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, 821 insertions, 0 deletions

diff --git a/block/elevator.c b/block/elevator.c
new file mode 100644
index 000000000..24909069f
--- /dev/null
+++ b/block/elevator.c
@@ -0,0 +1,821 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Block device elevator/IO-scheduler.
+ *
+ *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
+ *
+ * 30042000 Jens Axboe <axboe@kernel.dk> :
+ *
+ * Split the elevator a bit so that it is possible to choose a different
+ * one or even write a new "plug in". There are three pieces:
+ * - elevator_fn, inserts a new request in the queue list
+ * - elevator_merge_fn, decides whether a new buffer can be merged with
+ *   an existing request
+ * - elevator_dequeue_fn, called when a request is taken off the active list
+ *
+ * 20082000 Dave Jones <davej@suse.de> :
+ * Removed tests for max-bomb-segments, which was breaking elvtune
+ *  when run without -bN
+ *
+ * Jens:
+ * - Rework again to work with bio instead of buffer_heads
+ * - loose bi_dev comparisons, partition handling is right now
+ * - completely modularize elevator setup and teardown
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/blktrace_api.h>
+#include <linux/hash.h>
+#include <linux/uaccess.h>
+#include <linux/pm_runtime.h>
+
+#include <trace/events/block.h>
+
+#include "elevator.h"
+#include "blk.h"
+#include "blk-mq-sched.h"
+#include "blk-pm.h"
+#include "blk-wbt.h"
+#include "blk-cgroup.h"
+
+static DEFINE_SPINLOCK(elv_list_lock);
+static LIST_HEAD(elv_list);
+
+/*
+ * Merge hash stuff.
+ */
+#define rq_hash_key(rq)		(blk_rq_pos(rq) + blk_rq_sectors(rq))
+
+/*
+ * Query io scheduler to see if the current process issuing bio may be
+ * merged with rq.
+ */
+static bool elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.allow_merge)
+		return e->type->ops.allow_merge(q, rq, bio);
+
+	return true;
+}
+
+/*
+ * can we safely merge with this request?
+ */
+bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
+{
+	if (!blk_rq_merge_ok(rq, bio))
+		return false;
+
+	if (!elv_iosched_allow_bio_merge(rq, bio))
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL(elv_bio_merge_ok);
+
+static inline bool elv_support_features(struct request_queue *q,
+		const struct elevator_type *e)
+{
+	return (q->required_elevator_features & e->elevator_features) ==
+		q->required_elevator_features;
+}
+
+/**
+ * elevator_match - Check whether @e's name or alias matches @name
+ * @e: Scheduler to test
+ * @name: Elevator name to test
+ *
+ * Return true if the elevator @e's name or alias matches @name.
+ */
+static bool elevator_match(const struct elevator_type *e, const char *name)
+{
+	return !strcmp(e->elevator_name, name) ||
+		(e->elevator_alias && !strcmp(e->elevator_alias, name));
+}
+
+static struct elevator_type *__elevator_find(const char *name)
+{
+	struct elevator_type *e;
+
+	list_for_each_entry(e, &elv_list, list)
+		if (elevator_match(e, name))
+			return e;
+	return NULL;
+}
+
+static struct elevator_type *elevator_find_get(struct request_queue *q,
+		const char *name)
+{
+	struct elevator_type *e;
+
+	spin_lock(&elv_list_lock);
+	e = __elevator_find(name);
+	if (e && (!elv_support_features(q, e) || !elevator_tryget(e)))
+		e = NULL;
+	spin_unlock(&elv_list_lock);
+	return e;
+}
+
+static const struct kobj_type elv_ktype;
+
+struct elevator_queue *elevator_alloc(struct request_queue *q,
+				  struct elevator_type *e)
+{
+	struct elevator_queue *eq;
+
+	eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
+	if (unlikely(!eq))
+		return NULL;
+
+	__elevator_get(e);
+	eq->type = e;
+	kobject_init(&eq->kobj, &elv_ktype);
+	mutex_init(&eq->sysfs_lock);
+	hash_init(eq->hash);
+
+	return eq;
+}
+EXPORT_SYMBOL(elevator_alloc);
+
+static void elevator_release(struct kobject *kobj)
+{
+	struct elevator_queue *e;
+
+	e = container_of(kobj, struct elevator_queue, kobj);
