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, 725 insertions, 0 deletions

diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
new file mode 100644
index 000000000..0792fda49
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -0,0 +1,725 @@
+/*
+ * Driver giving user-space access to the kernel's xenbus connection
+ * to xenstore.
+ *
+ * Copyright (c) 2005, Christian Limpach
+ * Copyright (c) 2005, Rusty Russell, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Changes:
+ * 2008-10-07  Alex Zeffertt    Replaced /proc/xen/xenbus with xenfs filesystem
+ *                              and /proc/xen compatibility mount point.
+ *                              Turned xenfs into a loadable module.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/uio.h>
+#include <linux/notifier.h>
+#include <linux/wait.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/uaccess.h>
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/miscdevice.h>
+#include <linux/workqueue.h>
+
+#include <xen/xenbus.h>
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
+#include "xenbus.h"
+
+unsigned int xb_dev_generation_id;
+
+/*
+ * An element of a list of outstanding transactions, for which we're
+ * still waiting a reply.
+ */
+struct xenbus_transaction_holder {
+	struct list_head list;
+	struct xenbus_transaction handle;
+	unsigned int generation_id;
+};
+
+/*
+ * A buffer of data on the queue.
+ */
+struct read_buffer {
+	struct list_head list;
+	unsigned int cons;
+	unsigned int len;
+	char msg[];
+};
+
+struct xenbus_file_priv {
+	/*
+	 * msgbuffer_mutex is held while partial requests are built up
+	 * and complete requests are acted on.  It therefore protects
+	 * the "transactions" and "watches" lists, and the partial
+	 * request length and buffer.
+	 *
+	 * reply_mutex protects the reply being built up to return to
+	 * usermode.  It nests inside msgbuffer_mutex but may be held
+	 * alone during a watch callback.
+	 */
+	struct mutex msgbuffer_mutex;
+
+	/* In-progress transactions */
+	struct list_head transactions;
+
+	/* Active watches. */
+	struct list_head watches;
+
+	/* Partial request. */
+	unsigned int len;
+	union {
+		struct xsd_sockmsg msg;
+		char buffer[XENSTORE_PAYLOAD_MAX];
+	} u;
+
+	/* Response queue. */
+	struct mutex reply_mutex;
+	struct list_head read_buffers;
+	wait_queue_head_t read_waitq;
+
+	struct kref kref;
+
+	struct work_struct wq;
+};
+
+/* Read out any raw xenbus messages queued up. */
+static ssize_t xenbus_file_read(struct file *filp,
+			       char __user *ubuf,
+			       size_t len, loff_t *ppos)
+{
+	struct xenbus_file_priv *u = filp->private_data;
+	struct read_buffer *rb;
+	ssize_t i;
+	int ret;
+
+	mutex_lock(&u->reply_mutex);
+again:
+	while (list_empty(&u->read_buffers)) {
+		mutex_unlock(&u->reply_mutex);
+		if (filp->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		ret = wait_event_interruptible(u->read_waitq,
+					       !list_empty(&u->read_buffers));
+		if (ret)
+			return ret;
+		mutex_lock(&u->reply_mutex);
+	}
+
+	rb = list_entry(u->read_buffers.next, struct read_buffer, list);
+	i = 0;
+	while (i < len) {
+		size_t sz = min_t(size_t, len - i, rb->len - rb->cons);
+
+		ret = copy_to_user(ubuf + i, &rb->msg[rb->cons], sz);
+
+		i += sz - ret;
+		rb->cons += sz - ret;
+
+		if (ret != 0) {
+			if (i == 0)
+				i = -EFAULT;
+			goto out;
+		}
+
+		/* Clear out buffer if it has been consumed */
+		if (rb->cons == rb->len) {
+			list_del(&rb->list);
+			kfree(rb);
+			if (list_empty(&u->read_buffers))
+				break;
+			rb = list_entry(u->read_buffers.next,
+					struct read_buffer, list);
+		}
+	}
+	if (i == 0)
+		goto again;
+
+out:
+	mutex_unlock(&u->reply_mutex);
+	return i;
+}
+
+/*
+ * Add a buffer to the queue.  Caller must hold the appropriate lock
+ * if the queue is not local.  (Commonly the caller will build up
+ * multiple queued buffers on a temporary local list, and then add it
+ * to the appropriate list under lock once all the buffers have een
+ * successfully allocated.)
