Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 630 insertions, 0 deletions

diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
new file mode 100644
index 000000000..ba26c5567
--- /dev/null
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -0,0 +1,630 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * dlmfs.c
+ *
+ * Code which implements the kernel side of a minimal userspace
+ * interface to our DLM. This file handles the virtual file system
+ * used for communication with userspace. Credit should go to ramfs,
+ * which was a template for the fs side of this module.
+ *
+ * Copyright (C) 2003, 2004 Oracle.  All rights reserved.
+ */
+
+/* Simple VFS hooks based on: */
+/*
+ * Resizable simple ram filesystem for Linux.
+ *
+ * Copyright (C) 2000 Linus Torvalds.
+ *               2000 Transmeta Corp.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/backing-dev.h>
+#include <linux/poll.h>
+
+#include <linux/uaccess.h>
+
+#include "../stackglue.h"
+#include "userdlm.h"
+
+#define MLOG_MASK_PREFIX ML_DLMFS
+#include "../cluster/masklog.h"
+
+
+static const struct super_operations dlmfs_ops;
+static const struct file_operations dlmfs_file_operations;
+static const struct inode_operations dlmfs_dir_inode_operations;
+static const struct inode_operations dlmfs_root_inode_operations;
+static const struct inode_operations dlmfs_file_inode_operations;
+static struct kmem_cache *dlmfs_inode_cache;
+
+struct workqueue_struct *user_dlm_worker;
+
+
+
+/*
+ * These are the ABI capabilities of dlmfs.
+ *
+ * Over time, dlmfs has added some features that were not part of the
+ * initial ABI.  Unfortunately, some of these features are not detectable
+ * via standard usage.  For example, Linux's default poll always returns
+ * EPOLLIN, so there is no way for a caller of poll(2) to know when dlmfs
+ * added poll support.  Instead, we provide this list of new capabilities.
+ *
+ * Capabilities is a read-only attribute.  We do it as a module parameter
+ * so we can discover it whether dlmfs is built in, loaded, or even not
+ * loaded.
+ *
+ * The ABI features are local to this machine's dlmfs mount.  This is
+ * distinct from the locking protocol, which is concerned with inter-node
+ * interaction.
+ *
+ * Capabilities:
+ * - bast	: EPOLLIN against the file descriptor of a held lock
+ *		  signifies a bast fired on the lock.
+ */
+#define DLMFS_CAPABILITIES "bast stackglue"
+static int param_set_dlmfs_capabilities(const char *val,
+					const struct kernel_param *kp)
+{
+	printk(KERN_ERR "%s: readonly parameter\n", kp->name);
+	return -EINVAL;
+}
+static int param_get_dlmfs_capabilities(char *buffer,
+					const struct kernel_param *kp)
+{
+	return strlcpy(buffer, DLMFS_CAPABILITIES,
+		       strlen(DLMFS_CAPABILITIES) + 1);
+}
+module_param_call(capabilities, param_set_dlmfs_capabilities,
+		  param_get_dlmfs_capabilities, NULL, 0444);
+MODULE_PARM_DESC(capabilities, DLMFS_CAPABILITIES);
+
+
+/*
+ * decodes a set of open flags into a valid lock level and a set of flags.