+	elevator_put(e->type);
+	kfree(e);
+}
+
+void elevator_exit(struct request_queue *q)
+{
+	struct elevator_queue *e = q->elevator;
+
+	ioc_clear_queue(q);
+	blk_mq_sched_free_rqs(q);
+
+	mutex_lock(&e->sysfs_lock);
+	blk_mq_exit_sched(q, e);
+	mutex_unlock(&e->sysfs_lock);
+
+	kobject_put(&e->kobj);
+}
+
+static inline void __elv_rqhash_del(struct request *rq)
+{
+	hash_del(&rq->hash);
+	rq->rq_flags &= ~RQF_HASHED;
+}
+
+void elv_rqhash_del(struct request_queue *q, struct request *rq)
+{
+	if (ELV_ON_HASH(rq))
+		__elv_rqhash_del(rq);
+}
+EXPORT_SYMBOL_GPL(elv_rqhash_del);
+
+void elv_rqhash_add(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	BUG_ON(ELV_ON_HASH(rq));
+	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
+	rq->rq_flags |= RQF_HASHED;
+}
+EXPORT_SYMBOL_GPL(elv_rqhash_add);
+
+void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
+{
+	__elv_rqhash_del(rq);
+	elv_rqhash_add(q, rq);
+}
+
+struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
+{
+	struct elevator_queue *e = q->elevator;
+	struct hlist_node *next;
+	struct request *rq;
+
+	hash_for_each_possible_safe(e->hash, rq, next, hash, offset) {
+		BUG_ON(!ELV_ON_HASH(rq));
+
+		if (unlikely(!rq_mergeable(rq))) {
+			__elv_rqhash_del(rq);
+			continue;
+		}
+
+		if (rq_hash_key(rq) == offset)
+			return rq;
+	}
+
+	return NULL;
+}
+
+/*
+ * RB-tree support functions for inserting/lookup/removal of requests
+ * in a sorted RB tree.
+ */
+void elv_rb_add(struct rb_root *root, struct request *rq)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct request *__rq;
+
+	while (*p) {
+		parent = *p;
+		__rq = rb_entry(parent, struct request, rb_node);
+
+		if (blk_rq_pos(rq) < blk_rq_pos(__rq))
+			p = &(*p)->rb_left;
+		else if (blk_rq_pos(rq) >= blk_rq_pos(__rq))
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&rq->rb_node, parent, p);
+	rb_insert_color(&rq->rb_node, root);
+}
+EXPORT_SYMBOL(elv_rb_add);
+
+void elv_rb_del(struct rb_root *root, struct request *rq)
+{
+	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
+	rb_erase(&rq->rb_node, root);
+	RB_CLEAR_NODE(&rq->rb_node);
+}
+EXPORT_SYMBOL(elv_rb_del);
+
+struct request *elv_rb_find(struct rb_root *root, sector_t sector)
+{
+	struct rb_node *n = root->rb_node;
+	struct request *rq;
+
+	while (n) {
+		rq = rb_entry(n, struct request, rb_node);
+
+		if (sector < blk_rq_pos(rq))
+			n = n->rb_left;
+		else if (sector > blk_rq_pos(rq))
+			n = n->rb_right;
+		else
+			return rq;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_find);
+
+enum elv_merge elv_merge(struct request_queue *q, struct request **req,
+		struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+	struct request *__rq;
+
+	/*
+	 * Levels of merges:
+	 * 	nomerges:  No merges at all attempted
+	 * 	noxmerges: Only simple one-hit cache try
+	 * 	merges:	   All merge tries attempted
+	 */
+	if (blk_queue_nomerges(q) || !bio_mergeable(bio))
+		return ELEVATOR_NO_MERGE;
+
+	/*
+	 * First try one-hit cache.
+	 */
+	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
+		enum elv_merge ret = blk_try_merge(q->last_merge, bio);
+
+		if (ret != ELEVATOR_NO_MERGE) {
+			*req = q->last_merge;
+			return ret;
+		}
+	}
+
+	if (blk_queue_noxmerges(q))
+		return ELEVATOR_NO_MERGE;
+
+	/*
+	 * See if our hash lookup can find a potential backmerge.
+	 */
+	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
+		*req = __rq;
+
+		if (blk_discard_mergable(__rq))
+			return ELEVATOR_DISCARD_MERGE;
+		return ELEVATOR_BACK_MERGE;
+	}
+
+	if (e->type->ops.request_merge)
+		return e->type->ops.request_merge(q, req, bio);
+
+	return ELEVATOR_NO_MERGE;
+}
+
+/*
+ * Attempt to do an insertion back merge. Only check for the case where
+ * we can append 'rq' to an existing request, so we can throw 'rq' away
+ * afterwards.
+ *
+ * Returns true if we merged, false otherwise. 'free' will contain all
+ * requests that need to be freed.
