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, 734 insertions, 0 deletions

diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
new file mode 100644
index 000000000..9327dcdd6
--- /dev/null
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -0,0 +1,734 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
+ *		    Horst Hummel <Horst.Hummel@de.ibm.com>
+ *		    Carsten Otte <Cotte@de.ibm.com>
+ *		    Martin Schwidefsky <schwidefsky@de.ibm.com>
+ * Bugreports.to..: <Linux390@de.ibm.com>
+ * Copyright IBM Corp. 1999, 2001
+ *
+ * i/o controls for the dasd driver.
+ */
+
+#define KMSG_COMPONENT "dasd"
+
+#include <linux/interrupt.h>
+#include <linux/compat.h>
+#include <linux/major.h>
+#include <linux/fs.h>
+#include <linux/blkpg.h>
+#include <linux/slab.h>
+#include <asm/ccwdev.h>
+#include <asm/schid.h>
+#include <asm/cmb.h>
+#include <linux/uaccess.h>
+#include <linux/dasd_mod.h>
+
+/* This is ugly... */
+#define PRINTK_HEADER "dasd_ioctl:"
+
+#include "dasd_int.h"
+
+
+static int
+dasd_ioctl_api_version(void __user *argp)
+{
+	int ver = DASD_API_VERSION;
+	return put_user(ver, (int __user *)argp);
+}
+
+/*
+ * Enable device.
+ * used by dasdfmt after BIODASDDISABLE to retrigger blocksize detection
+ */
+static int
+dasd_ioctl_enable(struct block_device *bdev)
+{
+	struct dasd_device *base;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+
+	dasd_enable_device(base);
+	dasd_put_device(base);
+	return 0;
+}
+
+/*
+ * Disable device.
+ * Used by dasdfmt. Disable I/O operations but allow ioctls.
+ */
+static int
+dasd_ioctl_disable(struct block_device *bdev)
+{
+	struct dasd_device *base;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+	/*
+	 * Man this is sick. We don't do a real disable but only downgrade
+	 * the device to DASD_STATE_BASIC. The reason is that dasdfmt uses
+	 * BIODASDDISABLE to disable accesses to the device via the block
+	 * device layer but it still wants to do i/o on the device by
+	 * using the BIODASDFMT ioctl. Therefore the correct state for the
+	 * device is DASD_STATE_BASIC that allows to do basic i/o.
+	 */
+	dasd_set_target_state(base, DASD_STATE_BASIC);
+	/*
+	 * Set i_size to zero, since read, write, etc. check against this
+	 * value.
+	 */
+	set_capacity(bdev->bd_disk, 0);
+	dasd_put_device(base);
+	return 0;
+}
+
+/*
+ * Quiesce device.
+ */
+static int dasd_ioctl_quiesce(struct dasd_block *block)
+{
+	unsigned long flags;
+	struct dasd_device *base;
+
+	base = block->base;
+	if (!capable (CAP_SYS_ADMIN))
+		return -EACCES;
+
+	pr_info("%s: The DASD has been put in the quiesce "
+		"state\n", dev_name(&base->cdev->dev));
+	spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags);
+	dasd_device_set_stop_bits(base, DASD_STOPPED_QUIESCE);
+	spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags);
+	return 0;
+}
+
+
+/*
+ * Resume device.
+ */
+static int dasd_ioctl_resume(struct dasd_block *block)
+{
+	unsigned long flags;
+	struct dasd_device *base;
+
+	base = block->base;
+	if (!capable (CAP_SYS_ADMIN))
+		return -EACCES;
+
+	pr_info("%s: I/O operations have been resumed "
+		"on the DASD\n", dev_name(&base->cdev->dev));
+	spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags);
+	dasd_device_remove_stop_bits(base, DASD_STOPPED_QUIESCE);
+	spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags);
+
+	dasd_schedule_block_bh(block);
+	return 0;
+}
+
+/*
+ * Abort all failfast I/O on a device.