+ * returns < 0 if we have invalid flags
+ * flags which mean something to us:
+ * O_RDONLY -> PRMODE level
+ * O_WRONLY -> EXMODE level
+ *
+ * O_NONBLOCK -> NOQUEUE
+ */
+static int dlmfs_decode_open_flags(int open_flags,
+				   int *level,
+				   int *flags)
+{
+	if (open_flags & (O_WRONLY|O_RDWR))
+		*level = DLM_LOCK_EX;
+	else
+		*level = DLM_LOCK_PR;
+
+	*flags = 0;
+	if (open_flags & O_NONBLOCK)
+		*flags |= DLM_LKF_NOQUEUE;
+
+	return 0;
+}
+
+static int dlmfs_file_open(struct inode *inode,
+			   struct file *file)
+{
+	int status, level, flags;
+	struct dlmfs_filp_private *fp = NULL;
+	struct dlmfs_inode_private *ip;
+
+	if (S_ISDIR(inode->i_mode))
+		BUG();
+
+	mlog(0, "open called on inode %lu, flags 0x%x\n", inode->i_ino,
+		file->f_flags);
+
+	status = dlmfs_decode_open_flags(file->f_flags, &level, &flags);
+	if (status < 0)
+		goto bail;
+
+	/* We don't want to honor O_APPEND at read/write time as it
+	 * doesn't make sense for LVB writes. */
+	file->f_flags &= ~O_APPEND;
+
+	fp = kmalloc(sizeof(*fp), GFP_NOFS);
+	if (!fp) {
+		status = -ENOMEM;
+		goto bail;
+	}
+	fp->fp_lock_level = level;
+
+	ip = DLMFS_I(inode);
+
+	status = user_dlm_cluster_lock(&ip->ip_lockres, level, flags);
+	if (status < 0) {
+		/* this is a strange error to return here but I want
+		 * to be able userspace to be able to distinguish a
+		 * valid lock request from one that simply couldn't be
+		 * granted. */
+		if (flags & DLM_LKF_NOQUEUE && status == -EAGAIN)
+			status = -ETXTBSY;
+		kfree(fp);
+		goto bail;
+	}
+
+	file->private_data = fp;
+bail:
+	return status;
+}
+
+static int dlmfs_file_release(struct inode *inode,
+			      struct file *file)
+{
+	int level;
+	struct dlmfs_inode_private *ip = DLMFS_I(inode);
+	struct dlmfs_filp_private *fp = file->private_data;
+
+	if (S_ISDIR(inode->i_mode))
+		BUG();
+
+	mlog(0, "close called on inode %lu\n", inode->i_ino);
+
+	if (fp) {
+		level = fp->fp_lock_level;
+		if (level != DLM_LOCK_IV)
+			user_dlm_cluster_unlock(&ip->ip_lockres, level);
+
+		kfree(fp);
+		file->private_data = NULL;
+	}
+
+	return 0;
+}
+
+/*
+ * We do ->setattr() just to override size changes.  Our size is the size
+ * of the LVB and nothing else.
+ */
+static int dlmfs_file_setattr(struct mnt_idmap *idmap,
+			      struct dentry *dentry, struct iattr *attr)
+{
+	int error;
+	struct inode *inode = d_inode(dentry);
+
+	attr->ia_valid &= ~ATTR_SIZE;
+	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	if (error)
+		return error;
+
+	setattr_copy(&nop_mnt_idmap, inode, attr);
+	mark_inode_dirty(inode);
+	return 0;
+}
+
+static __poll_t dlmfs_file_poll(struct file *file, poll_table *wait)
+{
+	__poll_t event = 0;
+	struct inode *inode = file_inode(file);
+	struct dlmfs_inode_private *ip = DLMFS_I(inode);
+
+	poll_wait(file, &ip->ip_lockres.l_event, wait);
+
+	spin_lock(&ip->ip_lockres.l_lock);
+	if (ip->ip_lockres.l_flags & USER_LOCK_BLOCKED)
+		event = EPOLLIN | EPOLLRDNORM;
+	spin_unlock(&ip->ip_lockres.l_lock);
+
+	return event;
+}
+
+static ssize_t dlmfs_file_read(struct file *file,
+			       char __user *buf,
+			       size_t count,
+			       loff_t *ppos)
+{
+	char lvb[DLM_LVB_LEN];
+
+	if (!user_dlm_read_lvb(file_inode(file), lvb))
+		return 0;
+
+	return simple_read_from_buffer(buf, count, ppos, lvb, sizeof(lvb));
+}
+
+static ssize_t dlmfs_file_write(struct file *filp,
+				const char __user *buf,
+				size_t count,
+				loff_t *ppos)
+{
+	char lvb_buf[DLM_LVB_LEN];
+	int bytes_left;
+	struct inode *inode = file_inode(filp);
+
+	mlog(0, "inode %lu, count = %zu, *ppos = %llu\n",
+		inode->i_ino, count, *ppos);
+
+	if (*ppos >= DLM_LVB_LEN)
