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, 662 insertions, 0 deletions

diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
new file mode 100644
index 000000000..1eafe0b4d
--- /dev/null
+++ b/drivers/watchdog/cpwd.c
@@ -0,0 +1,662 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* cpwd.c - driver implementation for hardware watchdog
+ * timers found on Sun Microsystems CP1400 and CP1500 boards.
+ *
+ * This device supports both the generic Linux watchdog
+ * interface and Solaris-compatible ioctls as best it is
+ * able.
+ *
+ * NOTE:	CP1400 systems appear to have a defective intr_mask
+ *			register on the PLD, preventing the disabling of
+ *			timer interrupts.  We use a timer to periodically
+ *			reset 'stopped' watchdogs on affected platforms.
+ *
+ * Copyright (c) 2000 Eric Brower (ebrower@usa.net)
+ * Copyright (C) 2008 David S. Miller <davem@davemloft.net>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/errno.h>
+#include <linux/major.h>
+#include <linux/miscdevice.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/timer.h>
+#include <linux/compat.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/uaccess.h>
+
+#include <asm/irq.h>
+#include <asm/watchdog.h>
+
+#define DRIVER_NAME	"cpwd"
+
+#define WD_OBPNAME	"watchdog"
+#define WD_BADMODEL	"SUNW,501-5336"
+#define WD_BTIMEOUT	(jiffies + (HZ * 1000))
+#define WD_BLIMIT	0xFFFF
+
+#define WD0_MINOR	212
+#define WD1_MINOR	213
+#define WD2_MINOR	214
+
+/* Internal driver definitions.  */
+#define WD0_ID			0
+#define WD1_ID			1
+#define WD2_ID			2
+#define WD_NUMDEVS		3
+
+#define WD_INTR_OFF		0
+#define WD_INTR_ON		1
+
+#define WD_STAT_INIT	0x01	/* Watchdog timer is initialized	*/
+#define WD_STAT_BSTOP	0x02	/* Watchdog timer is brokenstopped	*/
+#define WD_STAT_SVCD	0x04	/* Watchdog interrupt occurred		*/
+
+/* Register value definitions
+ */
+#define WD0_INTR_MASK	0x01	/* Watchdog device interrupt masks	*/
+#define WD1_INTR_MASK	0x02
+#define WD2_INTR_MASK	0x04
+
+#define WD_S_RUNNING	0x01	/* Watchdog device status running	*/
+#define WD_S_EXPIRED	0x02	/* Watchdog device status expired	*/
+
+struct cpwd {
+	void __iomem	*regs;
+	spinlock_t	lock;
+
+	unsigned int	irq;
+
+	unsigned long	timeout;
+	bool		enabled;
+	bool		reboot;
+	bool		broken;
+	bool		initialized;
+
+	struct {
+		struct miscdevice	misc;
+		void __iomem		*regs;
+		u8			intr_mask;
+		u8			runstatus;
+		u16			timeout;
+	} devs[WD_NUMDEVS];
+};
+
+static DEFINE_MUTEX(cpwd_mutex);
+static struct cpwd *cpwd_device;
+
+/* Sun uses Altera PLD EPF8820ATC144-4
+ * providing three hardware watchdogs:
+ *
+ * 1) RIC - sends an interrupt when triggered
+ * 2) XIR - asserts XIR_B_RESET when triggered, resets CPU
+ * 3) POR - asserts POR_B_RESET when triggered, resets CPU, backplane, board
+ *
+ *** Timer register block definition (struct wd_timer_regblk)
+ *
+ * dcntr and limit registers (halfword access):
+ * -------------------
+ * | 15 | ...| 1 | 0 |
+ * -------------------
+ * |-  counter val  -|
+ * -------------------
+ * dcntr -	Current 16-bit downcounter value.
+ *			When downcounter reaches '0' watchdog expires.
+ *			Reading this register resets downcounter with
+ *			'limit' value.
+ * limit -	16-bit countdown value in 1/10th second increments.
+ *			Writing this register begins countdown with input value.
+ *			Reading from this register does not affect counter.
