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, 524 insertions, 0 deletions

diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
new file mode 100644
index 000000000..b396e3900
--- /dev/null
+++ b/drivers/mmc/core/queue.c
@@ -0,0 +1,524 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 2003 Russell King, All Rights Reserved.
+ *  Copyright 2006-2007 Pierre Ossman
+ */
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/freezer.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/backing-dev.h>
+
+#include <linux/mmc/card.h>
+#include <linux/mmc/host.h>
+
+#include "queue.h"
+#include "block.h"
+#include "core.h"
+#include "card.h"
+#include "crypto.h"
+#include "host.h"
+
+#define MMC_DMA_MAP_MERGE_SEGMENTS	512
+
+static inline bool mmc_cqe_dcmd_busy(struct mmc_queue *mq)
+{
+	/* Allow only 1 DCMD at a time */
+	return mq->in_flight[MMC_ISSUE_DCMD];
+}
+
+void mmc_cqe_check_busy(struct mmc_queue *mq)
+{
+	if ((mq->cqe_busy & MMC_CQE_DCMD_BUSY) && !mmc_cqe_dcmd_busy(mq))
+		mq->cqe_busy &= ~MMC_CQE_DCMD_BUSY;
+}
+
+static inline bool mmc_cqe_can_dcmd(struct mmc_host *host)
+{
+	return host->caps2 & MMC_CAP2_CQE_DCMD;
+}
+
+static enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
+					      struct request *req)
+{
+	switch (req_op(req)) {
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
+		return MMC_ISSUE_SYNC;
+	case REQ_OP_FLUSH:
+		return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
+	default:
+		return MMC_ISSUE_ASYNC;
+	}
+}
+
+enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_host *host = mq->card->host;
+
+	if (host->cqe_enabled && !host->hsq_enabled)
+		return mmc_cqe_issue_type(host, req);
+
+	if (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_WRITE)
+		return MMC_ISSUE_ASYNC;
+
+	return MMC_ISSUE_SYNC;
+}
+
+static void __mmc_cqe_recovery_notifier(struct mmc_queue *mq)
+{
+	if (!mq->recovery_needed) {
+		mq->recovery_needed = true;
+		schedule_work(&mq->recovery_work);
+	}
+}
+
+void mmc_cqe_recovery_notifier(struct mmc_request *mrq)
+{
+	struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+						  brq.mrq);
+	struct request *req = mmc_queue_req_to_req(mqrq);
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	unsigned long flags;
+
+	spin_lock_irqsave(&mq->lock, flags);
+	__mmc_cqe_recovery_notifier(mq);
+	spin_unlock_irqrestore(&mq->lock, flags);
+}
+
+static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct mmc_queue *mq = req->q->queuedata;
+	struct mmc_host *host = mq->card->host;
+	enum mmc_issue_type issue_type = mmc_issue_type(mq, req);
+	bool recovery_needed = false;
+
+	switch (issue_type) {
+	case MMC_ISSUE_ASYNC:
+	case MMC_ISSUE_DCMD:
+		if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
+			if (recovery_needed)
+				mmc_cqe_recovery_notifier(mrq);
+			return BLK_EH_RESET_TIMER;
+		}
+		/* The request has gone already */
+		return BLK_EH_DONE;
+	default:
+		/* Timeout is handled by mmc core */
+		return BLK_EH_RESET_TIMER;
+	}
+}
+
+static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req)
+{
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	unsigned long flags;
+	bool ignore_tout;
+
+	spin_lock_irqsave(&mq->lock, flags);
+	ignore_tout = mq->recovery_needed || !host->cqe_enabled || host->hsq_enabled;
+	spin_unlock_irqrestore(&mq->lock, flags);
+