+		return -ENOSPC;
+
+	/* don't write past the lvb */
+	if (count > DLM_LVB_LEN - *ppos)
+		count = DLM_LVB_LEN - *ppos;
+
+	if (!count)
+		return 0;
+
+	bytes_left = copy_from_user(lvb_buf, buf, count);
+	count -= bytes_left;
+	if (count)
+		user_dlm_write_lvb(inode, lvb_buf, count);
+
+	*ppos = *ppos + count;
+	mlog(0, "wrote %zu bytes\n", count);
+	return count;
+}
+
+static void dlmfs_init_once(void *foo)
+{
+	struct dlmfs_inode_private *ip =
+		(struct dlmfs_inode_private *) foo;
+
+	ip->ip_conn = NULL;
+	ip->ip_parent = NULL;
+
+	inode_init_once(&ip->ip_vfs_inode);
+}
+
+static struct inode *dlmfs_alloc_inode(struct super_block *sb)
+{
+	struct dlmfs_inode_private *ip;
+
+	ip = alloc_inode_sb(sb, dlmfs_inode_cache, GFP_NOFS);
+	if (!ip)
+		return NULL;
+
+	return &ip->ip_vfs_inode;
+}
+
+static void dlmfs_free_inode(struct inode *inode)
+{
+	kmem_cache_free(dlmfs_inode_cache, DLMFS_I(inode));
+}
+
+static void dlmfs_evict_inode(struct inode *inode)
+{
+	int status;
+	struct dlmfs_inode_private *ip;
+	struct user_lock_res *lockres;
+	int teardown;
+
+	clear_inode(inode);
+
+	mlog(0, "inode %lu\n", inode->i_ino);
+
+	ip = DLMFS_I(inode);
+	lockres = &ip->ip_lockres;
+
+	if (S_ISREG(inode->i_mode)) {
+		spin_lock(&lockres->l_lock);
+		teardown = !!(lockres->l_flags & USER_LOCK_IN_TEARDOWN);
+		spin_unlock(&lockres->l_lock);
+		if (!teardown) {
+			status = user_dlm_destroy_lock(lockres);
+			if (status < 0)
+				mlog_errno(status);
+		}
+		iput(ip->ip_parent);
+		goto clear_fields;
+	}
+
+	mlog(0, "we're a directory, ip->ip_conn = 0x%p\n", ip->ip_conn);
+	/* we must be a directory. If required, lets unregister the
+	 * dlm context now. */
+	if (ip->ip_conn)
+		user_dlm_unregister(ip->ip_conn);
+clear_fields:
+	ip->ip_parent = NULL;
+	ip->ip_conn = NULL;
+}
+
+static struct inode *dlmfs_get_root_inode(struct super_block *sb)
+{
+	struct inode *inode = new_inode(sb);
+	umode_t mode = S_IFDIR | 0755;
+
+	if (inode) {
+		inode->i_ino = get_next_ino();
+		inode_init_owner(&nop_mnt_idmap, inode, NULL, mode);
+		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+		inc_nlink(inode);
+
+		inode->i_fop = &simple_dir_operations;
+		inode->i_op = &dlmfs_root_inode_operations;
+	}
+
+	return inode;
+}
+
+static struct inode *dlmfs_get_inode(struct inode *parent,
+				     struct dentry *dentry,
+				     umode_t mode)
+{
+	struct super_block *sb = parent->i_sb;
+	struct inode * inode = new_inode(sb);
+	struct dlmfs_inode_private *ip;
+
+	if (!inode)
+		return NULL;
+
+	inode->i_ino = get_next_ino();
+	inode_init_owner(&nop_mnt_idmap, inode, parent, mode);
+	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+
+	ip = DLMFS_I(inode);
+	ip->ip_conn = DLMFS_I(parent)->ip_conn;
+
+	switch (mode & S_IFMT) {
+	default:
+		/* for now we don't support anything other than
+		 * directories and regular files. */
+		BUG();
+		break;
+	case S_IFREG:
+		inode->i_op = &dlmfs_file_inode_operations;
+		inode->i_fop = &dlmfs_file_operations;
+
+		i_size_write(inode,  DLM_LVB_LEN);
+
+		user_dlm_lock_res_init(&ip->ip_lockres, dentry);
+
+		/* released at clear_inode time, this insures that we
+		 * get to drop the dlm reference on each lock *before*
+		 * we call the unregister code for releasing parent
+		 * directories. */
+		ip->ip_parent = igrab(parent);
+		BUG_ON(!ip->ip_parent);
+		break;
+	case S_IFDIR:
+		inode->i_op = &dlmfs_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+
+		/* directory inodes start off with i_nlink ==
+		 * 2 (for "." entry) */
+		inc_nlink(inode);
+		break;
+	}
+	return inode;
+}
+
+/*
+ * File creation. Allocate an inode, and we're done..