+ * NOTES:	After watchdog reset, dcntr and limit contain '1'
+ *
+ * status register (byte access):
+ * ---------------------------
+ * | 7 | ... | 2 |  1  |  0  |
+ * --------------+------------
+ * |-   UNUSED  -| EXP | RUN |
+ * ---------------------------
+ * status-	Bit 0 - Watchdog is running
+ *			Bit 1 - Watchdog has expired
+ *
+ *** PLD register block definition (struct wd_pld_regblk)
+ *
+ * intr_mask register (byte access):
+ * ---------------------------------
+ * | 7 | ... | 3 |  2  |  1  |  0  |
+ * +-------------+------------------
+ * |-   UNUSED  -| WD3 | WD2 | WD1 |
+ * ---------------------------------
+ * WD3 -  1 == Interrupt disabled for watchdog 3
+ * WD2 -  1 == Interrupt disabled for watchdog 2
+ * WD1 -  1 == Interrupt disabled for watchdog 1
+ *
+ * pld_status register (byte access):
+ * UNKNOWN, MAGICAL MYSTERY REGISTER
+ *
+ */
+#define WD_TIMER_REGSZ	16
+#define WD0_OFF		0
+#define WD1_OFF		(WD_TIMER_REGSZ * 1)
+#define WD2_OFF		(WD_TIMER_REGSZ * 2)
+#define PLD_OFF		(WD_TIMER_REGSZ * 3)
+
+#define WD_DCNTR	0x00
+#define WD_LIMIT	0x04
+#define WD_STATUS	0x08
+
+#define PLD_IMASK	(PLD_OFF + 0x00)
+#define PLD_STATUS	(PLD_OFF + 0x04)
+
+static struct timer_list cpwd_timer;
+
+static int wd0_timeout;
+static int wd1_timeout;
+static int wd2_timeout;
+
+module_param(wd0_timeout, int, 0);
+MODULE_PARM_DESC(wd0_timeout, "Default watchdog0 timeout in 1/10secs");
+module_param(wd1_timeout, int, 0);
+MODULE_PARM_DESC(wd1_timeout, "Default watchdog1 timeout in 1/10secs");
+module_param(wd2_timeout, int, 0);
+MODULE_PARM_DESC(wd2_timeout, "Default watchdog2 timeout in 1/10secs");
+
+MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
+MODULE_DESCRIPTION("Hardware watchdog driver for Sun Microsystems CP1400/1500");
+MODULE_LICENSE("GPL");
+
+static void cpwd_writew(u16 val, void __iomem *addr)
+{
+	writew(cpu_to_le16(val), addr);
+}
+static u16 cpwd_readw(void __iomem *addr)
+{
+	u16 val = readw(addr);
+
+	return le16_to_cpu(val);
+}
+
+static void cpwd_writeb(u8 val, void __iomem *addr)
+{
+	writeb(val, addr);
+}
+
+static u8 cpwd_readb(void __iomem *addr)
+{
+	return readb(addr);
+}
+
+/* Enable or disable watchdog interrupts
+ * Because of the CP1400 defect this should only be
+ * called during initialzation or by wd_[start|stop]timer()
+ *
+ * index	- sub-device index, or -1 for 'all'
+ * enable	- non-zero to enable interrupts, zero to disable
+ */
+static void cpwd_toggleintr(struct cpwd *p, int index, int enable)
+{
+	unsigned char curregs = cpwd_readb(p->regs + PLD_IMASK);
+	unsigned char setregs =
+		(index == -1) ?
+		(WD0_INTR_MASK | WD1_INTR_MASK | WD2_INTR_MASK) :
+		(p->devs[index].intr_mask);
+
+	if (enable == WD_INTR_ON)
+		curregs &= ~setregs;
+	else
+		curregs |= setregs;
+
+	cpwd_writeb(curregs, p->regs + PLD_IMASK);
+}
+
+/* Restarts timer with maximum limit value and
+ * does not unset 'brokenstop' value.
+ */
+static void cpwd_resetbrokentimer(struct cpwd *p, int index)
+{
+	cpwd_toggleintr(p, index, WD_INTR_ON);
+	cpwd_writew(WD_BLIMIT, p->devs[index].regs + WD_LIMIT);
+}
+
+/* Timer method called to reset stopped watchdogs--
+ * because of the PLD bug on CP1400, we cannot mask
+ * interrupts within the PLD so me must continually
+ * reset the timers ad infinitum.