+ */
+bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq,
+			      struct list_head *free)
+{
+	struct request *__rq;
+	bool ret;
+
+	if (blk_queue_nomerges(q))
+		return false;
+
+	/*
+	 * First try one-hit cache.
+	 */
+	if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq)) {
+		list_add(&rq->queuelist, free);
+		return true;
+	}
+
+	if (blk_queue_noxmerges(q))
+		return false;
+
+	ret = false;
+	/*
+	 * See if our hash lookup can find a potential backmerge.
+	 */
+	while (1) {
+		__rq = elv_rqhash_find(q, blk_rq_pos(rq));
+		if (!__rq || !blk_attempt_req_merge(q, __rq, rq))
+			break;
+
+		list_add(&rq->queuelist, free);
+		/* The merged request could be merged with others, try again */
+		ret = true;
+		rq = __rq;
+	}
+
+	return ret;
+}
+
+void elv_merged_request(struct request_queue *q, struct request *rq,
+		enum elv_merge type)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.request_merged)
+		e->type->ops.request_merged(q, rq, type);
+
+	if (type == ELEVATOR_BACK_MERGE)
+		elv_rqhash_reposition(q, rq);
+
+	q->last_merge = rq;
+}
+
+void elv_merge_requests(struct request_queue *q, struct request *rq,
+			     struct request *next)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.requests_merged)
+		e->type->ops.requests_merged(q, rq, next);
+
+	elv_rqhash_reposition(q, rq);
+	q->last_merge = rq;
+}
+
+struct request *elv_latter_request(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.next_request)
+		return e->type->ops.next_request(q, rq);
+
+	return NULL;
+}
+
+struct request *elv_former_request(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.former_request)
+		return e->type->ops.former_request(q, rq);
+
+	return NULL;
+}
+
+#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
+
+static ssize_t
+elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct elv_fs_entry *entry = to_elv(attr);
+	struct elevator_queue *e;
+	ssize_t error;
+
+	if (!entry->show)
+		return -EIO;
+
+	e = container_of(kobj, struct elevator_queue, kobj);
+	mutex_lock(&e->sysfs_lock);
+	error = e->type ? entry->show(e, page) : -ENOENT;
+	mutex_unlock(&e->sysfs_lock);
+	return error;
+}
+
+static ssize_t
+elv_attr_store(struct kobject *kobj, struct attribute *attr,
+	       const char *page, size_t length)
+{
+	struct elv_fs_entry *entry = to_elv(attr);
+	struct elevator_queue *e;
+	ssize_t error;
+
+	if (!entry->store)
+		return -EIO;
+
+	e = container_of(kobj, struct elevator_queue, kobj);
+	mutex_lock(&e->sysfs_lock);
+	error = e->type ? entry->store(e, page, length) : -ENOENT;
+	mutex_unlock(&e->sysfs_lock);
+	return error;
+}
+
+static const struct sysfs_ops elv_sysfs_ops = {
+	.show	= elv_attr_show,
+	.store	= elv_attr_store,
+};
+
+static const struct kobj_type elv_ktype = {
+	.sysfs_ops	= &elv_sysfs_ops,
+	.release	= elevator_release,
+};
+
+int elv_register_queue(struct request_queue *q, bool uevent)
+{
+	struct elevator_queue *e = q->elevator;
+	int error;
+
+	lockdep_assert_held(&q->sysfs_lock);
+
+	error = kobject_add(&e->kobj, &q->disk->queue_kobj, "iosched");
+	if (!error) {
+		struct elv_fs_entry *attr = e->type->elevator_attrs;
+		if (attr) {
+			while (attr->attr.name) {
+				if (sysfs_create_file(&e->kobj, &attr->attr))
+					break;
+				attr++;
+			}
+		}
+		if (uevent)
+			kobject_uevent(&e->kobj, KOBJ_ADD);
+
+		set_bit(ELEVATOR_FLAG_REGISTERED, &e->flags);
+	}
+	return error;
+}
+
+void elv_unregister_queue(struct request_queue *q)
+{
+	struct elevator_queue *e = q->elevator;
+
+	lockdep_assert_held(&q->sysfs_lock);
+
+	if (e && test_and_clear_bit(ELEVATOR_FLAG_REGISTERED, &e->flags)) {
+		kobject_uevent(&e->kobj, KOBJ_REMOVE);
+		kobject_del(&e->kobj);
+	}
+}
+
+int elv_register(struct elevator_type *e)
+{
+	/* insert_requests and dispatch_request are mandatory */
+	if (WARN_ON_ONCE(!e->ops.insert_requests || !e->ops.dispatch_request))