+ */
+/* SMP-safe */
+static int dlmfs_mkdir(struct mnt_idmap * idmap,
+		       struct inode * dir,
+		       struct dentry * dentry,
+		       umode_t mode)
+{
+	int status;
+	struct inode *inode = NULL;
+	const struct qstr *domain = &dentry->d_name;
+	struct dlmfs_inode_private *ip;
+	struct ocfs2_cluster_connection *conn;
+
+	mlog(0, "mkdir %.*s\n", domain->len, domain->name);
+
+	/* verify that we have a proper domain */
+	if (domain->len >= GROUP_NAME_MAX) {
+		status = -EINVAL;
+		mlog(ML_ERROR, "invalid domain name for directory.\n");
+		goto bail;
+	}
+
+	inode = dlmfs_get_inode(dir, dentry, mode | S_IFDIR);
+	if (!inode) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto bail;
+	}
+
+	ip = DLMFS_I(inode);
+
+	conn = user_dlm_register(domain);
+	if (IS_ERR(conn)) {
+		status = PTR_ERR(conn);
+		mlog(ML_ERROR, "Error %d could not register domain \"%.*s\"\n",
+		     status, domain->len, domain->name);
+		goto bail;
+	}
+	ip->ip_conn = conn;
+
+	inc_nlink(dir);
+	d_instantiate(dentry, inode);
+	dget(dentry);	/* Extra count - pin the dentry in core */
+
+	status = 0;
+bail:
+	if (status < 0)
+		iput(inode);
+	return status;
+}
+
+static int dlmfs_create(struct mnt_idmap *idmap,
+			struct inode *dir,
+			struct dentry *dentry,
+			umode_t mode,
+			bool excl)
+{
+	int status = 0;
+	struct inode *inode;
+	const struct qstr *name = &dentry->d_name;
+
+	mlog(0, "create %.*s\n", name->len, name->name);
+
+	/* verify name is valid and doesn't contain any dlm reserved
+	 * characters */
+	if (name->len >= USER_DLM_LOCK_ID_MAX_LEN ||
+	    name->name[0] == '$') {
+		status = -EINVAL;
+		mlog(ML_ERROR, "invalid lock name, %.*s\n", name->len,
+		     name->name);
+		goto bail;
+	}
+
+	inode = dlmfs_get_inode(dir, dentry, mode | S_IFREG);
+	if (!inode) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto bail;
+	}
+
+	d_instantiate(dentry, inode);
+	dget(dentry);	/* Extra count - pin the dentry in core */
+bail:
+	return status;
+}
+
+static int dlmfs_unlink(struct inode *dir,
+			struct dentry *dentry)
+{
+	int status;
+	struct inode *inode = d_inode(dentry);
+
+	mlog(0, "unlink inode %lu\n", inode->i_ino);
+
+	/* if there are no current holders, or none that are waiting
+	 * to acquire a lock, this basically destroys our lockres. */
+	status = user_dlm_destroy_lock(&DLMFS_I(inode)->ip_lockres);
+	if (status < 0) {
+		mlog(ML_ERROR, "unlink %pd, error %d from destroy\n",
+		     dentry, status);
+		goto bail;
+	}
+	status = simple_unlink(dir, dentry);
+bail:
+	return status;
+}
+
+static int dlmfs_fill_super(struct super_block * sb,
+			    void * data,
+			    int silent)
+{
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+	sb->s_magic = DLMFS_MAGIC;
+	sb->s_op = &dlmfs_ops;