+ */
+static int queue_reply(struct list_head *queue, const void *data, size_t len)
+{
+	struct read_buffer *rb;
+
+	if (len == 0)
+		return 0;
+	if (len > XENSTORE_PAYLOAD_MAX)
+		return -EINVAL;
+
+	rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL);
+	if (rb == NULL)
+		return -ENOMEM;
+
+	rb->cons = 0;
+	rb->len = len;
+
+	memcpy(rb->msg, data, len);
+
+	list_add_tail(&rb->list, queue);
+	return 0;
+}
+
+/*
+ * Free all the read_buffer s on a list.
+ * Caller must have sole reference to list.
+ */
+static void queue_cleanup(struct list_head *list)
+{
+	struct read_buffer *rb;
+
+	while (!list_empty(list)) {
+		rb = list_entry(list->next, struct read_buffer, list);
+		list_del(list->next);
+		kfree(rb);
+	}
+}
+
+struct watch_adapter {
+	struct list_head list;
+	struct xenbus_watch watch;
+	struct xenbus_file_priv *dev_data;
+	char *token;
+};
+
+static void free_watch_adapter(struct watch_adapter *watch)
+{
+	kfree(watch->watch.node);
+	kfree(watch->token);
+	kfree(watch);
+}
+
+static struct watch_adapter *alloc_watch_adapter(const char *path,
+						 const char *token)
+{
+	struct watch_adapter *watch;
+
+	watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+	if (watch == NULL)
+		goto out_fail;
+
+	watch->watch.node = kstrdup(path, GFP_KERNEL);
+	if (watch->watch.node == NULL)
+		goto out_free;
+
+	watch->token = kstrdup(token, GFP_KERNEL);
+	if (watch->token == NULL)
+		goto out_free;
+
+	return watch;
+
+out_free:
+	free_watch_adapter(watch);
+
+out_fail:
+	return NULL;
+}
+
+static void watch_fired(struct xenbus_watch *watch,
+			const char *path,
+			const char *token)
+{
+	struct watch_adapter *adap;
+	struct xsd_sockmsg hdr;
+	const char *token_caller;
+	int path_len, tok_len, body_len;
+	int ret;
+	LIST_HEAD(staging_q);
+
+	adap = container_of(watch, struct watch_adapter, watch);
+
+	token_caller = adap->token;
+
+	path_len = strlen(path) + 1;
+	tok_len = strlen(token_caller) + 1;
+	body_len = path_len + tok_len;
+
+	hdr.type = XS_WATCH_EVENT;
+	hdr.len = body_len;
+
+	mutex_lock(&adap->dev_data->reply_mutex);
+
+	ret = queue_reply(&staging_q, &hdr, sizeof(hdr));
+	if (!ret)
+		ret = queue_reply(&staging_q, path, path_len);
+	if (!ret)
+		ret = queue_reply(&staging_q, token_caller, tok_len);
+
+	if (!ret) {
+		/* success: pass reply list onto watcher */
+		list_splice_tail(&staging_q, &adap->dev_data->read_buffers);
+		wake_up(&adap->dev_data->read_waitq);
+	} else
+		queue_cleanup(&staging_q);
+
+	mutex_unlock(&adap->dev_data->reply_mutex);
+}
+
+static void xenbus_worker(struct work_struct *wq)
+{
+	struct xenbus_file_priv *u;
+	struct xenbus_transaction_holder *trans, *tmp;
+	struct watch_adapter *watch, *tmp_watch;
+	struct read_buffer *rb, *tmp_rb;
+
+	u = container_of(wq, struct xenbus_file_priv, wq);
+
+	/*
+	 * No need for locking here because there are no other users,
+	 * by definition.
