *items;
+		unsigned int count;
 	} fw_area;
 	struct {
 		struct mlxsw_pci_mem_item out_mbox;
@@ -431,8 +434,7 @@ static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe,
 
 	mapaddr = pci_map_single(pdev, frag_data, frag_len, direction);
 	if (unlikely(pci_dma_mapping_error(pdev, mapaddr))) {
-		if (net_ratelimit())
-			dev_err(&pdev->dev, "failed to dma map tx frag\n");
+		dev_err_ratelimited(&pdev->dev, "failed to dma map tx frag\n");
 		return -EIO;
 	}
 	mlxsw_pci_wqe_address_set(wqe, index, mapaddr);
@@ -497,6 +499,7 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			      struct mlxsw_pci_queue *q)
 {
 	struct mlxsw_pci_queue_elem_info *elem_info;
+	u8 sdq_count = mlxsw_pci_sdq_count(mlxsw_pci);
 	int i;
 	int err;
 
@@ -504,9 +507,9 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	q->consumer_counter = 0;
 
 	/* Set CQ of same number of this RDQ with base
-	 * above MLXSW_PCI_SDQS_MAX as the lower ones are assigned to SDQs.
+	 * above SDQ count as the lower ones are assigned to SDQs.
 	 */
-	mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, q->num + MLXSW_PCI_SDQS_COUNT);
+	mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, sdq_count + q->num);
 	mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
 		dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i);
@@ -699,8 +702,8 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 put_new_skb:
 	memset(wqe, 0, q->elem_size);
 	err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
-	if (err && net_ratelimit())
-		dev_dbg(&pdev->dev, "Failed to alloc skb for RDQ\n");
+	if (err)
+		dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
 	/* Everything is set up, ring doorbell to pass elem to HW */
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
@@ -830,7 +833,8 @@ static void mlxsw_pci_eq_tasklet(unsigned long data)
 {
 	struct mlxsw_pci_queue *q = (struct mlxsw_pci_queue *) data;
 	struct mlxsw_pci *mlxsw_pci = q->pci;
-	unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_COUNT)];
+	u8 cq_count = mlxsw_pci_cq_count(mlxsw_pci);
+	unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_MAX)];
 	char *eqe;
 	u8 cqn;
 	bool cq_handle = false;
@@ -866,7 +870,7 @@ static void mlxsw_pci_eq_tasklet(unsigned long data)
 
 	if (!cq_handle)
 		return;
-	for_each_set_bit(cqn, active_cqns, MLXSW_PCI_CQS_COUNT) {
+	for_each_set_bit(cqn, active_cqns, cq_count) {
 		q = mlxsw_pci_cq_get(mlxsw_pci, cqn);
 		mlxsw_pci_queue_tasklet_schedule(q);
 	}
@@ -1067,10 +1071,8 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 	num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox);
 	eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox);
 
-	if ((num_sdqs != MLXSW_PCI_SDQS_COUNT) ||
-	    (num_rdqs != MLXSW_PCI_RDQS_COUNT) ||
-	    (num_cqs != MLXSW_PCI_CQS_COUNT) ||
-	    (num_eqs != MLXSW_PCI_EQS_COUNT)) {
+	if (num_sdqs + num_rdqs > num_cqs ||
+	    num_cqs > MLXSW_PCI_CQS_MAX || num_eqs != MLXSW_PCI_EQS_COUNT) {
 		dev_err(&pdev->dev, "Unsupported number of queues\n");
 		return -EINVAL;
 	}
@@ -1215,6 +1217,14 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			mbox, profile->max_flood_tables);
 		mlxsw_cmd_mbox_config_profile_max_vid_flood_tables_set(
 			mbox, profile->max_vid_flood_tables);
+		mlxsw_cmd_mbox_config_profile_max_fid_offset_flood_tables_set(
+			mbox, profile->max_fid_offset_flood_tables);
+		mlxsw_cmd_mbox_config_profile_fid_offset_flood_table_size_set(
+			mbox, profile->fid_offset_flood_table_size);
+		mlxsw_cmd_mbox_config_profile_max_fid_flood_tables_set(
+			mbox, profile->max_fid_flood_tables);
+		mlxsw_cmd_mbox_config_profile_fid_flood_table_size_set(
+			mbox, profile->fid_flood_table_size);
 	}
 	if (profile->used_flood_mode) {
 		mlxsw_cmd_mbox_config_profile_set_flood_mode_set(
@@ -1272,6 +1282,7 @@ static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 				  u16 num_pages)
 {
 	struct mlxsw_pci_mem_item *mem_item;
+	int nent = 0;
 	int i;
 	int err;
 
@@ -1279,7 +1290,7 @@ static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 					   GFP_KERNEL);
 	if (!mlxsw_pci->fw_area.items)
 		return -ENOMEM;
-	mlxsw_pci->fw_area.num_pages = num_pages;
+	mlxsw_pci->fw_area.count = num_pages;
 
 	mlxsw_cmd_mbox_zero(mbox);
 	for (i = 0; i < num_pages; i++) {
@@ -1293,13 +1304,22 @@ static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			err = -ENOMEM;
 			goto err_alloc;
 		}
-		mlxsw_cmd_mbox_map_fa_pa_set(mbox, i, mem_item->mapaddr);
-		mlxsw_cmd_mbox_map_fa_log2size_set(mbox, i, 0); /* 1 page */
+		mlxsw_cmd_mbox_map_fa_pa_set(mbox, nent, mem_item->mapaddr);
+		mlxsw_cmd_mbox_map_fa_log2size_set(mbox, nent, 0); /* 1 page */
+		if (++nent == MLXSW_CMD_MAP_FA_VPM_ENTRIES_MAX) {
+			err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, nent);
+			if (err)
+				goto err_cmd_map_fa;
+			nent = 0;
+			mlxsw_cmd_mbox_zero(mbox);
+		}
 	}
 
-	err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, num_pages);
-	if (err)
-		goto err_cmd_map_fa;
+	if (nent) {
+		err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, nent);
+		if (err)
+			goto err_cmd_map_fa;
+	}
 
 	return 0;
 
@@ -1322,7 +1342,7 @@ static void mlxsw_pci_fw_area_fini(struct mlxsw_pci *mlxsw_pci)
 
 	mlxsw_cmd_unmap_fa(mlxsw_pci->core);
 
-	for (i = 0; i < mlxsw_pci->fw_area.num_pages; i++) {
+	for (i = 0; i < mlxsw_pci->fw_area.count; i++) {
 		mem_item = &mlxsw_pci->fw_area.items[i];
 
 		pci_free_consistent(mlxsw_pci->pdev, mem_item->size,
@@ -1642,8 +1662,9 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 							   CIR_OUT_PARAM_LO));
 			memcpy(out_mbox + sizeof(tmp), &tmp, sizeof(tmp));
 		}
-	} else if (!err && out_mbox)
+	} else if (!err && out_mbox) {
 		memcpy(out_mbox, mlxsw_pci->cmd.out_mbox.buf, out_mbox_size);
+	}
 
 	mutex_unlock(&mlxsw_pci->cmd.lock);