+ */
+static int dasd_ioctl_abortio(struct dasd_block *block)
+{
+	unsigned long flags;
+	struct dasd_device *base;
+	struct dasd_ccw_req *cqr, *n;
+
+	base = block->base;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (test_and_set_bit(DASD_FLAG_ABORTALL, &base->flags))
+		return 0;
+	DBF_DEV_EVENT(DBF_NOTICE, base, "%s", "abortall flag set");
+
+	spin_lock_irqsave(&block->request_queue_lock, flags);
+	spin_lock(&block->queue_lock);
+	list_for_each_entry_safe(cqr, n, &block->ccw_queue, blocklist) {
+		if (test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) &&
+		    cqr->callback_data &&
+		    cqr->callback_data != DASD_SLEEPON_START_TAG &&
+		    cqr->callback_data != DASD_SLEEPON_END_TAG) {
+			spin_unlock(&block->queue_lock);
+			blk_abort_request(cqr->callback_data);
+			spin_lock(&block->queue_lock);
+		}
+	}
+	spin_unlock(&block->queue_lock);
+	spin_unlock_irqrestore(&block->request_queue_lock, flags);
+
+	dasd_schedule_block_bh(block);
+	return 0;
+}
+
+/*
+ * Allow I/O on a device
+ */
+static int dasd_ioctl_allowio(struct dasd_block *block)
+{
+	struct dasd_device *base;
+
+	base = block->base;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (test_and_clear_bit(DASD_FLAG_ABORTALL, &base->flags))
+		DBF_DEV_EVENT(DBF_NOTICE, base, "%s", "abortall flag unset");
+
+	return 0;
+}
+
+/*
+ * performs formatting of _device_ according to _fdata_
+ * Note: The discipline's format_function is assumed to deliver formatting
+ * commands to format multiple units of the device. In terms of the ECKD
+ * devices this means CCWs are generated to format multiple tracks.
+ */
+static int
+dasd_format(struct dasd_block *block, struct format_data_t *fdata)
+{
+	struct dasd_device *base;
+	int rc;
+
+	base = block->base;
+	if (base->discipline->format_device == NULL)
+		return -EPERM;
+
+	if (base->state != DASD_STATE_BASIC) {
+		pr_warn("%s: The DASD cannot be formatted while it is enabled\n",
+			dev_name(&base->cdev->dev));
+		return -EBUSY;
+	}
+
+	DBF_DEV_EVENT(DBF_NOTICE, base,
+		      "formatting units %u to %u (%u B blocks) flags %u",
+		      fdata->start_unit,
+		      fdata->stop_unit, fdata->blksize, fdata->intensity);
+
+	/* Since dasdfmt keeps the device open after it was disabled,
+	 * there still exists an inode for this device.
+	 * We must update i_blkbits, otherwise we might get errors when
+	 * enabling the device later.
+	 */
+	if (fdata->start_unit == 0) {
+		block->gdp->part0->bd_inode->i_blkbits =
+			blksize_bits(fdata->blksize);
+	}
+
+	rc = base->discipline->format_device(base, fdata, 1);
+	if (rc == -EAGAIN)
+		rc = base->discipline->format_device(base, fdata, 0);
+
+	return rc;
+}
+
+static int dasd_check_format(struct dasd_block *block,
+			     struct format_check_t *cdata)
+{
+	struct dasd_device *base;
+	int rc;
+
+	base = block->base;
+	if (!base->discipline->check_device_format)
+		return -ENOTTY;
+
+	rc = base->discipline->check_device_format(base, cdata, 1);
+	if (rc == -EAGAIN)
+		rc = base->discipline->check_device_format(base, cdata, 0);
+
+	return rc;
+}
+
+/*
+ * Format device.
