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, 1491 insertions, 0 deletions

diff --git a/block/genhd.c b/block/genhd.c
new file mode 100644
index 000000000..093ef292e
--- /dev/null
+++ b/block/genhd.c
@@ -0,0 +1,1491 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  gendisk handling
+ *
+ * Portions Copyright (C) 2020 Christoph Hellwig
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/fs.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/major.h>
+#include <linux/mutex.h>
+#include <linux/idr.h>
+#include <linux/log2.h>
+#include <linux/pm_runtime.h>
+#include <linux/badblocks.h>
+#include <linux/part_stat.h>
+#include "blk-throttle.h"
+
+#include "blk.h"
+#include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
+#include "blk-cgroup.h"
+
+static struct kobject *block_depr;
+
+/*
+ * Unique, monotonically increasing sequential number associated with block
+ * devices instances (i.e. incremented each time a device is attached).
+ * Associating uevents with block devices in userspace is difficult and racy:
+ * the uevent netlink socket is lossy, and on slow and overloaded systems has
+ * a very high latency.
+ * Block devices do not have exclusive owners in userspace, any process can set
+ * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0
+ * can be reused again and again).
+ * A userspace process setting up a block device and watching for its events
+ * cannot thus reliably tell whether an event relates to the device it just set
+ * up or another earlier instance with the same name.
+ * This sequential number allows userspace processes to solve this problem, and
+ * uniquely associate an uevent to the lifetime to a device.
+ */
+static atomic64_t diskseq;
+
+/* for extended dynamic devt allocation, currently only one major is used */
+#define NR_EXT_DEVT		(1 << MINORBITS)
+static DEFINE_IDA(ext_devt_ida);
+
+void set_capacity(struct gendisk *disk, sector_t sectors)
+{
+	struct block_device *bdev = disk->part0;
+
+	spin_lock(&bdev->bd_size_lock);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	bdev->bd_nr_sectors = sectors;
+	spin_unlock(&bdev->bd_size_lock);
+}
+EXPORT_SYMBOL(set_capacity);
+
+/*
+ * Set disk capacity and notify if the size is not currently zero and will not
+ * be set to zero.  Returns true if a uevent was sent, otherwise false.
+ */
+bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
+{
+	sector_t capacity = get_capacity(disk);
+	char *envp[] = { "RESIZE=1", NULL };
+
+	set_capacity(disk, size);
+
+	/*
+	 * Only print a message and send a uevent if the gendisk is user visible
+	 * and alive.  This avoids spamming the log and udev when setting the
+	 * initial capacity during probing.
+	 */
+	if (size == capacity ||
+	    !disk_live(disk) ||
+	    (disk->flags & GENHD_FL_HIDDEN))
+		return false;
+
+	pr_info("%s: detected capacity change from %lld to %lld\n",
+		disk->disk_name, capacity, size);
+
+	/*
+	 * Historically we did not send a uevent for changes to/from an empty
+	 * device.
+	 */
+	if (!capacity || !size)
+		return false;
+	kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+	return true;
+}
+EXPORT_SYMBOL_GPL(set_capacity_and_notify);
+
+static void part_stat_read_all(struct block_device *part,
+		struct disk_stats *stat)
+{
+	int cpu;
+
+	memset(stat, 0, sizeof(struct disk_stats));
+	for_each_possible_cpu(cpu) {
+		struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu);
+		int group;
+
+		for (group = 0; group < NR_STAT_GROUPS; group++) {
+			stat->nsecs[group] += ptr->nsecs[group];
+			stat->sectors[group] += ptr->sectors[group];
+			stat->ios[group] += ptr->ios[group];
+			stat->merges[group] += ptr->merges[group];
+		}
+
+		stat->io_ticks += ptr->io_ticks;
+	}
+}
+
+static unsigned int part_in_flight(struct block_device *part)
+{
+	unsigned int inflight = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) +
+			    part_stat_local_read_cpu(part, in_flight[1], cpu);
+	}
+	if ((int)inflight < 0)
+		inflight = 0;
+
+	return inflight;
+}
+
+static void part_in_flight_rw(struct block_device *part,
+		unsigned int inflight[2])
+{
+	int cpu;
+
+	inflight[0] = 0;
+	inflight[1] = 0;
+	for_each_possible_cpu(cpu) {
+		inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu);
+		inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu);
+	}
+	if ((int)inflight[0] < 0)
+		inflight[0] = 0;
+	if ((int)inflight[1] < 0)
+		inflight[1] = 0;
+}
+
+/*
+ * Can be deleted altogether. Later.
+ *
+ */
+#define BLKDEV_MAJOR_HASH_SIZE 255
+static struct blk_major_name {
+	struct blk_major_name *next;
+	int major;
+	char name[16];
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
+	void (*probe)(dev_t devt);
+#endif
+} *major_names[BLKDEV_MAJOR_HASH_SIZE];
+static DEFINE_MUTEX(major_names_lock);
+static DEFINE_SPINLOCK(major_names_spinlock);
+
+/* index in the above - for now: assume no multimajor ranges */
+static inline int major_to_index(unsigned major)
+{
+	return major % BLKDEV_MAJOR_HASH_SIZE;
+}
+
+#ifdef CONFIG_PROC_FS
+void blkdev_show(struct seq_file *seqf, off_t offset)
+{
+	struct blk_major_name *dp;
+
+	spin_lock(&major_names_spinlock);
+	for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
+		if (dp->major == offset)
+			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
+	spin_unlock(&major_names_spinlock);
+}
+#endif /* CONFIG_PROC_FS */
+
+/**
+ * __register_blkdev - register a new block device
+ *
+ * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If
+ *         @major = 0, try to allocate any unused major number.
