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, 531 insertions, 0 deletions

diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
new file mode 100644
index 000000000..3523dd82d
--- /dev/null
+++ b/drivers/block/aoe/aoedev.c
@@ -0,0 +1,531 @@
+/* Copyright (c) 2013 Coraid, Inc.  See COPYING for GPL terms. */
+/*
+ * aoedev.c
+ * AoE device utility functions; maintains device list.
+ */
+
+#include <linux/hdreg.h>
+#include <linux/blk-mq.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/bitmap.h>
+#include <linux/kdev_t.h>
+#include <linux/moduleparam.h>
+#include <linux/string.h>
+#include "aoe.h"
+
+static void freetgt(struct aoedev *d, struct aoetgt *t);
+static void skbpoolfree(struct aoedev *d);
+
+static int aoe_dyndevs = 1;
+module_param(aoe_dyndevs, int, 0644);
+MODULE_PARM_DESC(aoe_dyndevs, "Use dynamic minor numbers for devices.");
+
+static struct aoedev *devlist;
+static DEFINE_SPINLOCK(devlist_lock);
+
+/* Because some systems will have one, many, or no
+ *   - partitions,
+ *   - slots per shelf,
+ *   - or shelves,
+ * we need some flexibility in the way the minor numbers
+ * are allocated.  So they are dynamic.
+ */
+#define N_DEVS ((1U<<MINORBITS)/AOE_PARTITIONS)
+
+static DEFINE_SPINLOCK(used_minors_lock);
+static DECLARE_BITMAP(used_minors, N_DEVS);
+
+static int
+minor_get_dyn(ulong *sysminor)
+{
+	ulong flags;
+	ulong n;
+	int error = 0;
+
+	spin_lock_irqsave(&used_minors_lock, flags);
+	n = find_first_zero_bit(used_minors, N_DEVS);
+	if (n < N_DEVS)
+		set_bit(n, used_minors);
+	else
+		error = -1;
+	spin_unlock_irqrestore(&used_minors_lock, flags);
+
+	*sysminor = n * AOE_PARTITIONS;
+	return error;
+}
+
+static int
+minor_get_static(ulong *sysminor, ulong aoemaj, int aoemin)
+{
+	ulong flags;
+	ulong n;
+	int error = 0;
+	enum {
+		/* for backwards compatibility when !aoe_dyndevs,
+		 * a static number of supported slots per shelf */
+		NPERSHELF = 16,
+	};
+
+	if (aoemin >= NPERSHELF) {
+		pr_err("aoe: %s %d slots per shelf\n",
+			"static minor device numbers support only",
+			NPERSHELF);
+		error = -1;
+		goto out;
+	}
+
+	n = aoemaj * NPERSHELF + aoemin;
+	if (n >= N_DEVS) {
+		pr_err("aoe: %s with e%ld.%d\n",
+			"cannot use static minor device numbers",
+			aoemaj, aoemin);
+		error = -1;
+		goto out;
+	}
+
+	spin_lock_irqsave(&used_minors_lock, flags);
+	if (test_bit(n, used_minors)) {
+		pr_err("aoe: %s %lu\n",
+			"existing device already has static minor number",
+			n);
+		error = -1;
+	} else
+		set_bit(n, used_minors);
+	spin_unlock_irqrestore(&used_minors_lock, flags);
+	*sysminor = n * AOE_PARTITIONS;
+out:
+	return error;
+}
+
+static int
+minor_get(ulong *sysminor, ulong aoemaj, int aoemin)
+{
+	if (aoe_dyndevs)
+		return minor_get_dyn(sysminor);
+	else
+		return minor_get_static(sysminor, aoemaj, aoemin);
+}
+
+static void
+minor_free(ulong minor)
+{
+	ulong flags;
+
+	minor /= AOE_PARTITIONS;
+	BUG_ON(minor >= N_DEVS);
+
+	spin_lock_irqsave(&used_minors_lock, flags);
+	BUG_ON(!test_bit(minor, used_minors));
+	clear_bit(minor, used_minors);
+	spin_unlock_irqrestore(&used_minors_lock, flags);
+}
+
+/*
+ * Users who grab a pointer to the device with aoedev_by_aoeaddr
+ * automatically get a reference count and must be responsible
+ * for performing a aoedev_put.  With the addition of async
+ * kthread processing I'm no longer confident that we can
+ * guarantee consistency in the face of device flushes.