+	 */
+
+	list_for_each_entry_safe(trans, tmp, &u->transactions, list) {
+		xenbus_transaction_end(trans->handle, 1);
+		list_del(&trans->list);
+		kfree(trans);
+	}
+
+	list_for_each_entry_safe(watch, tmp_watch, &u->watches, list) {
+		unregister_xenbus_watch(&watch->watch);
+		list_del(&watch->list);
+		free_watch_adapter(watch);
+	}
+
+	list_for_each_entry_safe(rb, tmp_rb, &u->read_buffers, list) {
+		list_del(&rb->list);
+		kfree(rb);
+	}
+	kfree(u);
+}
+
+static void xenbus_file_free(struct kref *kref)
+{
+	struct xenbus_file_priv *u;
+
+	/*
+	 * We might be called in xenbus_thread().
+	 * Use workqueue to avoid deadlock.
+	 */
+	u = container_of(kref, struct xenbus_file_priv, kref);
+	schedule_work(&u->wq);
+}
+
+static struct xenbus_transaction_holder *xenbus_get_transaction(
+	struct xenbus_file_priv *u, uint32_t tx_id)
+{
+	struct xenbus_transaction_holder *trans;
+
+	list_for_each_entry(trans, &u->transactions, list)
+		if (trans->handle.id == tx_id)
+			return trans;
+
+	return NULL;
+}
+
+void xenbus_dev_queue_reply(struct xb_req_data *req)
+{
+	struct xenbus_file_priv *u = req->par;
+	struct xenbus_transaction_holder *trans = NULL;
+	int rc;
+	LIST_HEAD(staging_q);
+
+	xs_request_exit(req);
+
+	mutex_lock(&u->msgbuffer_mutex);
+
+	if (req->type == XS_TRANSACTION_START) {
+		trans = xenbus_get_transaction(u, 0);
+		if (WARN_ON(!trans))
+			goto out;
+		if (req->msg.type == XS_ERROR) {
+			list_del(&trans->list);
+			kfree(trans);
+		} else {
+			rc = kstrtou32(req->body, 10, &trans->handle.id);
+			if (WARN_ON(rc))
+				goto out;
+		}
+	} else if (req->type == XS_TRANSACTION_END) {
+		trans = xenbus_get_transaction(u, req->msg.tx_id);
+		if (WARN_ON(!trans))
+			goto out;
+		list_del(&trans->list);
+		kfree(trans);
+	}
+
+	mutex_unlock(&u->msgbuffer_mutex);
+
+	mutex_lock(&u->reply_mutex);
+	rc = queue_reply(&staging_q, &req->msg, sizeof(req->msg));
+	if (!rc)
+		rc = queue_reply(&staging_q, req->body, req->msg.len);
+	if (!rc) {
+		list_splice_tail(&staging_q, &u->read_buffers);
+		wake_up(&u->read_waitq);
+	} else {
+		queue_cleanup(&staging_q);
+	}
+	mutex_unlock(&u->reply_mutex);
+
+	kfree(req->body);
+	kfree(req);
+
+	kref_put(&u->kref, xenbus_file_free);
+
+	return;
+
+ out:
+	mutex_unlock(&u->msgbuffer_mutex);
+}
+
+static int xenbus_command_reply(struct xenbus_file_priv *u,
+				unsigned int msg_type, const char *reply)
+{
+	struct {
+		struct xsd_sockmsg hdr;
+		char body[16];
+	} msg;
+	int rc;
+
+	msg.hdr = u->u.msg;
+	msg.hdr.type = msg_type;
+	msg.hdr.len = strlen(reply) + 1;
+	if (msg.hdr.len > sizeof(msg.body))
+		return -E2BIG;
+	memcpy(&msg.body, reply, msg.hdr.len);
+
+	mutex_lock(&u->reply_mutex);
+	rc = queue_reply(&u->read_buffers, &msg, sizeof(msg.hdr) + msg.hdr.len);
+	wake_up(&u->read_waitq);
+	mutex_unlock(&u->reply_mutex);
+
+	if (!rc)
+		kref_put(&u->kref, xenbus_file_free);
+
+	return rc;
+}
+
+static int xenbus_write_transaction(unsigned msg_type,
+				    struct xenbus_file_priv *u)
+{
+	int rc;
+	struct xenbus_transaction_holder *trans = NULL;
+	struct {
+		struct xsd_sockmsg hdr;
+		char body[];
+	} *msg = (void *)u->u.buffer;
+
+	if (msg_type == XS_TRANSACTION_START) {