+ */
+static int
+dasd_ioctl_format(struct block_device *bdev, void __user *argp)
+{
+	struct dasd_device *base;
+	struct format_data_t fdata;
+	int rc;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (!argp)
+		return -EINVAL;
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+	if (base->features & DASD_FEATURE_READONLY ||
+	    test_bit(DASD_FLAG_DEVICE_RO, &base->flags)) {
+		dasd_put_device(base);
+		return -EROFS;
+	}
+	if (copy_from_user(&fdata, argp, sizeof(struct format_data_t))) {
+		dasd_put_device(base);
+		return -EFAULT;
+	}
+	if (bdev_is_partition(bdev)) {
+		pr_warn("%s: The specified DASD is a partition and cannot be formatted\n",
+			dev_name(&base->cdev->dev));
+		dasd_put_device(base);
+		return -EINVAL;
+	}
+	rc = dasd_format(base->block, &fdata);
+	dasd_put_device(base);
+
+	return rc;
+}
+
+/*
+ * Check device format
+ */
+static int dasd_ioctl_check_format(struct block_device *bdev, void __user *argp)
+{
+	struct format_check_t cdata;
+	struct dasd_device *base;
+	int rc = 0;
+
+	if (!argp)
+		return -EINVAL;
+
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+	if (bdev_is_partition(bdev)) {
+		pr_warn("%s: The specified DASD is a partition and cannot be checked\n",
+			dev_name(&base->cdev->dev));
+		rc = -EINVAL;
+		goto out_err;
+	}
+
+	if (copy_from_user(&cdata, argp, sizeof(cdata))) {
+		rc = -EFAULT;
+		goto out_err;
+	}
+
+	rc = dasd_check_format(base->block, &cdata);
+	if (rc)
+		goto out_err;
+
+	if (copy_to_user(argp, &cdata, sizeof(cdata)))
+		rc = -EFAULT;
+
+out_err:
+	dasd_put_device(base);
+
+	return rc;
+}
+
+static int dasd_release_space(struct dasd_device *device,
+			      struct format_data_t *rdata)
+{
+	if (!device->discipline->is_ese && !device->discipline->is_ese(device))
+		return -ENOTSUPP;
+	if (!device->discipline->release_space)
+		return -ENOTSUPP;
+
+	return device->discipline->release_space(device, rdata);
+}
+
+/*
+ * Release allocated space
+ */
+static int dasd_ioctl_release_space(struct block_device *bdev, void __user *argp)
+{
+	struct format_data_t rdata;
+	struct dasd_device *base;
+	int rc = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (!argp)
+		return -EINVAL;
+
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+	if (base->features & DASD_FEATURE_READONLY ||
+	    test_bit(DASD_FLAG_DEVICE_RO, &base->flags)) {
+		rc = -EROFS;
+		goto out_err;
+	}
+	if (bdev_is_partition(bdev)) {
+		pr_warn("%s: The specified DASD is a partition and tracks cannot be released\n",
+			dev_name(&base->cdev->dev));
+		rc = -EINVAL;
+		goto out_err;
+	}
+
+	if (copy_from_user(&rdata, argp, sizeof(rdata))) {
+		rc = -EFAULT;
+		goto out_err;
+	}
+
+	rc = dasd_release_space(base, &rdata);
+
+out_err:
+	dasd_put_device(base);
+
+	return rc;
+}
+
+/*
+ * Swap driver iternal copy relation.