+ *
+ * For the time being, we only bother to add extra references for
+ * frames sitting on the iocq.  When the kthreads finish processing
+ * these frames, they will aoedev_put the device.
+ */
+
+void
+aoedev_put(struct aoedev *d)
+{
+	ulong flags;
+
+	spin_lock_irqsave(&devlist_lock, flags);
+	d->ref--;
+	spin_unlock_irqrestore(&devlist_lock, flags);
+}
+
+static void
+dummy_timer(struct timer_list *t)
+{
+	struct aoedev *d;
+
+	d = from_timer(d, t, timer);
+	if (d->flags & DEVFL_TKILL)
+		return;
+	d->timer.expires = jiffies + HZ;
+	add_timer(&d->timer);
+}
+
+static void
+aoe_failip(struct aoedev *d)
+{
+	struct request *rq;
+	struct aoe_req *req;
+	struct bio *bio;
+
+	aoe_failbuf(d, d->ip.buf);
+	rq = d->ip.rq;
+	if (rq == NULL)
+		return;
+
+	req = blk_mq_rq_to_pdu(rq);
+	while ((bio = d->ip.nxbio)) {
+		bio->bi_status = BLK_STS_IOERR;
+		d->ip.nxbio = bio->bi_next;
+		req->nr_bios--;
+	}
+
+	if (!req->nr_bios)
+		aoe_end_request(d, rq, 0);
+}
+
+static void
+downdev_frame(struct list_head *pos)
+{
+	struct frame *f;
+
+	f = list_entry(pos, struct frame, head);
+	list_del(pos);
+	if (f->buf) {
+		f->buf->nframesout--;
+		aoe_failbuf(f->t->d, f->buf);
+	}
+	aoe_freetframe(f);
+}
+
+void
+aoedev_downdev(struct aoedev *d)
+{
+	struct aoetgt *t, **tt, **te;
+	struct list_head *head, *pos, *nx;
+	int i;
+
+	d->flags &= ~DEVFL_UP;
+
+	/* clean out active and to-be-retransmitted buffers */
+	for (i = 0; i < NFACTIVE; i++) {
+		head = &d->factive[i];
+		list_for_each_safe(pos, nx, head)
+			downdev_frame(pos);
+	}
+	head = &d->rexmitq;
+	list_for_each_safe(pos, nx, head)
+		downdev_frame(pos);
+
+	/* reset window dressings */
+	tt = d->targets;
+	te = tt + d->ntargets;
+	for (; tt < te && (t = *tt); tt++) {
+		aoecmd_wreset(t);
+		t->nout = 0;
+	}
+
+	/* clean out the in-process request (if any) */
+	aoe_failip(d);
+
+	/* fast fail all pending I/O */
+	if (d->blkq) {
+		/* UP is cleared, freeze+quiesce to insure all are errored */
+		blk_mq_freeze_queue(d->blkq);
+		blk_mq_quiesce_queue(d->blkq);
+		blk_mq_unquiesce_queue(d->blkq);
+		blk_mq_unfreeze_queue(d->blkq);
+	}
+
+	if (d->gd)
+		set_capacity(d->gd, 0);
+}
+
+/* return whether the user asked for this particular
+ * device to be flushed
+ */
+static int
+user_req(char *s, size_t slen, struct aoedev *d)
+{
+	const char *p;
+	size_t lim;
+
+	if (!d->gd)
+		return 0;
+	p = kbasename(d->gd->disk_name);
+	lim = sizeof(d->gd->disk_name);
+	lim -= p - d->gd->disk_name;
+	if (slen < lim)
+		lim = slen;
+
+	return !strncmp(s, p, lim);
+}
+
+static void
+freedev(struct aoedev *d)
+{
+	struct aoetgt **t, **e;
+	int freeing = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->lock, flags);
+	if (d->flags & DEVFL_TKILL
+	&& !(d->flags & DEVFL_FREEING)) {
+		d->flags |= DEVFL_FREEING;
+		freeing = 1;
+	}
+	spin_unlock_irqrestore(&d->lock, flags);
+	if (!freeing)
+		return;
+
+	del_timer_sync(&d->timer);
