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, 717 insertions, 0 deletions

diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c
new file mode 100644
index 000000000..b0d671db1
--- /dev/null
+++ b/drivers/firewire/nosy.c
@@ -0,0 +1,717 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * nosy - Snoop mode driver for TI PCILynx 1394 controllers
+ * Copyright (C) 2002-2007 Kristian Høgsberg
+ */
+
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/poll.h>
+#include <linux/sched.h> /* required for linux/wait.h */
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/time64.h>
+#include <linux/timex.h>
+#include <linux/uaccess.h>
+#include <linux/wait.h>
+#include <linux/dma-mapping.h>
+#include <linux/atomic.h>
+#include <asm/byteorder.h>
+
+#include "nosy.h"
+#include "nosy-user.h"
+
+#define TCODE_PHY_PACKET		0x10
+#define PCI_DEVICE_ID_TI_PCILYNX	0x8000
+
+static char driver_name[] = KBUILD_MODNAME;
+
+/* this is the physical layout of a PCL, its size is 128 bytes */
+struct pcl {
+	__le32 next;
+	__le32 async_error_next;
+	u32 user_data;
+	__le32 pcl_status;
+	__le32 remaining_transfer_count;
+	__le32 next_data_buffer;
+	struct {
+		__le32 control;
+		__le32 pointer;
+	} buffer[13];
+};
+
+struct packet {
+	unsigned int length;
+	char data[];
+};
+
+struct packet_buffer {
+	char *data;
+	size_t capacity;
+	long total_packet_count, lost_packet_count;
+	atomic_t size;
+	struct packet *head, *tail;
+	wait_queue_head_t wait;
+};
+
+struct pcilynx {
+	struct pci_dev *pci_device;
+	__iomem char *registers;
+
+	struct pcl *rcv_start_pcl, *rcv_pcl;
+	__le32 *rcv_buffer;
+
+	dma_addr_t rcv_start_pcl_bus, rcv_pcl_bus, rcv_buffer_bus;
+
+	spinlock_t client_list_lock;
+	struct list_head client_list;
+
+	struct miscdevice misc;
+	struct list_head link;
+	struct kref kref;
+};
+
+static inline struct pcilynx *
+lynx_get(struct pcilynx *lynx)
+{
+	kref_get(&lynx->kref);
+
+	return lynx;
+}
+
+static void
+lynx_release(struct kref *kref)
+{
+	kfree(container_of(kref, struct pcilynx, kref));
+}
+
+static inline void
+lynx_put(struct pcilynx *lynx)
+{
+	kref_put(&lynx->kref, lynx_release);
+}
+
+struct client {
+	struct pcilynx *lynx;
+	u32 tcode_mask;
+	struct packet_buffer buffer;
+	struct list_head link;
+};
+
+static DEFINE_MUTEX(card_mutex);
+static LIST_HEAD(card_list);
+
+static int
+packet_buffer_init(struct packet_buffer *buffer, size_t capacity)
+{
+	buffer->data = kmalloc(capacity, GFP_KERNEL);
+	if (buffer->data == NULL)
+		return -ENOMEM;
+	buffer->head = (struct packet *) buffer->data;
+	buffer->tail = (struct packet *) buffer->data;
+	buffer->capacity = capacity;
+	buffer->lost_packet_count = 0;
+	atomic_set(&buffer->size, 0);
+	init_waitqueue_head(&buffer->wait);
+
+	return 0;
+}
+
+static void
+packet_buffer_destroy(struct packet_buffer *buffer)
+{
+	kfree(buffer->data);
+}
+
+static int
+packet_buffer_get(struct client *client, char __user *data, size_t user_length)
+{
+	struct packet_buffer *buffer = &client->buffer;
+	size_t length;
+	char *end;
+
+	if (wait_event_interruptible(buffer->wait,
+				     atomic_read(&buffer->size) > 0) ||
+				     list_empty(&client->lynx->link))
+		return -ERESTARTSYS;
+
+	if (atomic_read(&buffer->size) == 0)
+		return -ENODEV;
+
+	/* FIXME: Check length <= user_length. */
+
+	end = buffer->data + buffer->capacity;
+	length = buffer->head->length;
+
+	if (&buffer->head->data[length] < end) {
+		if (copy_to_user(data, buffer->head->data, length))
+			return -EFAULT;
+		buffer->head = (struct packet *) &buffer->head->data[length];
+	} else {
+		size_t split = end - buffer->head->data;
+
+		if (copy_to_user(data, buffer->head->data, split))
+			return -EFAULT;
+		if (copy_to_user(data + split, buffer->data, length - split))
+			return -EFAULT;
+		buffer->head = (struct packet *) &buffer->data[length - split];
+	}
+
+	/*
+	 * Decrease buffer->size as the last thing, since this is what
+	 * keeps the interrupt from overwriting the packet we are
+	 * retrieving from the buffer.