+ * @name: the name of the new block device as a zero terminated string
+ * @probe: pre-devtmpfs / pre-udev callback used to create disks when their
+ *	   pre-created device node is accessed. When a probe call uses
+ *	   add_disk() and it fails the driver must cleanup resources. This
+ *	   interface may soon be removed.
+ *
+ * The @name must be unique within the system.
+ *
+ * The return value depends on the @major input parameter:
+ *
+ *  - if a major device number was requested in range [1..BLKDEV_MAJOR_MAX-1]
+ *    then the function returns zero on success, or a negative error code
+ *  - if any unused major number was requested with @major = 0 parameter
+ *    then the return value is the allocated major number in range
+ *    [1..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise
+ *
+ * See Documentation/admin-guide/devices.txt for the list of allocated
+ * major numbers.
+ *
+ * Use register_blkdev instead for any new code.
+ */
+int __register_blkdev(unsigned int major, const char *name,
+		void (*probe)(dev_t devt))
+{
+	struct blk_major_name **n, *p;
+	int index, ret = 0;
+
+	mutex_lock(&major_names_lock);
+
+	/* temporary */
+	if (major == 0) {
+		for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) {
+			if (major_names[index] == NULL)
+				break;
+		}
+
+		if (index == 0) {
+			printk("%s: failed to get major for %s\n",
+			       __func__, name);
+			ret = -EBUSY;
+			goto out;
+		}
+		major = index;
+		ret = major;
+	}
+
+	if (major >= BLKDEV_MAJOR_MAX) {
+		pr_err("%s: major requested (%u) is greater than the maximum (%u) for %s\n",
+		       __func__, major, BLKDEV_MAJOR_MAX-1, name);
+
+		ret = -EINVAL;
+		goto out;
+	}
+
+	p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL);
+	if (p == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	p->major = major;
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
+	p->probe = probe;
+#endif
+	strlcpy(p->name, name, sizeof(p->name));
+	p->next = NULL;
+	index = major_to_index(major);
+
+	spin_lock(&major_names_spinlock);
+	for (n = &major_names[index]; *n; n = &(*n)->next) {
+		if ((*n)->major == major)
+			break;
+	}
+	if (!*n)
+		*n = p;
+	else
+		ret = -EBUSY;
+	spin_unlock(&major_names_spinlock);
+
+	if (ret < 0) {
+		printk("register_blkdev: cannot get major %u for %s\n",
+		       major, name);
+		kfree(p);
+	}
+out:
+	mutex_unlock(&major_names_lock);
+	return ret;
+}
+EXPORT_SYMBOL(__register_blkdev);
+
+void unregister_blkdev(unsigned int major, const char *name)
+{
+	struct blk_major_name **n;
+	struct blk_major_name *p = NULL;
+	int index = major_to_index(major);
+
+	mutex_lock(&major_names_lock);
+	spin_lock(&major_names_spinlock);
+	for (n = &major_names[index]; *n; n = &(*n)->next)
+		if ((*n)->major == major)
+			break;
+	if (!*n || strcmp((*n)->name, name)) {
+		WARN_ON(1);
+	} else {
+		p = *n;
+		*n = p->next;
+	}
+	spin_unlock(&major_names_spinlock);
+	mutex_unlock(&major_names_lock);
+	kfree(p);
+}
+
+EXPORT_SYMBOL(unregister_blkdev);
+
+int blk_alloc_ext_minor(void)
+{
+	int idx;
+
+	idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT - 1, GFP_KERNEL);
+	if (idx == -ENOSPC)
+		return -EBUSY;
+	return idx;
+}
+
+void blk_free_ext_minor(unsigned int minor)
+{
+	ida_free(&ext_devt_ida, minor);
+}
+
+static char *bdevt_str(dev_t devt, char *buf)
+{
+	if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
+		char tbuf[BDEVT_SIZE];
+		snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt));
+		snprintf(buf, BDEVT_SIZE, "%-9s", tbuf);
+	} else
+		snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt));
+
+	return buf;
+}
+
+void disk_uevent(struct gendisk *disk, enum kobject_action action)
+{
+	struct block_device *part;
+	unsigned long idx;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, part) {
+		if (bdev_is_partition(part) && !bdev_nr_sectors(part))
+			continue;
+		if (!kobject_get_unless_zero(&part->bd_device.kobj))
+			continue;
+
+		rcu_read_unlock();
+		kobject_uevent(bdev_kobj(part), action);
+		put_device(&part->bd_device);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(disk_uevent);
+
+int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner)
+{
+	struct block_device *bdev;
+
+	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
+		return -EINVAL;
+	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+		return -EINVAL;
+	if (disk->open_partitions)
+		return -EBUSY;
+	/* Someone else has bdev exclusively open? */
+	if (disk->part0->bd_holder && disk->part0->bd_holder != owner)
+		return -EBUSY;
+
+	set_bit(GD_NEED_PART_SCAN, &disk->state);
+	bdev = blkdev_get_by_dev(disk_devt(disk), mode, NULL);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+	blkdev_put(bdev, mode);
+	return 0;
+}
+
+/**
+ * device_add_disk - add disk information to kernel list
+ * @parent: parent device for the disk
+ * @disk: per-device partitioning information
+ * @groups: Additional per-device sysfs groups
+ *
+ * This function registers the partitioning information in @disk
+ * with the kernel.