+	if (d->gd) {
+		aoedisk_rm_debugfs(d);
+		del_gendisk(d->gd);
+		put_disk(d->gd);
+		blk_mq_free_tag_set(&d->tag_set);
+	}
+	t = d->targets;
+	e = t + d->ntargets;
+	for (; t < e && *t; t++)
+		freetgt(d, *t);
+
+	mempool_destroy(d->bufpool);
+	skbpoolfree(d);
+	minor_free(d->sysminor);
+
+	spin_lock_irqsave(&d->lock, flags);
+	d->flags |= DEVFL_FREED;
+	spin_unlock_irqrestore(&d->lock, flags);
+}
+
+enum flush_parms {
+	NOT_EXITING = 0,
+	EXITING = 1,
+};
+
+static int
+flush(const char __user *str, size_t cnt, int exiting)
+{
+	ulong flags;
+	struct aoedev *d, **dd;
+	char buf[16];
+	int all = 0;
+	int specified = 0;	/* flush a specific device */
+	unsigned int skipflags;
+
+	skipflags = DEVFL_GDALLOC | DEVFL_NEWSIZE | DEVFL_TKILL;
+
+	if (!exiting && cnt >= 3) {
+		if (cnt > sizeof buf)
+			cnt = sizeof buf;
+		if (copy_from_user(buf, str, cnt))
+			return -EFAULT;
+		all = !strncmp(buf, "all", 3);
+		if (!all)
+			specified = 1;
+	}
+
+	flush_workqueue(aoe_wq);
+	/* pass one: do aoedev_downdev, which might sleep */
+restart1:
+	spin_lock_irqsave(&devlist_lock, flags);
+	for (d = devlist; d; d = d->next) {
+		spin_lock(&d->lock);
+		if (d->flags & DEVFL_TKILL)
+			goto cont;
+
+		if (exiting) {
+			/* unconditionally take each device down */
+		} else if (specified) {
+			if (!user_req(buf, cnt, d))
+				goto cont;
+		} else if ((!all && (d->flags & DEVFL_UP))
+		|| d->flags & skipflags
+		|| d->nopen
+		|| d->ref)
+			goto cont;
+
+		spin_unlock(&d->lock);
+		spin_unlock_irqrestore(&devlist_lock, flags);
+		aoedev_downdev(d);
+		d->flags |= DEVFL_TKILL;
+		goto restart1;
+cont:
+		spin_unlock(&d->lock);
+	}
+	spin_unlock_irqrestore(&devlist_lock, flags);
+
+	/* pass two: call freedev, which might sleep,
+	 * for aoedevs marked with DEVFL_TKILL
+	 */
+restart2:
+	spin_lock_irqsave(&devlist_lock, flags);
+	for (d = devlist; d; d = d->next) {
+		spin_lock(&d->lock);
+		if (d->flags & DEVFL_TKILL
+		&& !(d->flags & DEVFL_FREEING)) {
+			spin_unlock(&d->lock);
+			spin_unlock_irqrestore(&devlist_lock, flags);
+			freedev(d);
+			goto restart2;
+		}
+		spin_unlock(&d->lock);
+	}
+
+	/* pass three: remove aoedevs marked with DEVFL_FREED */
+	for (dd = &devlist, d = *dd; d; d = *dd) {
+		struct aoedev *doomed = NULL;
+
+		spin_lock(&d->lock);
+		if (d->flags & DEVFL_FREED) {
+			*dd = d->next;
+			doomed = d;
+		} else {
+			dd = &d->next;
+		}
+		spin_unlock(&d->lock);
+		if (doomed)
+			kfree(doomed->targets);
+		kfree(doomed);
+	}
+	spin_unlock_irqrestore(&devlist_lock, flags);
+
+	return 0;
+}
+
+int
+aoedev_flush(const char __user *str, size_t cnt)
+{
+	return flush(str, cnt, NOT_EXITING);
+}
+
+/* This has been confirmed to occur once with Tms=3*1000 due to the
+ * driver changing link and not processing its transmit ring.  The
+ * problem is hard enough to solve by returning an error that I'm
+ * still punting on "solving" this.