+ */
+static void cpwd_brokentimer(struct timer_list *unused)
+{
+	struct cpwd *p = cpwd_device;
+	int id, tripped = 0;
+
+	/* kill a running timer instance, in case we
+	 * were called directly instead of by kernel timer
+	 */
+	if (timer_pending(&cpwd_timer))
+		del_timer(&cpwd_timer);
+
+	for (id = 0; id < WD_NUMDEVS; id++) {
+		if (p->devs[id].runstatus & WD_STAT_BSTOP) {
+			++tripped;
+			cpwd_resetbrokentimer(p, id);
+		}
+	}
+
+	if (tripped) {
+		/* there is at least one timer brokenstopped-- reschedule */
+		cpwd_timer.expires = WD_BTIMEOUT;
+		add_timer(&cpwd_timer);
+	}
+}
+
+/* Reset countdown timer with 'limit' value and continue countdown.
+ * This will not start a stopped timer.
+ */
+static void cpwd_pingtimer(struct cpwd *p, int index)
+{
+	if (cpwd_readb(p->devs[index].regs + WD_STATUS) & WD_S_RUNNING)
+		cpwd_readw(p->devs[index].regs + WD_DCNTR);
+}
+
+/* Stop a running watchdog timer-- the timer actually keeps
+ * running, but the interrupt is masked so that no action is
+ * taken upon expiration.
+ */
+static void cpwd_stoptimer(struct cpwd *p, int index)
+{
+	if (cpwd_readb(p->devs[index].regs + WD_STATUS) & WD_S_RUNNING) {
+		cpwd_toggleintr(p, index, WD_INTR_OFF);
+
+		if (p->broken) {
+			p->devs[index].runstatus |= WD_STAT_BSTOP;
+			cpwd_brokentimer(NULL);
+		}
+	}
+}
+
+/* Start a watchdog timer with the specified limit value
+ * If the watchdog is running, it will be restarted with
+ * the provided limit value.
+ *
+ * This function will enable interrupts on the specified
+ * watchdog.
+ */
+static void cpwd_starttimer(struct cpwd *p, int index)
+{
+	if (p->broken)
+		p->devs[index].runstatus &= ~WD_STAT_BSTOP;
+
+	p->devs[index].runstatus &= ~WD_STAT_SVCD;
+
+	cpwd_writew(p->devs[index].timeout, p->devs[index].regs + WD_LIMIT);
+	cpwd_toggleintr(p, index, WD_INTR_ON);
+}
+
+static int cpwd_getstatus(struct cpwd *p, int index)
+{
+	unsigned char stat = cpwd_readb(p->devs[index].regs + WD_STATUS);
+	unsigned char intr = cpwd_readb(p->devs[index].regs + PLD_IMASK);
+	unsigned char ret  = WD_STOPPED;
+
+	/* determine STOPPED */
+	if (!stat)
+		return ret;
+
+	/* determine EXPIRED vs FREERUN vs RUNNING */
+	else if (WD_S_EXPIRED & stat) {
+		ret = WD_EXPIRED;
+	} else if (WD_S_RUNNING & stat) {
+		if (intr & p->devs[index].intr_mask) {
+			ret = WD_FREERUN;
+		} else {
+			/* Fudge WD_EXPIRED status for defective CP1400--
+			 * IF timer is running
+			 *	AND brokenstop is set
+			 *	AND an interrupt has been serviced
+			 * we are WD_EXPIRED.
+			 *
+			 * IF timer is running
+			 *	AND brokenstop is set
+			 *	AND no interrupt has been serviced
+			 * we are WD_FREERUN.
+			 */
+			if (p->broken &&
+			    (p->devs[index].runstatus & WD_STAT_BSTOP)) {
+				if (p->devs[index].runstatus & WD_STAT_SVCD) {
+					ret = WD_EXPIRED;
+				} else {
+					/* we could as well pretend
+					 * we are expired */
+					ret = WD_FREERUN;
+				}
+			} else {
+				ret = WD_RUNNING;
+			}
+		}
+	}
+
+	/* determine SERVICED */
+	if (p->devs[index].runstatus & WD_STAT_SVCD)
+		ret |= WD_SERVICED;
+
+	return ret;
+}
+
+static irqreturn_t cpwd_interrupt(int irq, void *dev_id)
+{
+	struct cpwd *p = dev_id;
+
+	/* Only WD0 will interrupt-- others are NMI and we won't
+	 * see them here....