+ */
+int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
+				 const struct attribute_group **groups)
+
+{
+	struct device *ddev = disk_to_dev(disk);
+	int ret;
+
+	/* Only makes sense for bio-based to set ->poll_bio */
+	if (queue_is_mq(disk->queue) && disk->fops->poll_bio)
+		return -EINVAL;
+
+	/*
+	 * The disk queue should now be all set with enough information about
+	 * the device for the elevator code to pick an adequate default
+	 * elevator if one is needed, that is, for devices requesting queue
+	 * registration.
+	 */
+	elevator_init_mq(disk->queue);
+
+	/*
+	 * If the driver provides an explicit major number it also must provide
+	 * the number of minors numbers supported, and those will be used to
+	 * setup the gendisk.
+	 * Otherwise just allocate the device numbers for both the whole device
+	 * and all partitions from the extended dev_t space.
+	 */
+	ret = -EINVAL;
+	if (disk->major) {
+		if (WARN_ON(!disk->minors))
+			goto out_exit_elevator;
+
+		if (disk->minors > DISK_MAX_PARTS) {
+			pr_err("block: can't allocate more than %d partitions\n",
+				DISK_MAX_PARTS);
+			disk->minors = DISK_MAX_PARTS;
+		}
+		if (disk->first_minor + disk->minors > MINORMASK + 1)
+			goto out_exit_elevator;
+	} else {
+		if (WARN_ON(disk->minors))
+			goto out_exit_elevator;
+
+		ret = blk_alloc_ext_minor();
+		if (ret < 0)
+			goto out_exit_elevator;
+		disk->major = BLOCK_EXT_MAJOR;
+		disk->first_minor = ret;
+	}
+
+	/* delay uevents, until we scanned partition table */
+	dev_set_uevent_suppress(ddev, 1);
+
+	ddev->parent = parent;
+	ddev->groups = groups;
+	dev_set_name(ddev, "%s", disk->disk_name);
+	if (!(disk->flags & GENHD_FL_HIDDEN))
+		ddev->devt = MKDEV(disk->major, disk->first_minor);
+	ret = device_add(ddev);
+	if (ret)
+		goto out_free_ext_minor;
+
+	ret = disk_alloc_events(disk);
+	if (ret)
+		goto out_device_del;
+
+	if (!sysfs_deprecated) {
+		ret = sysfs_create_link(block_depr, &ddev->kobj,
+					kobject_name(&ddev->kobj));
+		if (ret)
+			goto out_device_del;
+	}
+
+	/*
+	 * avoid probable deadlock caused by allocating memory with
+	 * GFP_KERNEL in runtime_resume callback of its all ancestor
+	 * devices
+	 */
+	pm_runtime_set_memalloc_noio(ddev, true);
+
+	ret = blk_integrity_add(disk);
+	if (ret)
+		goto out_del_block_link;
+
+	disk->part0->bd_holder_dir =
+		kobject_create_and_add("holders", &ddev->kobj);
+	if (!disk->part0->bd_holder_dir) {
+		ret = -ENOMEM;
+		goto out_del_integrity;
+	}
+	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
+	if (!disk->slave_dir) {
+		ret = -ENOMEM;
+		goto out_put_holder_dir;
+	}
+
+	ret = blk_register_queue(disk);
+	if (ret)
+		goto out_put_slave_dir;
+
+	if (!(disk->flags & GENHD_FL_HIDDEN)) {
+		ret = bdi_register(disk->bdi, "%u:%u",
+				   disk->major, disk->first_minor);
+		if (ret)
+			goto out_unregister_queue;
+		bdi_set_owner(disk->bdi, ddev);
+		ret = sysfs_create_link(&ddev->kobj,
+					&disk->bdi->dev->kobj, "bdi");
+		if (ret)
+			goto out_unregister_bdi;
+
+		bdev_add(disk->part0, ddev->devt);
+		if (get_capacity(disk))
+			disk_scan_partitions(disk, FMODE_READ, NULL);
+
+		/*
+		 * Announce the disk and partitions after all partitions are
+		 * created. (for hidden disks uevents remain suppressed forever)
+		 */
+		dev_set_uevent_suppress(ddev, 0);
+		disk_uevent(disk, KOBJ_ADD);
+	} else {
+		/*
+		 * Even if the block_device for a hidden gendisk is not
+		 * registered, it needs to have a valid bd_dev so that the
+		 * freeing of the dynamic major works.