+	 */
+	atomic_sub(sizeof(struct packet) + length, &buffer->size);
+
+	return length;
+}
+
+static void
+packet_buffer_put(struct packet_buffer *buffer, void *data, size_t length)
+{
+	char *end;
+
+	buffer->total_packet_count++;
+
+	if (buffer->capacity <
+	    atomic_read(&buffer->size) + sizeof(struct packet) + length) {
+		buffer->lost_packet_count++;
+		return;
+	}
+
+	end = buffer->data + buffer->capacity;
+	buffer->tail->length = length;
+
+	if (&buffer->tail->data[length] < end) {
+		memcpy(buffer->tail->data, data, length);
+		buffer->tail = (struct packet *) &buffer->tail->data[length];
+	} else {
+		size_t split = end - buffer->tail->data;
+
+		memcpy(buffer->tail->data, data, split);
+		memcpy(buffer->data, data + split, length - split);
+		buffer->tail = (struct packet *) &buffer->data[length - split];
+	}
+
+	/* Finally, adjust buffer size and wake up userspace reader. */
+
+	atomic_add(sizeof(struct packet) + length, &buffer->size);
+	wake_up_interruptible(&buffer->wait);
+}
+
+static inline void
+reg_write(struct pcilynx *lynx, int offset, u32 data)
+{
+	writel(data, lynx->registers + offset);
+}
+
+static inline u32
+reg_read(struct pcilynx *lynx, int offset)
+{
+	return readl(lynx->registers + offset);
+}
+
+static inline void
+reg_set_bits(struct pcilynx *lynx, int offset, u32 mask)
+{
+	reg_write(lynx, offset, (reg_read(lynx, offset) | mask));
+}
+
+/*
+ * Maybe the pcl programs could be set up to just append data instead
+ * of using a whole packet.
+ */
+static inline void
+run_pcl(struct pcilynx *lynx, dma_addr_t pcl_bus,
+			   int dmachan)
+{
+	reg_write(lynx, DMA0_CURRENT_PCL + dmachan * 0x20, pcl_bus);
+	reg_write(lynx, DMA0_CHAN_CTRL + dmachan * 0x20,
+		  DMA_CHAN_CTRL_ENABLE | DMA_CHAN_CTRL_LINK);
+}
+
+static int
+set_phy_reg(struct pcilynx *lynx, int addr, int val)
+{
+	if (addr > 15) {
+		dev_err(&lynx->pci_device->dev,
+			"PHY register address %d out of range\n", addr);
+		return -1;
+	}
+	if (val > 0xff) {
+		dev_err(&lynx->pci_device->dev,
+			"PHY register value %d out of range\n", val);
+		return -1;
+	}
+	reg_write(lynx, LINK_PHY, LINK_PHY_WRITE |
+		  LINK_PHY_ADDR(addr) | LINK_PHY_WDATA(val));
+
+	return 0;
+}
+
+static int
+nosy_open(struct inode *inode, struct file *file)
+{
+	int minor = iminor(inode);
+	struct client *client;
+	struct pcilynx *tmp, *lynx = NULL;
+
+	mutex_lock(&card_mutex);
+	list_for_each_entry(tmp, &card_list, link)
+		if (tmp->misc.minor == minor) {
+			lynx = lynx_get(tmp);
+			break;
+		}
+	mutex_unlock(&card_mutex);
+	if (lynx == NULL)
+		return -ENODEV;
+
+	client = kmalloc(sizeof *client, GFP_KERNEL);
+	if (client == NULL)
+		goto fail;
+
+	client->tcode_mask = ~0;
+	client->lynx = lynx;
+	INIT_LIST_HEAD(&client->link);
+
+	if (packet_buffer_init(&client->buffer, 128 * 1024) < 0)
+		goto fail;
+
+	file->private_data = client;