+ */
+static void
+skbfree(struct sk_buff *skb)
+{
+	enum { Sms = 250, Tms = 30 * 1000};
+	int i = Tms / Sms;
+
+	if (skb == NULL)
+		return;
+	while (atomic_read(&skb_shinfo(skb)->dataref) != 1 && i-- > 0)
+		msleep(Sms);
+	if (i < 0) {
+		printk(KERN_ERR
+			"aoe: %s holds ref: %s\n",
+			skb->dev ? skb->dev->name : "netif",
+			"cannot free skb -- memory leaked.");
+		return;
+	}
+	skb->truesize -= skb->data_len;
+	skb_shinfo(skb)->nr_frags = skb->data_len = 0;
+	skb_trim(skb, 0);
+	dev_kfree_skb(skb);
+}
+
+static void
+skbpoolfree(struct aoedev *d)
+{
+	struct sk_buff *skb, *tmp;
+
+	skb_queue_walk_safe(&d->skbpool, skb, tmp)
+		skbfree(skb);
+
+	__skb_queue_head_init(&d->skbpool);
+}
+
+/* find it or allocate it */
+struct aoedev *
+aoedev_by_aoeaddr(ulong maj, int min, int do_alloc)
+{
+	struct aoedev *d;
+	int i;
+	ulong flags;
+	ulong sysminor = 0;
+
+	spin_lock_irqsave(&devlist_lock, flags);
+
+	for (d=devlist; d; d=d->next)
+		if (d->aoemajor == maj && d->aoeminor == min) {
+			spin_lock(&d->lock);
+			if (d->flags & DEVFL_TKILL) {
+				spin_unlock(&d->lock);
+				d = NULL;
+				goto out;
+			}
+			d->ref++;
+			spin_unlock(&d->lock);
+			break;
+		}
+	if (d || !do_alloc || minor_get(&sysminor, maj, min) < 0)
+		goto out;
+	d = kcalloc(1, sizeof *d, GFP_ATOMIC);
+	if (!d)
+		goto out;
+	d->targets = kcalloc(NTARGETS, sizeof(*d->targets), GFP_ATOMIC);
+	if (!d->targets) {
+		kfree(d);
+		d = NULL;
+		goto out;
+	}
+	d->ntargets = NTARGETS;
+	INIT_WORK(&d->work, aoecmd_sleepwork);
+	spin_lock_init(&d->lock);
+	INIT_LIST_HEAD(&d->rq_list);
+	skb_queue_head_init(&d->skbpool);
+	timer_setup(&d->timer, dummy_timer, 0);
+	d->timer.expires = jiffies + HZ;
+	add_timer(&d->timer);
+	d->bufpool = NULL;	/* defer to aoeblk_gdalloc */
+	d->tgt = d->targets;
+	d->ref = 1;
+	for (i = 0; i < NFACTIVE; i++)
+		INIT_LIST_HEAD(&d->factive[i]);
+	INIT_LIST_HEAD(&d->rexmitq);
+	d->sysminor = sysminor;
+	d->aoemajor = maj;
+	d->aoeminor = min;
+	d->rttavg = RTTAVG_INIT;
+	d->rttdev = RTTDEV_INIT;
+	d->next = devlist;
+	devlist = d;
+ out:
+	spin_unlock_irqrestore(&devlist_lock, flags);
+	return d;
+}
+
+static void
+freetgt(struct aoedev *d, struct aoetgt *t)
+{
+	struct frame *f;
+	struct list_head *pos, *nx, *head;
+	struct aoeif *ifp;
+
+	for (ifp = t->ifs; ifp < &t->ifs[NAOEIFS]; ++ifp) {
+		if (!ifp->nd)
+			break;
+		dev_put(ifp->nd);
+	}
+
+	head = &t->ffree;
+	list_for_each_safe(pos, nx, head) {
+		list_del(pos);
+		f = list_entry(pos, struct frame, head);
+		skbfree(f->skb);
+		kfree(f);
+	}
+	kfree(t);
+}
+
+void
+aoedev_exit(void)
+{
+	flush_workqueue(aoe_wq);
+	flush(NULL, 0, EXITING);
+}
+
+int __init
+aoedev_init(void)
+{
+	return 0;
+}