+		 */
+		disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor);
+	}
+
+	disk_update_readahead(disk);
+	disk_add_events(disk);
+	set_bit(GD_ADDED, &disk->state);
+	return 0;
+
+out_unregister_bdi:
+	if (!(disk->flags & GENHD_FL_HIDDEN))
+		bdi_unregister(disk->bdi);
+out_unregister_queue:
+	blk_unregister_queue(disk);
+	rq_qos_exit(disk->queue);
+out_put_slave_dir:
+	kobject_put(disk->slave_dir);
+	disk->slave_dir = NULL;
+out_put_holder_dir:
+	kobject_put(disk->part0->bd_holder_dir);
+out_del_integrity:
+	blk_integrity_del(disk);
+out_del_block_link:
+	if (!sysfs_deprecated)
+		sysfs_remove_link(block_depr, dev_name(ddev));
+out_device_del:
+	device_del(ddev);
+out_free_ext_minor:
+	if (disk->major == BLOCK_EXT_MAJOR)
+		blk_free_ext_minor(disk->first_minor);
+out_exit_elevator:
+	if (disk->queue->elevator)
+		elevator_exit(disk->queue);
+	return ret;
+}
+EXPORT_SYMBOL(device_add_disk);
+
+/**
+ * blk_mark_disk_dead - mark a disk as dead
+ * @disk: disk to mark as dead
+ *
+ * Mark as disk as dead (e.g. surprise removed) and don't accept any new I/O
+ * to this disk.
+ */
+void blk_mark_disk_dead(struct gendisk *disk)
+{
+	set_bit(GD_DEAD, &disk->state);
+	blk_queue_start_drain(disk->queue);
+
+	/*
+	 * Stop buffered writers from dirtying pages that can't be written out.
+	 */
+	set_capacity_and_notify(disk, 0);
+}
+EXPORT_SYMBOL_GPL(blk_mark_disk_dead);
+
+/**
+ * del_gendisk - remove the gendisk
+ * @disk: the struct gendisk to remove
+ *
+ * Removes the gendisk and all its associated resources. This deletes the
+ * partitions associated with the gendisk, and unregisters the associated
+ * request_queue.
+ *
+ * This is the counter to the respective __device_add_disk() call.
+ *
+ * The final removal of the struct gendisk happens when its refcount reaches 0
+ * with put_disk(), which should be called after del_gendisk(), if
+ * __device_add_disk() was used.
+ *
+ * Drivers exist which depend on the release of the gendisk to be synchronous,
+ * it should not be deferred.
+ *
+ * Context: can sleep
+ */
+void del_gendisk(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+
+	might_sleep();
+
+	if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN)))
+		return;
+
+	blk_integrity_del(disk);
+	disk_del_events(disk);
+
+	mutex_lock(&disk->open_mutex);
+	remove_inode_hash(disk->part0->bd_inode);
+	blk_drop_partitions(disk);
+	mutex_unlock(&disk->open_mutex);
+
+	fsync_bdev(disk->part0);
+	__invalidate_device(disk->part0, true);
+
+	/*
+	 * Fail any new I/O.
+	 */
+	set_bit(GD_DEAD, &disk->state);
+	if (test_bit(GD_OWNS_QUEUE, &disk->state))
+		blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+	set_capacity(disk, 0);
+
+	/*
+	 * Prevent new I/O from crossing bio_queue_enter().
+	 */
+	blk_queue_start_drain(q);
+
+	if (!(disk->flags & GENHD_FL_HIDDEN)) {
+		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
+
+		/*
+		 * Unregister bdi before releasing device numbers (as they can
+		 * get reused and we'd get clashes in sysfs).
+		 */
+		bdi_unregister(disk->bdi);
+	}
+
+	blk_unregister_queue(disk);
+
+	kobject_put(disk->part0->bd_holder_dir);
+	kobject_put(disk->slave_dir);
+	disk->slave_dir = NULL;
+
+	part_stat_set_all(disk->part0, 0);
+	disk->part0->bd_stamp = 0;
+	if (!sysfs_deprecated)
+		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
+	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
+	device_del(disk_to_dev(disk));
+
+	blk_mq_freeze_queue_wait(q);
+
+	blk_throtl_cancel_bios(disk);
+
+	blk_sync_queue(q);
+	blk_flush_integrity();
+
+	if (queue_is_mq(q))
+		blk_mq_cancel_work_sync(q);
+
+	blk_mq_quiesce_queue(q);
+	if (q->elevator) {
+		mutex_lock(&q->sysfs_lock);
+		elevator_exit(q);
+		mutex_unlock(&q->sysfs_lock);
+	}
+	rq_qos_exit(q);
+	blk_mq_unquiesce_queue(q);
+
+	/*
+	 * If the disk does not own the queue, allow using passthrough requests
+	 * again.  Else leave the queue frozen to fail all I/O.
+	 */
+	if (!test_bit(GD_OWNS_QUEUE, &disk->state)) {
+		blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+		__blk_mq_unfreeze_queue(q, true);
+	} else {
+		if (queue_is_mq(q))
+			blk_mq_exit_queue(q);
+	}
+}
+EXPORT_SYMBOL(del_gendisk);
+
+/**
+ * invalidate_disk - invalidate the disk
+ * @disk: the struct gendisk to invalidate
+ *
+ * A helper to invalidates the disk. It will clean the disk's associated
+ * buffer/page caches and reset its internal states so that the disk
+ * can be reused by the drivers.