+
+	return stream_open(inode, file);
+fail:
+	kfree(client);
+	lynx_put(lynx);
+
+	return -ENOMEM;
+}
+
+static int
+nosy_release(struct inode *inode, struct file *file)
+{
+	struct client *client = file->private_data;
+	struct pcilynx *lynx = client->lynx;
+
+	spin_lock_irq(&lynx->client_list_lock);
+	list_del_init(&client->link);
+	spin_unlock_irq(&lynx->client_list_lock);
+
+	packet_buffer_destroy(&client->buffer);
+	kfree(client);
+	lynx_put(lynx);
+
+	return 0;
+}
+
+static __poll_t
+nosy_poll(struct file *file, poll_table *pt)
+{
+	struct client *client = file->private_data;
+	__poll_t ret = 0;
+
+	poll_wait(file, &client->buffer.wait, pt);
+
+	if (atomic_read(&client->buffer.size) > 0)
+		ret = EPOLLIN | EPOLLRDNORM;
+
+	if (list_empty(&client->lynx->link))
+		ret |= EPOLLHUP;
+
+	return ret;
+}
+
+static ssize_t
+nosy_read(struct file *file, char __user *buffer, size_t count, loff_t *offset)
+{
+	struct client *client = file->private_data;
+
+	return packet_buffer_get(client, buffer, count);
+}
+
+static long
+nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct client *client = file->private_data;
+	spinlock_t *client_list_lock = &client->lynx->client_list_lock;
+	struct nosy_stats stats;
+	int ret;
+
+	switch (cmd) {
+	case NOSY_IOC_GET_STATS:
+		spin_lock_irq(client_list_lock);
+		stats.total_packet_count = client->buffer.total_packet_count;
+		stats.lost_packet_count  = client->buffer.lost_packet_count;
+		spin_unlock_irq(client_list_lock);
+
+		if (copy_to_user((void __user *) arg, &stats, sizeof stats))
+			return -EFAULT;
+		else
+			return 0;
+
+	case NOSY_IOC_START:
+		ret = -EBUSY;
+		spin_lock_irq(client_list_lock);
+		if (list_empty(&client->link)) {
+			list_add_tail(&client->link, &client->lynx->client_list);
+			ret = 0;
+		}
+		spin_unlock_irq(client_list_lock);
+
+		return ret;
+
+	case NOSY_IOC_STOP:
+		spin_lock_irq(client_list_lock);
+		list_del_init(&client->link);
+		spin_unlock_irq(client_list_lock);
+
+		return 0;
+
+	case NOSY_IOC_FILTER:
+		spin_lock_irq(client_list_lock);
+		client->tcode_mask = arg;
+		spin_unlock_irq(client_list_lock);
+
+		return 0;
+
+	default:
+		return -EINVAL;
+		/* Flush buffer, configure filter. */
+	}
+}
+
+static const struct file_operations nosy_ops = {
+	.owner =		THIS_MODULE,
+	.read =			nosy_read,
+	.unlocked_ioctl =	nosy_ioctl,
+	.poll =			nosy_poll,
+	.open =			nosy_open,
+	.release =		nosy_release,
+};
+
+#define PHY_PACKET_SIZE 12 /* 1 payload, 1 inverse, 1 ack = 3 quadlets */
+
+static void
+packet_irq_handler(struct pcilynx *lynx)
+{
+	struct client *client;
+	u32 tcode_mask, tcode, timestamp;
+	size_t length;
+	struct timespec64 ts64;
+
+	/* FIXME: Also report rcv_speed. */
+
+	length = __le32_to_cpu(lynx->rcv_pcl->pcl_status) & 0x00001fff;
+	tcode  = __le32_to_cpu(lynx->rcv_buffer[1]) >> 4 & 0xf;
