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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 120 insertions, 30 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index dde35dae35c5..d67969d3e484 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -41,9 +41,11 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/firmware.h>
 #include <linux/vermagic.h>
+#include <net/devlink.h>
 
 #include "nfpcore/nfp.h"
 #include "nfpcore/nfp_cpp.h"
@@ -52,6 +54,7 @@
 
 #include "nfpcore/nfp6000_pcie.h"
 
+#include "nfp_app.h"
 #include "nfp_main.h"
 #include "nfp_net.h"
 
@@ -71,20 +74,22 @@ static const struct pci_device_id nfp_pci_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, nfp_pci_device_ids);
 
-static void nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
+static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 {
-#ifdef CONFIG_PCI_IOV
 	int err;
 
-	pf->limit_vfs = nfp_rtsym_read_le(pf->cpp, "nfd_vf_cfg_max_vfs", &err);
+	pf->limit_vfs = nfp_rtsym_read_le(pf->rtbl, "nfd_vf_cfg_max_vfs", &err);
 	if (!err)
-		return;
+		return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
 
 	pf->limit_vfs = ~0;
+	pci_sriov_set_totalvfs(pf->pdev, 0); /* 0 is unset */
 	/* Allow any setting for backwards compatibility if symbol not found */
-	if (err != -ENOENT)
-		nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err);
-#endif
+	if (err == -ENOENT)
+		return 0;
+
+	nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err);
+	return err;
 }
 
 static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs)
@@ -93,23 +98,41 @@ static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	struct nfp_pf *pf = pci_get_drvdata(pdev);
 	int err;
 
+	mutex_lock(&pf->lock);
+
 	if (num_vfs > pf->limit_vfs) {
 		nfp_info(pf->cpp, "Firmware limits number of VFs to %u\n",
 			 pf->limit_vfs);
-		return -EINVAL;
+		err = -EINVAL;
+		goto err_unlock;
 	}
 
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
-		dev_warn(&pdev->dev, "Failed to enable PCI sriov: %d\n", err);
-		return err;
+		dev_warn(&pdev->dev, "Failed to enable PCI SR-IOV: %d\n", err);
+		goto err_unlock;
+	}
+
+	err = nfp_app_sriov_enable(pf->app, num_vfs);
+	if (err) {
+		dev_warn(&pdev->dev,
+			 "App specific PCI SR-IOV configuration failed: %d\n",
+			 err);
+		goto err_sriov_disable;
 	}
 
 	pf->num_vfs = num_vfs;
 
 	dev_dbg(&pdev->dev, "Created %d VFs.\n", pf->num_vfs);
 
+	mutex_unlock(&pf->lock);
 	return num_vfs;
+
+err_sriov_disable:
+	pci_disable_sriov(pdev);
+err_unlock:
+	mutex_unlock(&pf->lock);
+	return err;
 #endif
 	return 0;
 }
@@ -119,19 +142,26 @@ static int nfp_pcie_sriov_disable(struct pci_dev *pdev)
 #ifdef CONFIG_PCI_IOV
 	struct nfp_pf *pf = pci_get_drvdata(pdev);
 
+	mutex_lock(&pf->lock);
+
 	/* If the VFs are assigned we cannot shut down SR-IOV without
 	 * causing issues, so just leave the hardware available but
 	 * disabled
 	 */
 	if (pci_vfs_assigned(pdev)) {
 		dev_warn(&pdev->dev, "Disabling while VFs assigned - VFs will not be deallocated\n");
+		mutex_unlock(&pf->lock);
 		return -EPERM;
 	}
 
+	nfp_app_sriov_disable(pf->app);
+
 	pf->num_vfs = 0;
 
 	pci_disable_sriov(pdev);
 	dev_dbg(&pdev->dev, "Removed VFs.\n");
+
+	mutex_unlock(&pf->lock);
 #endif
 	return 0;
 }
@@ -166,7 +196,7 @@ nfp_net_fw_find(struct pci_dev *pdev, struct nfp_pf *pf)
 		return NULL;
 	}
 
-	fw_model = nfp_hwinfo_lookup(pf->cpp, "assembly.partno");
+	fw_model = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno");
 	if (!fw_model) {
 		dev_err(&pdev->dev, "Error: can't read part number\n");
 		return NULL;
@@ -253,7 +283,6 @@ exit_release_fw:
 
 static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
 {
-	struct nfp_nsp_identify *nspi;
 	struct nfp_nsp *nsp;
 	int err;
 
@@ -270,14 +299,13 @@ static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
 
 	pf->eth_tbl = __nfp_eth_read_ports(pf->cpp, nsp);
 
-	nspi = __nfp_nsp_identify(nsp);
-	if (nspi) {
-		dev_info(&pdev->dev, "BSP: %s\n", nspi->version);
-		kfree(nspi);
-	}
+	pf->nspi = __nfp_nsp_identify(nsp);
+	if (pf->nspi)
+		dev_info(&pdev->dev, "BSP: %s\n", pf->nspi->version);
 
 	err = nfp_fw_load(pdev, pf, nsp);
 	if (err < 0) {
+		kfree(pf->nspi);
 		kfree(pf->eth_tbl);
 		dev_err(&pdev->dev, "Failed to load FW\n");
 		goto exit_close_nsp;
@@ -315,6 +343,7 @@ static void nfp_fw_unload(struct nfp_pf *pf)
 static int nfp_pci_probe(struct pci_dev *pdev,
 			 const struct pci_device_id *pci_id)
 {
+	struct devlink *devlink;
 	struct nfp_pf *pf;
 	int err;
 