+ *
+ * Context: can sleep
+ */
+void invalidate_disk(struct gendisk *disk)
+{
+	struct block_device *bdev = disk->part0;
+
+	invalidate_bdev(bdev);
+	bdev->bd_inode->i_mapping->wb_err = 0;
+	set_capacity(disk, 0);
+}
+EXPORT_SYMBOL(invalidate_disk);
+
+/* sysfs access to bad-blocks list. */
+static ssize_t disk_badblocks_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (!disk->bb)
+		return sprintf(page, "\n");
+
+	return badblocks_show(disk->bb, page, 0);
+}
+
+static ssize_t disk_badblocks_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *page, size_t len)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (!disk->bb)
+		return -ENXIO;
+
+	return badblocks_store(disk->bb, page, len, 0);
+}
+
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
+void blk_request_module(dev_t devt)
+{
+	unsigned int major = MAJOR(devt);
+	struct blk_major_name **n;
+
+	mutex_lock(&major_names_lock);
+	for (n = &major_names[major_to_index(major)]; *n; n = &(*n)->next) {
+		if ((*n)->major == major && (*n)->probe) {
+			(*n)->probe(devt);
+			mutex_unlock(&major_names_lock);
+			return;
+		}
+	}
+	mutex_unlock(&major_names_lock);
+
+	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
+		/* Make old-style 2.4 aliases work */
+		request_module("block-major-%d", MAJOR(devt));
+}
+#endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */
+
+/*
+ * print a full list of all partitions - intended for places where the root
+ * filesystem can't be mounted and thus to give the victim some idea of what
+ * went wrong
+ */
+void __init printk_all_partitions(void)
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+		struct block_device *part;
+		char devt_buf[BDEVT_SIZE];
+		unsigned long idx;
+
+		/*
+		 * Don't show empty devices or things that have been
+		 * suppressed
+		 */
+		if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN))
+			continue;
+
+		/*
+		 * Note, unlike /proc/partitions, I am showing the numbers in
+		 * hex - the same format as the root= option takes.
+		 */
+		rcu_read_lock();
+		xa_for_each(&disk->part_tbl, idx, part) {
+			if (!bdev_nr_sectors(part))
+				continue;
+			printk("%s%s %10llu %pg %s",
+			       bdev_is_partition(part) ? "  " : "",
+			       bdevt_str(part->bd_dev, devt_buf),
+			       bdev_nr_sectors(part) >> 1, part,
+			       part->bd_meta_info ?
+					part->bd_meta_info->uuid : "");
+			if (bdev_is_partition(part))
+				printk("\n");
+			else if (dev->parent && dev->parent->driver)
+				printk(" driver: %s\n",
+					dev->parent->driver->name);
+			else
+				printk(" (driver?)\n");
+		}
+		rcu_read_unlock();
+	}
+	class_dev_iter_exit(&iter);
+}
+
+#ifdef CONFIG_PROC_FS
+/* iterator */
+static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos)
+{
+	loff_t skip = *pos;
+	struct class_dev_iter *iter;
+	struct device *dev;
+
+	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return ERR_PTR(-ENOMEM);
+
+	seqf->private = iter;
+	class_dev_iter_init(iter, &block_class, NULL, &disk_type);
+	do {
+		dev = class_dev_iter_next(iter);
+		if (!dev)
+			return NULL;
+	} while (skip--);
+
+	return dev_to_disk(dev);
+}
+
+static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos)
+{
+	struct device *dev;
+
+	(*pos)++;
+	dev = class_dev_iter_next(seqf->private);
+	if (dev)
+		return dev_to_disk(dev);
+
+	return NULL;
+}
+
+static void disk_seqf_stop(struct seq_file *seqf, void *v)
+{
+	struct class_dev_iter *iter = seqf->private;
+
+	/* stop is called even after start failed :-( */
+	if (iter) {
+		class_dev_iter_exit(iter);
+		kfree(iter);
+		seqf->private = NULL;
+	}
+}
+
+static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
+{
+	void *p;
+
+	p = disk_seqf_start(seqf, pos);
+	if (!IS_ERR_OR_NULL(p) && !*pos)
+		seq_puts(seqf, "major minor  #blocks  name\n\n");
+	return p;
+}
+
+static int show_partition(struct seq_file *seqf, void *v)
+{
+	struct gendisk *sgp = v;
+	struct block_device *part;
+	unsigned long idx;
+
+	if (!get_capacity(sgp) || (sgp->flags & GENHD_FL_HIDDEN))
+		return 0;
+
+	rcu_read_lock();
+	xa_for_each(&sgp->part_tbl, idx, part) {
+		if (!bdev_nr_sectors(part))
+			continue;
+		seq_printf(seqf, "%4d  %7d %10llu %pg\n",
+			   MAJOR(part->bd_dev), MINOR(part->bd_dev),
+			   bdev_nr_sectors(part) >> 1, part);
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+static const struct seq_operations partitions_op = {
+	.start	= show_partition_start,
+	.next	= disk_seqf_next,
+	.stop	= disk_seqf_stop,
+	.show	= show_partition
+};
+#endif
+
+static int __init genhd_device_init(void)
+{
+	int error;
+
+	block_class.dev_kobj = sysfs_dev_block_kobj;
+	error = class_register(&block_class);
+	if (unlikely(error))
+		return error;
+	blk_dev_init();
+
+	register_blkdev(BLOCK_EXT_MAJOR, "blkext");
+
+	/* create top-level block dir */
+	if (!sysfs_deprecated)
+		block_depr = kobject_create_and_add("block", NULL);
+	return 0;
+}
+
+subsys_initcall(genhd_device_init);
+
+static ssize_t disk_range_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", disk->minors);
+}
+
+static ssize_t disk_ext_range_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n",
+		(disk->flags & GENHD_FL_NO_PART) ? 1 : DISK_MAX_PARTS);
+}
+
+static ssize_t disk_removable_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n",
+		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
+}
+