+
+	ktime_get_real_ts64(&ts64);
+	timestamp = ts64.tv_nsec / NSEC_PER_USEC;
+	lynx->rcv_buffer[0] = (__force __le32)timestamp;
+
+	if (length == PHY_PACKET_SIZE)
+		tcode_mask = 1 << TCODE_PHY_PACKET;
+	else
+		tcode_mask = 1 << tcode;
+
+	spin_lock(&lynx->client_list_lock);
+
+	list_for_each_entry(client, &lynx->client_list, link)
+		if (client->tcode_mask & tcode_mask)
+			packet_buffer_put(&client->buffer,
+					  lynx->rcv_buffer, length + 4);
+
+	spin_unlock(&lynx->client_list_lock);
+}
+
+static void
+bus_reset_irq_handler(struct pcilynx *lynx)
+{
+	struct client *client;
+	struct timespec64 ts64;
+	u32    timestamp;
+
+	ktime_get_real_ts64(&ts64);
+	timestamp = ts64.tv_nsec / NSEC_PER_USEC;
+
+	spin_lock(&lynx->client_list_lock);
+
+	list_for_each_entry(client, &lynx->client_list, link)
+		packet_buffer_put(&client->buffer, &timestamp, 4);
+
+	spin_unlock(&lynx->client_list_lock);
+}
+
+static irqreturn_t
+irq_handler(int irq, void *device)
+{
+	struct pcilynx *lynx = device;
+	u32 pci_int_status;
+
+	pci_int_status = reg_read(lynx, PCI_INT_STATUS);
+
+	if (pci_int_status == ~0)
+		/* Card was ejected. */
+		return IRQ_NONE;
+
+	if ((pci_int_status & PCI_INT_INT_PEND) == 0)
+		/* Not our interrupt, bail out quickly. */
+		return IRQ_NONE;
+
+	if ((pci_int_status & PCI_INT_P1394_INT) != 0) {
+		u32 link_int_status;
+
+		link_int_status = reg_read(lynx, LINK_INT_STATUS);
+		reg_write(lynx, LINK_INT_STATUS, link_int_status);
+
+		if ((link_int_status & LINK_INT_PHY_BUSRESET) > 0)
+			bus_reset_irq_handler(lynx);
+	}
+
+	/* Clear the PCI_INT_STATUS register only after clearing the
+	 * LINK_INT_STATUS register; otherwise the PCI_INT_P1394 will
+	 * be set again immediately. */
+
+	reg_write(lynx, PCI_INT_STATUS, pci_int_status);
+
+	if ((pci_int_status & PCI_INT_DMA0_HLT) > 0) {
+		packet_irq_handler(lynx);
+		run_pcl(lynx, lynx->rcv_start_pcl_bus, 0);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void
+remove_card(struct pci_dev *dev)
+{
+	struct pcilynx *lynx = pci_get_drvdata(dev);
+	struct client *client;
+
+	mutex_lock(&card_mutex);
+	list_del_init(&lynx->link);
+	misc_deregister(&lynx->misc);
+	mutex_unlock(&card_mutex);
+
+	reg_write(lynx, PCI_INT_ENABLE, 0);
+	free_irq(lynx->pci_device->irq, lynx);
+
+	spin_lock_irq(&lynx->client_list_lock);
+	list_for_each_entry(client, &lynx->client_list, link)
+		wake_up_interruptible(&client->buffer.wait);
+	spin_unlock_irq(&lynx->client_list_lock);
+
+	dma_free_coherent(&lynx->pci_device->dev, sizeof(struct pcl),
+			  lynx->rcv_start_pcl, lynx->rcv_start_pcl_bus);
+	dma_free_coherent(&lynx->pci_device->dev, sizeof(struct pcl),
+			  lynx->rcv_pcl, lynx->rcv_pcl_bus);
+	dma_free_coherent(&lynx->pci_device->dev, PAGE_SIZE, lynx->rcv_buffer,
+			  lynx->rcv_buffer_bus);
+
+	iounmap(lynx->registers);
+	pci_disable_device(dev);