+	 */
+	spin_lock_irq(&p->lock);
+
+	cpwd_stoptimer(p, WD0_ID);
+	p->devs[WD0_ID].runstatus |=  WD_STAT_SVCD;
+
+	spin_unlock_irq(&p->lock);
+
+	return IRQ_HANDLED;
+}
+
+static int cpwd_open(struct inode *inode, struct file *f)
+{
+	struct cpwd *p = cpwd_device;
+
+	mutex_lock(&cpwd_mutex);
+	switch (iminor(inode)) {
+	case WD0_MINOR:
+	case WD1_MINOR:
+	case WD2_MINOR:
+		break;
+
+	default:
+		mutex_unlock(&cpwd_mutex);
+		return -ENODEV;
+	}
+
+	/* Register IRQ on first open of device */
+	if (!p->initialized) {
+		if (request_irq(p->irq, &cpwd_interrupt,
+				IRQF_SHARED, DRIVER_NAME, p)) {
+			pr_err("Cannot register IRQ %d\n", p->irq);
+			mutex_unlock(&cpwd_mutex);
+			return -EBUSY;
+		}
+		p->initialized = true;
+	}
+
+	mutex_unlock(&cpwd_mutex);
+
+	return stream_open(inode, f);
+}
+
+static int cpwd_release(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+
+static long cpwd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	static const struct watchdog_info info = {
+		.options		= WDIOF_SETTIMEOUT,
+		.firmware_version	= 1,
+		.identity		= DRIVER_NAME,
+	};
+	void __user *argp = (void __user *)arg;
+	struct inode *inode = file_inode(file);
+	int index = iminor(inode) - WD0_MINOR;
+	struct cpwd *p = cpwd_device;
+	int setopt = 0;
+
+	switch (cmd) {
+	/* Generic Linux IOCTLs */
+	case WDIOC_GETSUPPORT:
+		if (copy_to_user(argp, &info, sizeof(struct watchdog_info)))
+			return -EFAULT;
+		break;
+
+	case WDIOC_GETSTATUS:
+	case WDIOC_GETBOOTSTATUS:
+		if (put_user(0, (int __user *)argp))
+			return -EFAULT;
+		break;
+
+	case WDIOC_KEEPALIVE:
+		cpwd_pingtimer(p, index);
+		break;
+
+	case WDIOC_SETOPTIONS:
+		if (copy_from_user(&setopt, argp, sizeof(unsigned int)))
+			return -EFAULT;
+
+		if (setopt & WDIOS_DISABLECARD) {
+			if (p->enabled)
+				return -EINVAL;
+			cpwd_stoptimer(p, index);
+		} else if (setopt & WDIOS_ENABLECARD) {
+			cpwd_starttimer(p, index);
+		} else {
+			return -EINVAL;
+		}
+		break;
+
+	/* Solaris-compatible IOCTLs */
+	case WIOCGSTAT:
+		setopt = cpwd_getstatus(p, index);
+		if (copy_to_user(argp, &setopt, sizeof(unsigned int)))
+			return -EFAULT;
+		break;
+
+	case WIOCSTART:
+		cpwd_starttimer(p, index);
+		break;
+
+	case WIOCSTOP:
+		if (p->enabled)
+			return -EINVAL;
+
+		cpwd_stoptimer(p, index);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static long cpwd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return cpwd_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+
+static ssize_t cpwd_write(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	struct inode *inode = file_inode(file);
+	struct cpwd *p = cpwd_device;
+	int index = iminor(inode);
+
+	if (count) {
+		cpwd_pingtimer(p, index);
+		return 1;
+	}
+
+	return 0;
+}
+
+static ssize_t cpwd_read(struct file *file, char __user *buffer,
+			 size_t count, loff_t *ppos)
+{
+	return -EINVAL;
+}
+
+static const struct file_operations cpwd_fops = {
+	.owner =		THIS_MODULE,
+	.unlocked_ioctl =	cpwd_ioctl,
+	.compat_ioctl =		cpwd_compat_ioctl,
+	.open =			cpwd_open,
+	.write =		cpwd_write,
+	.read =			cpwd_read,
+	.release =		cpwd_release,
+	.llseek =		no_llseek,
+};
+
+static int cpwd_probe(struct platform_device *op)
+{
+	struct device_node *options;
+	const char *str_prop;
+	const void *prop_val;
+	int i, err = -EINVAL;
+	struct cpwd *p;
+
+	if (cpwd_device)
+		return -EINVAL;
+
+	p = devm_kzalloc(&op->dev, sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	p->irq = op->archdata.irqs[0];
+
+	spin_lock_init(&p->lock);
+
+	p->regs = of_ioremap(&op->resource[0], 0,
+			     4 * WD_TIMER_REGSZ, DRIVER_NAME);
+	if (!p->regs) {
+		pr_err("Unable to map registers\n");
+		return -ENOMEM;
+	}
+
+	options = of_find_node_by_path("/options");
+	if (!options) {
+		err = -ENODEV;
+		pr_err("Unable to find /options node\n");
+		goto out_iounmap;
+	}
+
+	prop_val = of_get_property(options, "watchdog-enable?", NULL);
+	p->enabled = (prop_val ? true : false);
+
+	prop_val = of_get_property(options, "watchdog-reboot?", NULL);
+	p->reboot = (prop_val ? true : false);
+
+	str_prop = of_get_property(options, "watchdog-timeout", NULL);
+	if (str_prop)
+		p->timeout = simple_strtoul(str_prop, NULL, 10);
+
+	of_node_put(options);
+
+	/* CP1400s seem to have broken PLD implementations-- the
+	 * interrupt_mask register cannot be written, so no timer
+	 * interrupts can be masked within the PLD.