+ */
+static int
+dasd_ioctl_copy_pair_swap(struct block_device *bdev, void __user *argp)
+{
+	struct dasd_copypair_swap_data_t data;
+	struct dasd_device *device;
+	int rc;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	device = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!device)
+		return -ENODEV;
+
+	if (copy_from_user(&data, argp, sizeof(struct dasd_copypair_swap_data_t))) {
+		dasd_put_device(device);
+		return -EFAULT;
+	}
+	if (memchr_inv(data.reserved, 0, sizeof(data.reserved))) {
+		pr_warn("%s: Invalid swap data specified\n",
+			dev_name(&device->cdev->dev));
+		dasd_put_device(device);
+		return DASD_COPYPAIRSWAP_INVALID;
+	}
+	if (bdev_is_partition(bdev)) {
+		pr_warn("%s: The specified DASD is a partition and cannot be swapped\n",
+			dev_name(&device->cdev->dev));
+		dasd_put_device(device);
+		return DASD_COPYPAIRSWAP_INVALID;
+	}
+	if (!device->copy) {
+		pr_warn("%s: The specified DASD has no copy pair set up\n",
+			dev_name(&device->cdev->dev));
+		dasd_put_device(device);
+		return -ENODEV;
+	}
+	if (!device->discipline->copy_pair_swap) {
+		dasd_put_device(device);
+		return -EOPNOTSUPP;
+	}
+	rc = device->discipline->copy_pair_swap(device, data.primary,
+						data.secondary);
+	dasd_put_device(device);
+
+	return rc;
+}
+
+#ifdef CONFIG_DASD_PROFILE
+/*
+ * Reset device profile information
+ */
+static int dasd_ioctl_reset_profile(struct dasd_block *block)
+{
+	dasd_profile_reset(&block->profile);
+	return 0;
+}
+
+/*
+ * Return device profile information
+ */
+static int dasd_ioctl_read_profile(struct dasd_block *block, void __user *argp)
+{
+	struct dasd_profile_info_t *data;
+	int rc = 0;
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	spin_lock_bh(&block->profile.lock);
+	if (block->profile.data) {
+		data->dasd_io_reqs = block->profile.data->dasd_io_reqs;
+		data->dasd_io_sects = block->profile.data->dasd_io_sects;
+		memcpy(data->dasd_io_secs, block->profile.data->dasd_io_secs,
+		       sizeof(data->dasd_io_secs));
+		memcpy(data->dasd_io_times, block->profile.data->dasd_io_times,
+		       sizeof(data->dasd_io_times));
+		memcpy(data->dasd_io_timps, block->profile.data->dasd_io_timps,
+		       sizeof(data->dasd_io_timps));
+		memcpy(data->dasd_io_time1, block->profile.data->dasd_io_time1,
+		       sizeof(data->dasd_io_time1));
+		memcpy(data->dasd_io_time2, block->profile.data->dasd_io_time2,
+		       sizeof(data->dasd_io_time2));
+		memcpy(data->dasd_io_time2ps,
+		       block->profile.data->dasd_io_time2ps,
+		       sizeof(data->dasd_io_time2ps));
+		memcpy(data->dasd_io_time3, block->profile.data->dasd_io_time3,
+		       sizeof(data->dasd_io_time3));
+		memcpy(data->dasd_io_nr_req,
+		       block->profile.data->dasd_io_nr_req,
+		       sizeof(data->dasd_io_nr_req));
+		spin_unlock_bh(&block->profile.lock);
+	} else {
+		spin_unlock_bh(&block->profile.lock);
+		rc = -EIO;
+		goto out;
+	}
+	if (copy_to_user(argp, data, sizeof(*data)))
+		rc = -EFAULT;
+out:
+	kfree(data);
+	return rc;
+}
+#else
+static int dasd_ioctl_reset_profile(struct dasd_block *block)
+{
+	return -ENOTTY;
+}
+
+static int dasd_ioctl_read_profile(struct dasd_block *block, void __user *argp)
+{
+	return -ENOTTY;
+}
+#endif
+
+/*
+ * Return dasd information. Used for BIODASDINFO and BIODASDINFO2.