+static ssize_t disk_hidden_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n",
+		       (disk->flags & GENHD_FL_HIDDEN ? 1 : 0));
+}
+
+static ssize_t disk_ro_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0);
+}
+
+ssize_t part_size_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%llu\n", bdev_nr_sectors(dev_to_bdev(dev)));
+}
+
+ssize_t part_stat_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct disk_stats stat;
+	unsigned int inflight;
+
+	if (queue_is_mq(q))
+		inflight = blk_mq_in_flight(q, bdev);
+	else
+		inflight = part_in_flight(bdev);
+
+	if (inflight) {
+		part_stat_lock();
+		update_io_ticks(bdev, jiffies, true);
+		part_stat_unlock();
+	}
+	part_stat_read_all(bdev, &stat);
+	return sprintf(buf,
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8lu %8llu %8u "
+		"%8u %8u %8u "
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8u"
+		"\n",
+		stat.ios[STAT_READ],
+		stat.merges[STAT_READ],
+		(unsigned long long)stat.sectors[STAT_READ],
+		(unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC),
+		stat.ios[STAT_WRITE],
+		stat.merges[STAT_WRITE],
+		(unsigned long long)stat.sectors[STAT_WRITE],
+		(unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC),
+		inflight,
+		jiffies_to_msecs(stat.io_ticks),
+		(unsigned int)div_u64(stat.nsecs[STAT_READ] +
+				      stat.nsecs[STAT_WRITE] +
+				      stat.nsecs[STAT_DISCARD] +
+				      stat.nsecs[STAT_FLUSH],
+						NSEC_PER_MSEC),
+		stat.ios[STAT_DISCARD],
+		stat.merges[STAT_DISCARD],
+		(unsigned long long)stat.sectors[STAT_DISCARD],
+		(unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC),
+		stat.ios[STAT_FLUSH],
+		(unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC));
+}
+
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev_get_queue(bdev);
+	unsigned int inflight[2];
+
+	if (queue_is_mq(q))
+		blk_mq_in_flight_rw(q, bdev, inflight);
+	else
+		part_in_flight_rw(bdev, inflight);
+
+	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
+}
+
+static ssize_t disk_capability_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	dev_warn_once(dev, "the capability attribute has been deprecated.\n");
+	return sprintf(buf, "0\n");
+}
+
+static ssize_t disk_alignment_offset_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0));
+}
+
+static ssize_t disk_discard_alignment_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0));
+}
+
+static ssize_t diskseq_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%llu\n", disk->diskseq);
+}
+
+static DEVICE_ATTR(range, 0444, disk_range_show, NULL);
+static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL);
+static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL);
+static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL);
+static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL);
+static DEVICE_ATTR(size, 0444, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL);
+static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL);
+static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
+static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
+static DEVICE_ATTR(diskseq, 0444, diskseq_show, NULL);
+
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+ssize_t part_fail_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_make_it_fail);
+}
+
+ssize_t part_fail_store(struct device *dev,
+			struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	int i;
+
+	if (count > 0 && sscanf(buf, "%d", &i) > 0)
+		dev_to_bdev(dev)->bd_make_it_fail = i;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_fail =
+	__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+static struct device_attribute dev_attr_fail_timeout =
+	__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
+#endif
+
+static struct attribute *disk_attrs[] = {
+	&dev_attr_range.attr,
+	&dev_attr_ext_range.attr,
+	&dev_attr_removable.attr,
+	&dev_attr_hidden.attr,
+	&dev_attr_ro.attr,
+	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
+	&dev_attr_discard_alignment.attr,
+	&dev_attr_capability.attr,
+	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
+	&dev_attr_badblocks.attr,
+	&dev_attr_events.attr,
+	&dev_attr_events_async.attr,
+	&dev_attr_events_poll_msecs.attr,
+	&dev_attr_diskseq.attr,
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	&dev_attr_fail.attr,
+#endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+	&dev_attr_fail_timeout.attr,
+#endif
+	NULL
+};
+
+static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (a == &dev_attr_badblocks.attr && !disk->bb)
+		return 0;
+	return a->mode;
+}
+
+static struct attribute_group disk_attr_group = {
+	.attrs = disk_attrs,
+	.is_visible = disk_visible,
+};
+
+static const struct attribute_group *disk_attr_groups[] = {
+	&disk_attr_group,
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	&blk_trace_attr_group,
+#endif
+	NULL
+};
+
+/**
+ * disk_release - releases all allocated resources of the gendisk
+ * @dev: the device representing this disk
+ *
+ * This function releases all allocated resources of the gendisk.
+ *
+ * Drivers which used __device_add_disk() have a gendisk with a request_queue
+ * assigned. Since the request_queue sits on top of the gendisk for these
+ * drivers we also call blk_put_queue() for them, and we expect the
+ * request_queue refcount to reach 0 at this point, and so the request_queue
+ * will also be freed prior to the disk.