+	 */
+	str_prop = of_get_property(op->dev.of_node, "model", NULL);
+	p->broken = (str_prop && !strcmp(str_prop, WD_BADMODEL));
+
+	if (!p->enabled)
+		cpwd_toggleintr(p, -1, WD_INTR_OFF);
+
+	for (i = 0; i < WD_NUMDEVS; i++) {
+		static const char *cpwd_names[] = { "RIC", "XIR", "POR" };
+		static int *parms[] = { &wd0_timeout,
+					&wd1_timeout,
+					&wd2_timeout };
+		struct miscdevice *mp = &p->devs[i].misc;
+
+		mp->minor = WD0_MINOR + i;
+		mp->name = cpwd_names[i];
+		mp->fops = &cpwd_fops;
+
+		p->devs[i].regs = p->regs + (i * WD_TIMER_REGSZ);
+		p->devs[i].intr_mask = (WD0_INTR_MASK << i);
+		p->devs[i].runstatus &= ~WD_STAT_BSTOP;
+		p->devs[i].runstatus |= WD_STAT_INIT;
+		p->devs[i].timeout = p->timeout;
+		if (*parms[i])
+			p->devs[i].timeout = *parms[i];
+
+		err = misc_register(&p->devs[i].misc);
+		if (err) {
+			pr_err("Could not register misc device for dev %d\n",
+			       i);
+			goto out_unregister;
+		}
+	}
+
+	if (p->broken) {
+		timer_setup(&cpwd_timer, cpwd_brokentimer, 0);
+		cpwd_timer.expires	= WD_BTIMEOUT;
+
+		pr_info("PLD defect workaround enabled for model %s\n",
+			WD_BADMODEL);
+	}
+
+	platform_set_drvdata(op, p);
+	cpwd_device = p;
+	return 0;
+
+out_unregister:
+	for (i--; i >= 0; i--)
+		misc_deregister(&p->devs[i].misc);
+
+out_iounmap:
+	of_iounmap(&op->resource[0], p->regs, 4 * WD_TIMER_REGSZ);
+
+	return err;
+}
+
+static int cpwd_remove(struct platform_device *op)
+{
+	struct cpwd *p = platform_get_drvdata(op);
+	int i;
+
+	for (i = 0; i < WD_NUMDEVS; i++) {
+		misc_deregister(&p->devs[i].misc);
+
+		if (!p->enabled) {
+			cpwd_stoptimer(p, i);
+			if (p->devs[i].runstatus & WD_STAT_BSTOP)
+				cpwd_resetbrokentimer(p, i);
+		}
+	}
+
+	if (p->broken)
+		del_timer_sync(&cpwd_timer);
+
+	if (p->initialized)
+		free_irq(p->irq, p);
+
+	of_iounmap(&op->resource[0], p->regs, 4 * WD_TIMER_REGSZ);
+
+	cpwd_device = NULL;
+
+	return 0;
+}
+
+static const struct of_device_id cpwd_match[] = {
+	{
+		.name = "watchdog",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, cpwd_match);
+
+static struct platform_driver cpwd_driver = {
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = cpwd_match,
+	},
+	.probe		= cpwd_probe,
+	.remove		= cpwd_remove,
+};
+
+module_platform_driver(cpwd_driver);