+		trans = kzalloc(sizeof(*trans), GFP_KERNEL);
+		if (!trans) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		trans->generation_id = xb_dev_generation_id;
+		list_add(&trans->list, &u->transactions);
+	} else if (msg->hdr.tx_id != 0 &&
+		   !xenbus_get_transaction(u, msg->hdr.tx_id))
+		return xenbus_command_reply(u, XS_ERROR, "ENOENT");
+	else if (msg_type == XS_TRANSACTION_END &&
+		 !(msg->hdr.len == 2 &&
+		   (!strcmp(msg->body, "T") || !strcmp(msg->body, "F"))))
+		return xenbus_command_reply(u, XS_ERROR, "EINVAL");
+	else if (msg_type == XS_TRANSACTION_END) {
+		trans = xenbus_get_transaction(u, msg->hdr.tx_id);
+		if (trans && trans->generation_id != xb_dev_generation_id) {
+			list_del(&trans->list);
+			kfree(trans);
+			if (!strcmp(msg->body, "T"))
+				return xenbus_command_reply(u, XS_ERROR,
+							    "EAGAIN");
+			else
+				return xenbus_command_reply(u,
+							    XS_TRANSACTION_END,
+							    "OK");
+		}
+	}
+
+	rc = xenbus_dev_request_and_reply(&msg->hdr, u);
+	if (rc && trans) {
+		list_del(&trans->list);
+		kfree(trans);
+	}
+
+out:
+	return rc;
+}
+
+static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u)
+{
+	struct watch_adapter *watch;
+	char *path, *token;
+	int err, rc;
+
+	path = u->u.buffer + sizeof(u->u.msg);
+	token = memchr(path, 0, u->u.msg.len);
+	if (token == NULL) {
+		rc = xenbus_command_reply(u, XS_ERROR, "EINVAL");
+		goto out;
+	}
+	token++;
+	if (memchr(token, 0, u->u.msg.len - (token - path)) == NULL) {
+		rc = xenbus_command_reply(u, XS_ERROR, "EINVAL");
+		goto out;
+	}
+
+	if (msg_type == XS_WATCH) {
+		watch = alloc_watch_adapter(path, token);
+		if (watch == NULL) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		watch->watch.callback = watch_fired;
+		watch->dev_data = u;
+
+		err = register_xenbus_watch(&watch->watch);
+		if (err) {
+			free_watch_adapter(watch);
+			rc = err;
+			goto out;
+		}
+		list_add(&watch->list, &u->watches);
+	} else {
+		list_for_each_entry(watch, &u->watches, list) {
+			if (!strcmp(watch->token, token) &&
+			    !strcmp(watch->watch.node, path)) {
+				unregister_xenbus_watch(&watch->watch);
+				list_del(&watch->list);
+				free_watch_adapter(watch);
+				break;
+			}
+		}
+	}
+
+	/* Success.  Synthesize a reply to say all is OK. */
+	rc = xenbus_command_reply(u, msg_type, "OK");
+
+out:
+	return rc;
+}
+
+static ssize_t xenbus_file_write(struct file *filp,
+				const char __user *ubuf,
+				size_t len, loff_t *ppos)
+{
+	struct xenbus_file_priv *u = filp->private_data;
+	uint32_t msg_type;
+	int rc = len;
+	int ret;
+
+	/*
+	 * We're expecting usermode to be writing properly formed
+	 * xenbus messages.  If they write an incomplete message we
+	 * buffer it up.  Once it is complete, we act on it.
+	 */
+
+	/*
+	 * Make sure concurrent writers can't stomp all over each
+	 * other's messages and make a mess of our partial message
+	 * buffer.  We don't make any attemppt to stop multiple
+	 * writers from making a mess of each other's incomplete
+	 * messages; we're just trying to guarantee our own internal
+	 * consistency and make sure that single writes are handled
+	 * atomically.