+ *
+ * Context: can sleep
+ */
+static void disk_release(struct device *dev)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	might_sleep();
+	WARN_ON_ONCE(disk_live(disk));
+
+	/*
+	 * To undo the all initialization from blk_mq_init_allocated_queue in
+	 * case of a probe failure where add_disk is never called we have to
+	 * call blk_mq_exit_queue here. We can't do this for the more common
+	 * teardown case (yet) as the tagset can be gone by the time the disk
+	 * is released once it was added.
+	 */
+	if (queue_is_mq(disk->queue) &&
+	    test_bit(GD_OWNS_QUEUE, &disk->state) &&
+	    !test_bit(GD_ADDED, &disk->state))
+		blk_mq_exit_queue(disk->queue);
+
+	blkcg_exit_disk(disk);
+
+	bioset_exit(&disk->bio_split);
+
+	disk_release_events(disk);
+	kfree(disk->random);
+	disk_free_zone_bitmaps(disk);
+	xa_destroy(&disk->part_tbl);
+
+	disk->queue->disk = NULL;
+	blk_put_queue(disk->queue);
+
+	if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk)
+		disk->fops->free_disk(disk);
+
+	iput(disk->part0->bd_inode);	/* frees the disk */
+}
+
+static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+	const struct gendisk *disk = dev_to_disk(dev);
+
+	return add_uevent_var(env, "DISKSEQ=%llu", disk->diskseq);
+}
+
+struct class block_class = {
+	.name		= "block",
+	.dev_uevent	= block_uevent,
+};
+
+static char *block_devnode(struct device *dev, umode_t *mode,
+			   kuid_t *uid, kgid_t *gid)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (disk->fops->devnode)
+		return disk->fops->devnode(disk, mode);
+	return NULL;
+}
+
+const struct device_type disk_type = {
+	.name		= "disk",
+	.groups		= disk_attr_groups,
+	.release	= disk_release,
+	.devnode	= block_devnode,
+};
+
+#ifdef CONFIG_PROC_FS
+/*
+ * aggregate disk stat collector.  Uses the same stats that the sysfs
+ * entries do, above, but makes them available through one seq_file.
+ *
+ * The output looks suspiciously like /proc/partitions with a bunch of
+ * extra fields.
+ */
+static int diskstats_show(struct seq_file *seqf, void *v)
+{
+	struct gendisk *gp = v;
+	struct block_device *hd;
+	unsigned int inflight;
+	struct disk_stats stat;
+	unsigned long idx;
+
+	/*
+	if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
+		seq_puts(seqf,	"major minor name"
+				"     rio rmerge rsect ruse wio wmerge "
+				"wsect wuse running use aveq"
+				"\n\n");
+	*/
+
+	rcu_read_lock();
+	xa_for_each(&gp->part_tbl, idx, hd) {
+		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
+			continue;
+		if (queue_is_mq(gp->queue))
+			inflight = blk_mq_in_flight(gp->queue, hd);
+		else
+			inflight = part_in_flight(hd);
+
+		if (inflight) {
+			part_stat_lock();
+			update_io_ticks(hd, jiffies, true);
+			part_stat_unlock();
+		}
+		part_stat_read_all(hd, &stat);
+		seq_printf(seqf, "%4d %7d %pg "
+			   "%lu %lu %lu %u "
+			   "%lu %lu %lu %u "
+			   "%u %u %u "
+			   "%lu %lu %lu %u "
+			   "%lu %u"
+			   "\n",
+			   MAJOR(hd->bd_dev), MINOR(hd->bd_dev), hd,
+			   stat.ios[STAT_READ],
+			   stat.merges[STAT_READ],
+			   stat.sectors[STAT_READ],
+			   (unsigned int)div_u64(stat.nsecs[STAT_READ],
+							NSEC_PER_MSEC),
+			   stat.ios[STAT_WRITE],
+			   stat.merges[STAT_WRITE],
+			   stat.sectors[STAT_WRITE],
+			   (unsigned int)div_u64(stat.nsecs[STAT_WRITE],
+							NSEC_PER_MSEC),
+			   inflight,
+			   jiffies_to_msecs(stat.io_ticks),
+			   (unsigned int)div_u64(stat.nsecs[STAT_READ] +
+						 stat.nsecs[STAT_WRITE] +
+						 stat.nsecs[STAT_DISCARD] +
+						 stat.nsecs[STAT_FLUSH],
+							NSEC_PER_MSEC),
+			   stat.ios[STAT_DISCARD],
+			   stat.merges[STAT_DISCARD],
+			   stat.sectors[STAT_DISCARD],
+			   (unsigned int)div_u64(stat.nsecs[STAT_DISCARD],
+						 NSEC_PER_MSEC),
+			   stat.ios[STAT_FLUSH],
+			   (unsigned int)div_u64(stat.nsecs[STAT_FLUSH],
+						 NSEC_PER_MSEC)
+			);
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static const struct seq_operations diskstats_op = {
+	.start	= disk_seqf_start,
+	.next	= disk_seqf_next,
+	.stop	= disk_seqf_stop,
+	.show	= diskstats_show
+};
+
+static int __init proc_genhd_init(void)
+{
+	proc_create_seq("diskstats", 0, NULL, &diskstats_op);
+	proc_create_seq("partitions", 0, NULL, &partitions_op);
+	return 0;
+}
+module_init(proc_genhd_init);
+#endif /* CONFIG_PROC_FS */
+
+dev_t part_devt(struct gendisk *disk, u8 partno)
+{
+	struct block_device *part;
+	dev_t devt = 0;
+
+	rcu_read_lock();
+	part = xa_load(&disk->part_tbl, partno);
+	if (part)
+		devt = part->bd_dev;
+	rcu_read_unlock();
+
+	return devt;
+}
+
+dev_t blk_lookup_devt(const char *name, int partno)
+{
+	dev_t devt = MKDEV(0, 0);
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+
+		if (strcmp(dev_name(dev), name))
+			continue;
+
+		if (partno < disk->minors) {
+			/* We need to return the right devno, even
+			 * if the partition doesn't exist yet.