+	lynx_put(lynx);
+}
+
+#define RCV_BUFFER_SIZE (16 * 1024)
+
+static int
+add_card(struct pci_dev *dev, const struct pci_device_id *unused)
+{
+	struct pcilynx *lynx;
+	u32 p, end;
+	int ret, i;
+
+	if (dma_set_mask(&dev->dev, DMA_BIT_MASK(32))) {
+		dev_err(&dev->dev,
+		    "DMA address limits not supported for PCILynx hardware\n");
+		return -ENXIO;
+	}
+	if (pci_enable_device(dev)) {
+		dev_err(&dev->dev, "Failed to enable PCILynx hardware\n");
+		return -ENXIO;
+	}
+	pci_set_master(dev);
+
+	lynx = kzalloc(sizeof *lynx, GFP_KERNEL);
+	if (lynx == NULL) {
+		dev_err(&dev->dev, "Failed to allocate control structure\n");
+		ret = -ENOMEM;
+		goto fail_disable;
+	}
+	lynx->pci_device = dev;
+	pci_set_drvdata(dev, lynx);
+
+	spin_lock_init(&lynx->client_list_lock);
+	INIT_LIST_HEAD(&lynx->client_list);
+	kref_init(&lynx->kref);
+
+	lynx->registers = ioremap(pci_resource_start(dev, 0),
+					  PCILYNX_MAX_REGISTER);
+	if (lynx->registers == NULL) {
+		dev_err(&dev->dev, "Failed to map registers\n");
+		ret = -ENOMEM;
+		goto fail_deallocate_lynx;
+	}
+
+	lynx->rcv_start_pcl = dma_alloc_coherent(&lynx->pci_device->dev,
+						 sizeof(struct pcl),
+						 &lynx->rcv_start_pcl_bus,
+						 GFP_KERNEL);
+	lynx->rcv_pcl = dma_alloc_coherent(&lynx->pci_device->dev,
+					   sizeof(struct pcl),
+					   &lynx->rcv_pcl_bus, GFP_KERNEL);
+	lynx->rcv_buffer = dma_alloc_coherent(&lynx->pci_device->dev,
+					      RCV_BUFFER_SIZE,
+					      &lynx->rcv_buffer_bus, GFP_KERNEL);
+	if (lynx->rcv_start_pcl == NULL ||
+	    lynx->rcv_pcl == NULL ||
+	    lynx->rcv_buffer == NULL) {
+		dev_err(&dev->dev, "Failed to allocate receive buffer\n");
+		ret = -ENOMEM;
+		goto fail_deallocate_buffers;
+	}
+	lynx->rcv_start_pcl->next	= cpu_to_le32(lynx->rcv_pcl_bus);
+	lynx->rcv_pcl->next		= cpu_to_le32(PCL_NEXT_INVALID);
+	lynx->rcv_pcl->async_error_next	= cpu_to_le32(PCL_NEXT_INVALID);
+
+	lynx->rcv_pcl->buffer[0].control =
+			cpu_to_le32(PCL_CMD_RCV | PCL_BIGENDIAN | 2044);
+	lynx->rcv_pcl->buffer[0].pointer =
+			cpu_to_le32(lynx->rcv_buffer_bus + 4);
+	p = lynx->rcv_buffer_bus + 2048;
+	end = lynx->rcv_buffer_bus + RCV_BUFFER_SIZE;
+	for (i = 1; p < end; i++, p += 2048) {
+		lynx->rcv_pcl->buffer[i].control =
+			cpu_to_le32(PCL_CMD_RCV | PCL_BIGENDIAN | 2048);
+		lynx->rcv_pcl->buffer[i].pointer = cpu_to_le32(p);
+	}
+	lynx->rcv_pcl->buffer[i - 1].control |= cpu_to_le32(PCL_LAST_BUFF);
+
+	reg_set_bits(lynx, MISC_CONTROL, MISC_CONTROL_SWRESET);
+	/* Fix buggy cards with autoboot pin not tied low: */
+	reg_write(lynx, DMA0_CHAN_CTRL, 0);
+	reg_write(lynx, DMA_GLOBAL_REGISTER, 0x00 << 24);
+
+#if 0
+	/* now, looking for PHY register set */
+	if ((get_phy_reg(lynx, 2) & 0xe0) == 0xe0) {
+		lynx->phyic.reg_1394a = 1;
+		PRINT(KERN_INFO, lynx->id,
+		      "found 1394a conform PHY (using extended register set)");