+	 */
+	mutex_lock(&u->msgbuffer_mutex);
+
+	/* Get this out of the way early to avoid confusion */
+	if (len == 0)
+		goto out;
+
+	/* Can't write a xenbus message larger we can buffer */
+	if (len > sizeof(u->u.buffer) - u->len) {
+		/* On error, dump existing buffer */
+		u->len = 0;
+		rc = -EINVAL;
+		goto out;
+	}
+
+	ret = copy_from_user(u->u.buffer + u->len, ubuf, len);
+
+	if (ret != 0) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	/* Deal with a partial copy. */
+	len -= ret;
+	rc = len;
+
+	u->len += len;
+
+	/* Return if we haven't got a full message yet */
+	if (u->len < sizeof(u->u.msg))
+		goto out;	/* not even the header yet */
+
+	/* If we're expecting a message that's larger than we can
+	   possibly send, dump what we have and return an error. */
+	if ((sizeof(u->u.msg) + u->u.msg.len) > sizeof(u->u.buffer)) {
+		rc = -E2BIG;
+		u->len = 0;
+		goto out;
+	}
+
+	if (u->len < (sizeof(u->u.msg) + u->u.msg.len))
+		goto out;	/* incomplete data portion */
+
+	/*
+	 * OK, now we have a complete message.  Do something with it.
+	 */
+
+	kref_get(&u->kref);
+
+	msg_type = u->u.msg.type;
+
+	switch (msg_type) {
+	case XS_WATCH:
+	case XS_UNWATCH:
+		/* (Un)Ask for some path to be watched for changes */
+		ret = xenbus_write_watch(msg_type, u);
+		break;
+
+	default:
+		/* Send out a transaction */
+		ret = xenbus_write_transaction(msg_type, u);
+		break;
+	}
+	if (ret != 0) {
+		rc = ret;
+		kref_put(&u->kref, xenbus_file_free);
+	}
+
+	/* Buffered message consumed */
+	u->len = 0;
+
+ out:
+	mutex_unlock(&u->msgbuffer_mutex);
+	return rc;
+}
+
+static int xenbus_file_open(struct inode *inode, struct file *filp)
+{
+	struct xenbus_file_priv *u;
+
+	if (xen_store_evtchn == 0)
+		return -ENOENT;
+
+	stream_open(inode, filp);
+
+	u = kzalloc(sizeof(*u), GFP_KERNEL);
+	if (u == NULL)
+		return -ENOMEM;
+
+	kref_init(&u->kref);
+
+	INIT_LIST_HEAD(&u->transactions);
+	INIT_LIST_HEAD(&u->watches);
+	INIT_LIST_HEAD(&u->read_buffers);
+	init_waitqueue_head(&u->read_waitq);
+	INIT_WORK(&u->wq, xenbus_worker);
+
+	mutex_init(&u->reply_mutex);
+	mutex_init(&u->msgbuffer_mutex);
+
+	filp->private_data = u;
+
+	return 0;
+}
+
+static int xenbus_file_release(struct inode *inode, struct file *filp)
+{
+	struct xenbus_file_priv *u = filp->private_data;
+
+	kref_put(&u->kref, xenbus_file_free);
+
+	return 0;
+}
+
+static __poll_t xenbus_file_poll(struct file *file, poll_table *wait)
+{
+	struct xenbus_file_priv *u = file->private_data;
+
+	poll_wait(file, &u->read_waitq, wait);
+	if (!list_empty(&u->read_buffers))
+		return EPOLLIN | EPOLLRDNORM;
+	return 0;
+}
+
+const struct file_operations xen_xenbus_fops = {
+	.read = xenbus_file_read,
+	.write = xenbus_file_write,
+	.open = xenbus_file_open,
+	.release = xenbus_file_release,
+	.poll = xenbus_file_poll,
+	.llseek = no_llseek,
+};
+EXPORT_SYMBOL_GPL(xen_xenbus_fops);
+
+static struct miscdevice xenbus_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "xen/xenbus",
+	.fops = &xen_xenbus_fops,
+};
+
+static int __init xenbus_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	err = misc_register(&xenbus_dev);
+	if (err)
+		pr_err("Could not register xenbus frontend device\n");
+	return err;
+}
+device_initcall(xenbus_init);