@@ -335,15 +364,24 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 		goto err_pci_disable;
 	}
 
-	pf = kzalloc(sizeof(*pf), GFP_KERNEL);
-	if (!pf) {
+	devlink = devlink_alloc(&nfp_devlink_ops, sizeof(*pf));
+	if (!devlink) {
 		err = -ENOMEM;
 		goto err_rel_regions;
 	}
+	pf = devlink_priv(devlink);
+	INIT_LIST_HEAD(&pf->vnics);
 	INIT_LIST_HEAD(&pf->ports);
+	mutex_init(&pf->lock);
 	pci_set_drvdata(pdev, pf);
 	pf->pdev = pdev;
 
+	pf->wq = alloc_workqueue("nfp-%s", 0, 2, pci_name(pdev));
+	if (!pf->wq) {
+		err = -ENOMEM;
+		goto err_pci_priv_unset;
+	}
+
 	pf->cpp = nfp_cpp_from_nfp6000_pcie(pdev);
 	if (IS_ERR_OR_NULL(pf->cpp)) {
 		err = PTR_ERR(pf->cpp);
@@ -352,34 +390,72 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 		goto err_disable_msix;
 	}
 
+	pf->hwinfo = nfp_hwinfo_read(pf->cpp);
+
 	dev_info(&pdev->dev, "Assembly: %s%s%s-%s CPLD: %s\n",
-		 nfp_hwinfo_lookup(pf->cpp, "assembly.vendor"),
-		 nfp_hwinfo_lookup(pf->cpp, "assembly.partno"),
-		 nfp_hwinfo_lookup(pf->cpp, "assembly.serial"),
-		 nfp_hwinfo_lookup(pf->cpp, "assembly.revision"),
-		 nfp_hwinfo_lookup(pf->cpp, "cpld.version"));
+		 nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor"),
+		 nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno"),
+		 nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial"),
+		 nfp_hwinfo_lookup(pf->hwinfo, "assembly.revision"),
+		 nfp_hwinfo_lookup(pf->hwinfo, "cpld.version"));
+
+	err = devlink_register(devlink, &pdev->dev);
+	if (err)
+		goto err_hwinfo_free;
 
 	err = nfp_nsp_init(pdev, pf);
 	if (err)
-		goto err_cpp_free;
+		goto err_devlink_unreg;
 
-	nfp_pcie_sriov_read_nfd_limit(pf);
+	pf->mip = nfp_mip_open(pf->cpp);
+	pf->rtbl = __nfp_rtsym_table_read(pf->cpp, pf->mip);
 
-	err = nfp_net_pci_probe(pf);
+	err = nfp_pcie_sriov_read_nfd_limit(pf);
 	if (err)
 		goto err_fw_unload;
 
+	pf->num_vfs = pci_num_vf(pdev);
+	if (pf->num_vfs > pf->limit_vfs) {
+		dev_err(&pdev->dev,
+			"Error: %d VFs already enabled, but loaded FW can only support %d\n",
+			pf->num_vfs, pf->limit_vfs);
+		goto err_fw_unload;
+	}
+
+	err = nfp_net_pci_probe(pf);
+	if (err)
+		goto err_sriov_unlimit;
+
+	err = nfp_hwmon_register(pf);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to register hwmon info\n");
+		goto err_net_remove;
+	}
+
 	return 0;
 
+err_net_remove:
+	nfp_net_pci_remove(pf);
+err_sriov_unlimit:
+	pci_sriov_set_totalvfs(pf->pdev, 0);
 err_fw_unload:
+	kfree(pf->rtbl);
+	nfp_mip_close(pf->mip);
 	if (pf->fw_loaded)
 		nfp_fw_unload(pf);
 	kfree(pf->eth_tbl);
-err_cpp_free:
+	kfree(pf->nspi);
+err_devlink_unreg:
+	devlink_unregister(devlink);
+err_hwinfo_free:
+	kfree(pf->hwinfo);
 	nfp_cpp_free(pf->cpp);
 err_disable_msix:
+	destroy_workqueue(pf->wq);
+err_pci_priv_unset:
 	pci_set_drvdata(pdev, NULL);
-	kfree(pf);
+	mutex_destroy(&pf->lock);
+	devlink_free(devlink);
 err_rel_regions:
 	pci_release_regions(pdev);
 err_pci_disable:
@@ -391,19 +467,33 @@ err_pci_disable:
 static void nfp_pci_remove(struct pci_dev *pdev)
 {
 	struct nfp_pf *pf = pci_get_drvdata(pdev);
+	struct devlink *devlink;
+
+	nfp_hwmon_unregister(pf);
+
+	devlink = priv_to_devlink(pf);
 
 	nfp_net_pci_remove(pf);
 
 	nfp_pcie_sriov_disable(pdev);
+	pci_sriov_set_totalvfs(pf->pdev, 0);
+
+	devlink_unregister(devlink);
 
+	kfree(pf->rtbl);
+	nfp_mip_close(pf->mip);
 	if (pf->fw_loaded)
 		nfp_fw_unload(pf);
 
+	destroy_workqueue(pf->wq);
 	pci_set_drvdata(pdev, NULL);
+	kfree(pf->hwinfo);
 	nfp_cpp_free(pf->cpp);
 
 	kfree(pf->eth_tbl);
-	kfree(pf);
+	kfree(pf->nspi);
+	mutex_destroy(&pf->lock);
+	devlink_free(devlink);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 }