+		lynx->phyic.vendor = get_phy_vendorid(lynx);
+		lynx->phyic.product = get_phy_productid(lynx);
+	} else {
+		lynx->phyic.reg_1394a = 0;
+		PRINT(KERN_INFO, lynx->id, "found old 1394 PHY");
+	}
+#endif
+
+	/* Setup the general receive FIFO max size. */
+	reg_write(lynx, FIFO_SIZES, 255);
+
+	reg_set_bits(lynx, PCI_INT_ENABLE, PCI_INT_DMA_ALL);
+
+	reg_write(lynx, LINK_INT_ENABLE,
+		  LINK_INT_PHY_TIME_OUT | LINK_INT_PHY_REG_RCVD |
+		  LINK_INT_PHY_BUSRESET | LINK_INT_IT_STUCK |
+		  LINK_INT_AT_STUCK | LINK_INT_SNTRJ |
+		  LINK_INT_TC_ERR | LINK_INT_GRF_OVER_FLOW |
+		  LINK_INT_ITF_UNDER_FLOW | LINK_INT_ATF_UNDER_FLOW);
+
+	/* Disable the L flag in self ID packets. */
+	set_phy_reg(lynx, 4, 0);
+
+	/* Put this baby into snoop mode */
+	reg_set_bits(lynx, LINK_CONTROL, LINK_CONTROL_SNOOP_ENABLE);
+
+	run_pcl(lynx, lynx->rcv_start_pcl_bus, 0);
+
+	if (request_irq(dev->irq, irq_handler, IRQF_SHARED,
+			driver_name, lynx)) {
+		dev_err(&dev->dev,
+			"Failed to allocate shared interrupt %d\n", dev->irq);
+		ret = -EIO;
+		goto fail_deallocate_buffers;
+	}
+
+	lynx->misc.parent = &dev->dev;
+	lynx->misc.minor = MISC_DYNAMIC_MINOR;
+	lynx->misc.name = "nosy";
+	lynx->misc.fops = &nosy_ops;
+
+	mutex_lock(&card_mutex);
+	ret = misc_register(&lynx->misc);
+	if (ret) {
+		dev_err(&dev->dev, "Failed to register misc char device\n");
+		mutex_unlock(&card_mutex);
+		goto fail_free_irq;
+	}
+	list_add_tail(&lynx->link, &card_list);
+	mutex_unlock(&card_mutex);
+
+	dev_info(&dev->dev,
+		 "Initialized PCILynx IEEE1394 card, irq=%d\n", dev->irq);
+
+	return 0;
+
+fail_free_irq:
+	reg_write(lynx, PCI_INT_ENABLE, 0);
+	free_irq(lynx->pci_device->irq, lynx);
+
+fail_deallocate_buffers:
+	if (lynx->rcv_start_pcl)
+		dma_free_coherent(&lynx->pci_device->dev, sizeof(struct pcl),
+				  lynx->rcv_start_pcl,
+				  lynx->rcv_start_pcl_bus);
+	if (lynx->rcv_pcl)
+		dma_free_coherent(&lynx->pci_device->dev, sizeof(struct pcl),
+				  lynx->rcv_pcl, lynx->rcv_pcl_bus);
+	if (lynx->rcv_buffer)
+		dma_free_coherent(&lynx->pci_device->dev, PAGE_SIZE,
+				  lynx->rcv_buffer, lynx->rcv_buffer_bus);
+	iounmap(lynx->registers);
+
+fail_deallocate_lynx:
+	kfree(lynx);
+
+fail_disable:
+	pci_disable_device(dev);
+
+	return ret;
+}
+
+static struct pci_device_id pci_table[] = {
+	{
+		.vendor =    PCI_VENDOR_ID_TI,
+		.device =    PCI_DEVICE_ID_TI_PCILYNX,
+		.subvendor = PCI_ANY_ID,
+		.subdevice = PCI_ANY_ID,
+	},
+	{ }	/* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(pci, pci_table);
+
+static struct pci_driver lynx_pci_driver = {
+	.name =		driver_name,
+	.id_table =	pci_table,
+	.probe =	add_card,
+	.remove =	remove_card,
+};
+
+module_pci_driver(lynx_pci_driver);
+
+MODULE_AUTHOR("Kristian Hoegsberg");
+MODULE_DESCRIPTION("Snoop mode driver for TI pcilynx 1394 controllers");
+MODULE_LICENSE("GPL");