+	sb->s_root = d_make_root(dlmfs_get_root_inode(sb));
+	if (!sb->s_root)
+		return -ENOMEM;
+	return 0;
+}
+
+static const struct file_operations dlmfs_file_operations = {
+	.open		= dlmfs_file_open,
+	.release	= dlmfs_file_release,
+	.poll		= dlmfs_file_poll,
+	.read		= dlmfs_file_read,
+	.write		= dlmfs_file_write,
+	.llseek		= default_llseek,
+};
+
+static const struct inode_operations dlmfs_dir_inode_operations = {
+	.create		= dlmfs_create,
+	.lookup		= simple_lookup,
+	.unlink		= dlmfs_unlink,
+};
+
+/* this way we can restrict mkdir to only the toplevel of the fs. */
+static const struct inode_operations dlmfs_root_inode_operations = {
+	.lookup		= simple_lookup,
+	.mkdir		= dlmfs_mkdir,
+	.rmdir		= simple_rmdir,
+};
+
+static const struct super_operations dlmfs_ops = {
+	.statfs		= simple_statfs,
+	.alloc_inode	= dlmfs_alloc_inode,
+	.free_inode	= dlmfs_free_inode,
+	.evict_inode	= dlmfs_evict_inode,
+	.drop_inode	= generic_delete_inode,
+};
+
+static const struct inode_operations dlmfs_file_inode_operations = {
+	.getattr	= simple_getattr,
+	.setattr	= dlmfs_file_setattr,
+};
+
+static struct dentry *dlmfs_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
+{
+	return mount_nodev(fs_type, flags, data, dlmfs_fill_super);
+}
+
+static struct file_system_type dlmfs_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ocfs2_dlmfs",
+	.mount		= dlmfs_mount,
+	.kill_sb	= kill_litter_super,
+};
+MODULE_ALIAS_FS("ocfs2_dlmfs");
+
+static int __init init_dlmfs_fs(void)
+{
+	int status;
+	int cleanup_inode = 0, cleanup_worker = 0;
+
+	dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
+				sizeof(struct dlmfs_inode_private),
+				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
+					SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+				dlmfs_init_once);
+	if (!dlmfs_inode_cache) {
+		status = -ENOMEM;
+		goto bail;
+	}
+	cleanup_inode = 1;
+
+	user_dlm_worker = alloc_workqueue("user_dlm", WQ_MEM_RECLAIM, 0);
+	if (!user_dlm_worker) {
+		status = -ENOMEM;
+		goto bail;
+	}
+	cleanup_worker = 1;
+
+	user_dlm_set_locking_protocol();
+	status = register_filesystem(&dlmfs_fs_type);
+bail:
+	if (status) {
+		if (cleanup_inode)
+			kmem_cache_destroy(dlmfs_inode_cache);
+		if (cleanup_worker)
+			destroy_workqueue(user_dlm_worker);
+	} else
+		printk("OCFS2 User DLM kernel interface loaded\n");
+	return status;
+}
+
+static void __exit exit_dlmfs_fs(void)
+{
+	unregister_filesystem(&dlmfs_fs_type);
+
+	destroy_workqueue(user_dlm_worker);
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+	kmem_cache_destroy(dlmfs_inode_cache);
+
+}
+
+MODULE_AUTHOR("Oracle");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("OCFS2 DLM-Filesystem");
+
+module_init(init_dlmfs_fs)
+module_exit(exit_dlmfs_fs)