+			 */
+			devt = MKDEV(MAJOR(dev->devt),
+				     MINOR(dev->devt) + partno);
+		} else {
+			devt = part_devt(disk, partno);
+			if (devt)
+				break;
+		}
+	}
+	class_dev_iter_exit(&iter);
+	return devt;
+}
+
+struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
+		struct lock_class_key *lkclass)
+{
+	struct gendisk *disk;
+
+	disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
+	if (!disk)
+		return NULL;
+
+	if (bioset_init(&disk->bio_split, BIO_POOL_SIZE, 0, 0))
+		goto out_free_disk;
+
+	disk->bdi = bdi_alloc(node_id);
+	if (!disk->bdi)
+		goto out_free_bioset;
+
+	/* bdev_alloc() might need the queue, set before the first call */
+	disk->queue = q;
+
+	disk->part0 = bdev_alloc(disk, 0);
+	if (!disk->part0)
+		goto out_free_bdi;
+
+	disk->node_id = node_id;
+	mutex_init(&disk->open_mutex);
+	xa_init(&disk->part_tbl);
+	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
+		goto out_destroy_part_tbl;
+
+	if (blkcg_init_disk(disk))
+		goto out_erase_part0;
+
+	rand_initialize_disk(disk);
+	disk_to_dev(disk)->class = &block_class;
+	disk_to_dev(disk)->type = &disk_type;
+	device_initialize(disk_to_dev(disk));
+	inc_diskseq(disk);
+	q->disk = disk;
+	lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0);
+#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
+	INIT_LIST_HEAD(&disk->slave_bdevs);
+#endif
+	return disk;
+
+out_erase_part0:
+	xa_erase(&disk->part_tbl, 0);
+out_destroy_part_tbl:
+	xa_destroy(&disk->part_tbl);
+	disk->part0->bd_disk = NULL;
+	iput(disk->part0->bd_inode);
+out_free_bdi:
+	bdi_put(disk->bdi);
+out_free_bioset:
+	bioset_exit(&disk->bio_split);
+out_free_disk:
+	kfree(disk);
+	return NULL;
+}
+
+struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
+{
+	struct request_queue *q;
+	struct gendisk *disk;
+
+	q = blk_alloc_queue(node);
+	if (!q)
+		return NULL;
+
+	disk = __alloc_disk_node(q, node, lkclass);
+	if (!disk) {
+		blk_put_queue(q);
+		return NULL;
+	}
+	set_bit(GD_OWNS_QUEUE, &disk->state);
+	return disk;
+}
+EXPORT_SYMBOL(__blk_alloc_disk);
+
+/**
+ * put_disk - decrements the gendisk refcount
+ * @disk: the struct gendisk to decrement the refcount for
+ *
+ * This decrements the refcount for the struct gendisk. When this reaches 0
+ * we'll have disk_release() called.
+ *
+ * Note: for blk-mq disk put_disk must be called before freeing the tag_set
+ * when handling probe errors (that is before add_disk() is called).
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
+ */
+void put_disk(struct gendisk *disk)
+{
+	if (disk)
+		put_device(disk_to_dev(disk));
+}
+EXPORT_SYMBOL(put_disk);
+
+static void set_disk_ro_uevent(struct gendisk *gd, int ro)
+{
+	char event[] = "DISK_RO=1";
+	char *envp[] = { event, NULL };
+
+	if (!ro)
+		event[8] = '0';
+	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
+}
+
+/**
+ * set_disk_ro - set a gendisk read-only
+ * @disk:	gendisk to operate on
+ * @read_only:	%true to set the disk read-only, %false set the disk read/write
+ *
+ * This function is used to indicate whether a given disk device should have its
+ * read-only flag set. set_disk_ro() is typically used by device drivers to
+ * indicate whether the underlying physical device is write-protected.
+ */
+void set_disk_ro(struct gendisk *disk, bool read_only)
+{
+	if (read_only) {
+		if (test_and_set_bit(GD_READ_ONLY, &disk->state))
+			return;
+	} else {
+		if (!test_and_clear_bit(GD_READ_ONLY, &disk->state))
+			return;
+	}
+	set_disk_ro_uevent(disk, read_only);
+}
+EXPORT_SYMBOL(set_disk_ro);
+
+void inc_diskseq(struct gendisk *disk)
+{
+	disk->diskseq = atomic64_inc_return(&diskseq);
+}