+		return -EINVAL;
+
+	/* create icq_cache if requested */
+	if (e->icq_size) {
+		if (WARN_ON(e->icq_size < sizeof(struct io_cq)) ||
+		    WARN_ON(e->icq_align < __alignof__(struct io_cq)))
+			return -EINVAL;
+
+		snprintf(e->icq_cache_name, sizeof(e->icq_cache_name),
+			 "%s_io_cq", e->elevator_name);
+		e->icq_cache = kmem_cache_create(e->icq_cache_name, e->icq_size,
+						 e->icq_align, 0, NULL);
+		if (!e->icq_cache)
+			return -ENOMEM;
+	}
+
+	/* register, don't allow duplicate names */
+	spin_lock(&elv_list_lock);
+	if (__elevator_find(e->elevator_name)) {
+		spin_unlock(&elv_list_lock);
+		kmem_cache_destroy(e->icq_cache);
+		return -EBUSY;
+	}
+	list_add_tail(&e->list, &elv_list);
+	spin_unlock(&elv_list_lock);
+
+	printk(KERN_INFO "io scheduler %s registered\n", e->elevator_name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(elv_register);
+
+void elv_unregister(struct elevator_type *e)
+{
+	/* unregister */
+	spin_lock(&elv_list_lock);
+	list_del_init(&e->list);
+	spin_unlock(&elv_list_lock);
+
+	/*
+	 * Destroy icq_cache if it exists.  icq's are RCU managed.  Make
+	 * sure all RCU operations are complete before proceeding.
+	 */
+	if (e->icq_cache) {
+		rcu_barrier();
+		kmem_cache_destroy(e->icq_cache);
+		e->icq_cache = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(elv_unregister);
+
+static inline bool elv_support_iosched(struct request_queue *q)
+{
+	if (!queue_is_mq(q) ||
+	    (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)))
+		return false;
+	return true;
+}
+
+/*
+ * For single queue devices, default to using mq-deadline. If we have multiple
+ * queues or mq-deadline is not available, default to "none".
+ */
+static struct elevator_type *elevator_get_default(struct request_queue *q)
+{
+	if (q->tag_set && q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT)
+		return NULL;
+
+	if (q->nr_hw_queues != 1 &&
+	    !blk_mq_is_shared_tags(q->tag_set->flags))
+		return NULL;
+
+	return elevator_find_get(q, "mq-deadline");
+}
+
+/*
+ * Get the first elevator providing the features required by the request queue.
+ * Default to "none" if no matching elevator is found.
+ */
+static struct elevator_type *elevator_get_by_features(struct request_queue *q)
+{
+	struct elevator_type *e, *found = NULL;
+
+	spin_lock(&elv_list_lock);
+
+	list_for_each_entry(e, &elv_list, list) {
+		if (elv_support_features(q, e)) {
+			found = e;
+			break;
+		}
+	}
+
+	if (found && !elevator_tryget(found))
+		found = NULL;
+
+	spin_unlock(&elv_list_lock);
+	return found;
+}
+
+/*
+ * For a device queue that has no required features, use the default elevator
+ * settings. Otherwise, use the first elevator available matching the required
+ * features. If no suitable elevator is find or if the chosen elevator
+ * initialization fails, fall back to the "none" elevator (no elevator).
+ */
+void elevator_init_mq(struct request_queue *q)
+{
+	struct elevator_type *e;
+	int err;
+
+	if (!elv_support_iosched(q))
+		return;
+
+	WARN_ON_ONCE(blk_queue_registered(q));
+
+	if (unlikely(q->elevator))
+		return;
+
+	if (!q->required_elevator_features)
+		e = elevator_get_default(q);
+	else
+		e = elevator_get_by_features(q);
+	if (!e)
+		return;
+
+	/*
+	 * We are called before adding disk, when there isn't any FS I/O,
+	 * so freezing queue plus canceling dispatch work is enough to
+	 * drain any dispatch activities originated from passthrough
+	 * requests, then no need to quiesce queue which may add long boot
+	 * latency, especially when lots of disks are involved.
+	 */
+	blk_mq_freeze_queue(q);
+	blk_mq_cancel_work_sync(q);
+
+	err = blk_mq_init_sched(q, e);
+
+	blk_mq_unfreeze_queue(q);
+
+	if (err) {
+		pr_warn("\"%s\" elevator initialization failed, "
+			"falling back to \"none\"\n", e->elevator_name);
+	}
+
+	elevator_put(e);
+}
+
+/*
+ * Switch to new_e io scheduler.