+ */
+static int __dasd_ioctl_information(struct dasd_block *block,
+		struct dasd_information2_t *dasd_info)
+{
+	struct subchannel_id sch_id;
+	struct ccw_dev_id dev_id;
+	struct dasd_device *base;
+	struct ccw_device *cdev;
+	struct list_head *l;
+	unsigned long flags;
+	int rc;
+
+	base = block->base;
+	if (!base->discipline || !base->discipline->fill_info)
+		return -EINVAL;
+
+	rc = base->discipline->fill_info(base, dasd_info);
+	if (rc)
+		return rc;
+
+	cdev = base->cdev;
+	ccw_device_get_id(cdev, &dev_id);
+	ccw_device_get_schid(cdev, &sch_id);
+
+	dasd_info->devno = dev_id.devno;
+	dasd_info->schid = sch_id.sch_no;
+	dasd_info->cu_type = cdev->id.cu_type;
+	dasd_info->cu_model = cdev->id.cu_model;
+	dasd_info->dev_type = cdev->id.dev_type;
+	dasd_info->dev_model = cdev->id.dev_model;
+	dasd_info->status = base->state;
+	/*
+	 * The open_count is increased for every opener, that includes
+	 * the blkdev_get in dasd_scan_partitions.
+	 * This must be hidden from user-space.
+	 */
+	dasd_info->open_count = atomic_read(&block->open_count);
+	if (!block->bdev)
+		dasd_info->open_count++;
+
+	/*
+	 * check if device is really formatted
+	 * LDL / CDL was returned by 'fill_info'
+	 */
+	if ((base->state < DASD_STATE_READY) ||
+	    (dasd_check_blocksize(block->bp_block)))
+		dasd_info->format = DASD_FORMAT_NONE;
+
+	dasd_info->features |=
+		((base->features & DASD_FEATURE_READONLY) != 0);
+
+	memcpy(dasd_info->type, base->discipline->name, 4);
+
+	spin_lock_irqsave(&block->queue_lock, flags);
+	list_for_each(l, &base->ccw_queue)
+		dasd_info->chanq_len++;
+	spin_unlock_irqrestore(&block->queue_lock, flags);
+	return 0;
+}
+
+static int dasd_ioctl_information(struct dasd_block *block, void __user *argp,
+		size_t copy_size)
+{
+	struct dasd_information2_t *dasd_info;
+	int error;
+
+	dasd_info = kzalloc(sizeof(*dasd_info), GFP_KERNEL);
+	if (!dasd_info)
+		return -ENOMEM;
+
+	error = __dasd_ioctl_information(block, dasd_info);
+	if (!error && copy_to_user(argp, dasd_info, copy_size))
+		error = -EFAULT;
+	kfree(dasd_info);
+	return error;
+}
+
+/*
+ * Set read only
+ */
+int dasd_set_read_only(struct block_device *bdev, bool ro)
+{
+	struct dasd_device *base;
+	int rc;
+
+	/* do not manipulate hardware state for partitions */
+	if (bdev_is_partition(bdev))
+		return 0;
+
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+	if (!ro && test_bit(DASD_FLAG_DEVICE_RO, &base->flags))
+		rc = -EROFS;
+	else
+		rc = dasd_set_feature(base->cdev, DASD_FEATURE_READONLY, ro);
+	dasd_put_device(base);
+	return rc;
+}
+
+static int dasd_ioctl_readall_cmb(struct dasd_block *block, unsigned int cmd,
+				  struct cmbdata __user *argp)
+{
+	size_t size = _IOC_SIZE(cmd);
+	struct cmbdata data;
+	int ret;
+
+	ret = cmf_readall(block->base->cdev, &data);
+	if (!ret && copy_to_user(argp, &data, min(size, sizeof(*argp))))
+		return -EFAULT;
+	return ret;
+}
+
+int dasd_ioctl(struct block_device *bdev, fmode_t mode,
+	       unsigned int cmd, unsigned long arg)
+{