+ *
+ * If switching fails, we are most likely running out of memory and not able
+ * to restore the old io scheduler, so leaving the io scheduler being none.
+ */
+int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
+{
+	int ret;
+
+	lockdep_assert_held(&q->sysfs_lock);
+
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
+
+	if (q->elevator) {
+		elv_unregister_queue(q);
+		elevator_exit(q);
+	}
+
+	ret = blk_mq_init_sched(q, new_e);
+	if (ret)
+		goto out_unfreeze;
+
+	ret = elv_register_queue(q, true);
+	if (ret) {
+		elevator_exit(q);
+		goto out_unfreeze;
+	}
+	blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+
+out_unfreeze:
+	blk_mq_unquiesce_queue(q);
+	blk_mq_unfreeze_queue(q);
+
+	if (ret) {
+		pr_warn("elv: switch to \"%s\" failed, falling back to \"none\"\n",
+			new_e->elevator_name);
+	}
+
+	return ret;
+}
+
+void elevator_disable(struct request_queue *q)
+{
+	lockdep_assert_held(&q->sysfs_lock);
+
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
+
+	elv_unregister_queue(q);
+	elevator_exit(q);
+	blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
+	q->elevator = NULL;
+	q->nr_requests = q->tag_set->queue_depth;
+	blk_add_trace_msg(q, "elv switch: none");
+
+	blk_mq_unquiesce_queue(q);
+	blk_mq_unfreeze_queue(q);
+}
+
+/*
+ * Switch this queue to the given IO scheduler.
+ */
+static int elevator_change(struct request_queue *q, const char *elevator_name)
+{
+	struct elevator_type *e;
+	int ret;
+
+	/* Make sure queue is not in the middle of being removed */
+	if (!blk_queue_registered(q))
+		return -ENOENT;
+
+	if (!strncmp(elevator_name, "none", 4)) {
+		if (q->elevator)
+			elevator_disable(q);
+		return 0;
+	}
+
+	if (q->elevator && elevator_match(q->elevator->type, elevator_name))
+		return 0;
+
+	e = elevator_find_get(q, elevator_name);
+	if (!e) {
+		request_module("%s-iosched", elevator_name);
+		e = elevator_find_get(q, elevator_name);
+		if (!e)
+			return -EINVAL;
+	}
+	ret = elevator_switch(q, e);
+	elevator_put(e);
+	return ret;
+}
+
+ssize_t elv_iosched_store(struct request_queue *q, const char *buf,
+			  size_t count)
+{
+	char elevator_name[ELV_NAME_MAX];
+	int ret;
+
+	if (!elv_support_iosched(q))
+		return count;
+
+	strlcpy(elevator_name, buf, sizeof(elevator_name));
+	ret = elevator_change(q, strstrip(elevator_name));
+	if (!ret)
+		return count;
+	return ret;
+}
+
+ssize_t elv_iosched_show(struct request_queue *q, char *name)
+{
+	struct elevator_queue *eq = q->elevator;
+	struct elevator_type *cur = NULL, *e;
+	int len = 0;
+
+	if (!elv_support_iosched(q))
+		return sprintf(name, "none\n");
+
+	if (!q->elevator) {
+		len += sprintf(name+len, "[none] ");
+	} else {
+		len += sprintf(name+len, "none ");
+		cur = eq->type;
+	}
+
+	spin_lock(&elv_list_lock);
+	list_for_each_entry(e, &elv_list, list) {
+		if (e == cur)
+			len += sprintf(name+len, "[%s] ", e->elevator_name);
+		else if (elv_support_features(q, e))
+			len += sprintf(name+len, "%s ", e->elevator_name);
+	}
+	spin_unlock(&elv_list_lock);
+
+	len += sprintf(name+len, "\n");
+	return len;
+}
+
+struct request *elv_rb_former_request(struct request_queue *q,
+				      struct request *rq)
+{
+	struct rb_node *rbprev = rb_prev(&rq->rb_node);
+
+	if (rbprev)
+		return rb_entry_rq(rbprev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_former_request);
+
+struct request *elv_rb_latter_request(struct request_queue *q,
+				      struct request *rq)
+{
+	struct rb_node *rbnext = rb_next(&rq->rb_node);
+
+	if (rbnext)
+		return rb_entry_rq(rbnext);
+
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_latter_request);
+
+static int __init elevator_setup(char *str)
+{
+	pr_warn("Kernel parameter elevator= does not have any effect anymore.\n"
+		"Please use sysfs to set IO scheduler for individual devices.\n");
+	return 1;
+}
+
+__setup("elevator=", elevator_setup);