+	struct dasd_block *block;
+	struct dasd_device *base;
+	void __user *argp;
+	int rc;
+
+	if (is_compat_task())
+		argp = compat_ptr(arg);
+	else
+		argp = (void __user *)arg;
+
+	if ((_IOC_DIR(cmd) != _IOC_NONE) && !arg)
+		return -EINVAL;
+
+	base = dasd_device_from_gendisk(bdev->bd_disk);
+	if (!base)
+		return -ENODEV;
+	block = base->block;
+	rc = 0;
+	switch (cmd) {
+	case BIODASDDISABLE:
+		rc = dasd_ioctl_disable(bdev);
+		break;
+	case BIODASDENABLE:
+		rc = dasd_ioctl_enable(bdev);
+		break;
+	case BIODASDQUIESCE:
+		rc = dasd_ioctl_quiesce(block);
+		break;
+	case BIODASDRESUME:
+		rc = dasd_ioctl_resume(block);
+		break;
+	case BIODASDABORTIO:
+		rc = dasd_ioctl_abortio(block);
+		break;
+	case BIODASDALLOWIO:
+		rc = dasd_ioctl_allowio(block);
+		break;
+	case BIODASDFMT:
+		rc = dasd_ioctl_format(bdev, argp);
+		break;
+	case BIODASDCHECKFMT:
+		rc = dasd_ioctl_check_format(bdev, argp);
+		break;
+	case BIODASDINFO:
+		rc = dasd_ioctl_information(block, argp,
+				sizeof(struct dasd_information_t));
+		break;
+	case BIODASDINFO2:
+		rc = dasd_ioctl_information(block, argp,
+				sizeof(struct dasd_information2_t));
+		break;
+	case BIODASDPRRD:
+		rc = dasd_ioctl_read_profile(block, argp);
+		break;
+	case BIODASDPRRST:
+		rc = dasd_ioctl_reset_profile(block);
+		break;
+	case DASDAPIVER:
+		rc = dasd_ioctl_api_version(argp);
+		break;
+	case BIODASDCMFENABLE:
+		rc = enable_cmf(base->cdev);
+		break;
+	case BIODASDCMFDISABLE:
+		rc = disable_cmf(base->cdev);
+		break;
+	case BIODASDREADALLCMB:
+		rc = dasd_ioctl_readall_cmb(block, cmd, argp);
+		break;
+	case BIODASDRAS:
+		rc = dasd_ioctl_release_space(bdev, argp);
+		break;
+	case BIODASDCOPYPAIRSWAP:
+		rc = dasd_ioctl_copy_pair_swap(bdev, argp);
+		break;
+	default:
+		/* if the discipline has an ioctl method try it. */
+		rc = -ENOTTY;
+		if (base->discipline->ioctl)
+			rc = base->discipline->ioctl(block, cmd, argp);
+	}
+	dasd_put_device(base);
+	return rc;
+}
+
+
+/**
+ * dasd_biodasdinfo() - fill out the dasd information structure
+ * @disk: [in] pointer to gendisk structure that references a DASD
+ * @info: [out] pointer to the dasd_information2_t structure
+ *
+ * Provide access to DASD specific information.
+ * The gendisk structure is checked if it belongs to the DASD driver by
+ * comparing the gendisk->fops pointer.
+ * If it does not belong to the DASD driver -EINVAL is returned.
+ * Otherwise the provided dasd_information2_t structure is filled out.
+ *
+ * Returns:
+ *   %0 on success and a negative error value on failure.
+ */
+int dasd_biodasdinfo(struct gendisk *disk, struct dasd_information2_t *info)
+{
+	struct dasd_device *base;
+	int error;
+
+	if (disk->fops != &dasd_device_operations)
+		return -EINVAL;
+
+	base = dasd_device_from_gendisk(disk);
+	if (!base)
+		return -ENODEV;
+	error = __dasd_ioctl_information(base->block, info);
+	dasd_put_device(base);
+	return error;
+}
+/* export that symbol_get in partition detection is possible */
+EXPORT_SYMBOL_GPL(dasd_biodasdinfo);