+	return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req);
+}
+
+static void mmc_mq_recovery_handler(struct work_struct *work)
+{
+	struct mmc_queue *mq = container_of(work, struct mmc_queue,
+					    recovery_work);
+	struct request_queue *q = mq->queue;
+	struct mmc_host *host = mq->card->host;
+
+	mmc_get_card(mq->card, &mq->ctx);
+
+	mq->in_recovery = true;
+
+	if (host->cqe_enabled && !host->hsq_enabled)
+		mmc_blk_cqe_recovery(mq);
+	else
+		mmc_blk_mq_recovery(mq);
+
+	mq->in_recovery = false;
+
+	spin_lock_irq(&mq->lock);
+	mq->recovery_needed = false;
+	spin_unlock_irq(&mq->lock);
+
+	if (host->hsq_enabled)
+		host->cqe_ops->cqe_recovery_finish(host);
+
+	mmc_put_card(mq->card, &mq->ctx);
+
+	blk_mq_run_hw_queues(q, true);
+}
+
+static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp)
+{
+	struct scatterlist *sg;
+
+	sg = kmalloc_array(sg_len, sizeof(*sg), gfp);
+	if (sg)
+		sg_init_table(sg, sg_len);
+
+	return sg;
+}
+
+static void mmc_queue_setup_discard(struct request_queue *q,
+				    struct mmc_card *card)
+{
+	unsigned max_discard;
+
+	max_discard = mmc_calc_max_discard(card);
+	if (!max_discard)
+		return;
+
+	blk_queue_max_discard_sectors(q, max_discard);
+	q->limits.discard_granularity = card->pref_erase << 9;
+	/* granularity must not be greater than max. discard */
+	if (card->pref_erase > max_discard)
+		q->limits.discard_granularity = SECTOR_SIZE;
+	if (mmc_can_secure_erase_trim(card))
+		blk_queue_max_secure_erase_sectors(q, max_discard);
+	if (mmc_can_trim(card) && card->erased_byte == 0)
+		blk_queue_max_write_zeroes_sectors(q, max_discard);
+}
+
+static unsigned short mmc_get_max_segments(struct mmc_host *host)
+{
+	return host->can_dma_map_merge ? MMC_DMA_MAP_MERGE_SEGMENTS :
+					 host->max_segs;
+}
+
+static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
+			       unsigned int hctx_idx, unsigned int numa_node)
+{
+	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
+	struct mmc_queue *mq = set->driver_data;
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+
+	mq_rq->sg = mmc_alloc_sg(mmc_get_max_segments(host), GFP_KERNEL);
+	if (!mq_rq->sg)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
+				unsigned int hctx_idx)
+{
+	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
+
+	kfree(mq_rq->sg);
+	mq_rq->sg = NULL;
+}
+
+static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+				    const struct blk_mq_queue_data *bd)
+{
+	struct request *req = bd->rq;
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	enum mmc_issue_type issue_type;
+	enum mmc_issued issued;
+	bool get_card, cqe_retune_ok;
+	blk_status_t ret;
+
+	if (mmc_card_removed(mq->card)) {
+		req->rq_flags |= RQF_QUIET;
+		return BLK_STS_IOERR;
+	}
+
+	issue_type = mmc_issue_type(mq, req);
+
+	spin_lock_irq(&mq->lock);
+
+	if (mq->recovery_needed || mq->busy) {
+		spin_unlock_irq(&mq->lock);
+		return BLK_STS_RESOURCE;
+	}
+
+	switch (issue_type) {
+	case MMC_ISSUE_DCMD:
+		if (mmc_cqe_dcmd_busy(mq)) {
+			mq->cqe_busy |= MMC_CQE_DCMD_BUSY;
+			spin_unlock_irq(&mq->lock);
+			return BLK_STS_RESOURCE;
+		}
+		break;
+	case MMC_ISSUE_ASYNC:
+		/*
+		 * For MMC host software queue, we only allow 2 requests in
+		 * flight to avoid a long latency.
+		 */
+		if (host->hsq_enabled && mq->in_flight[issue_type] > 2) {
+			spin_unlock_irq(&mq->lock);
+			return BLK_STS_RESOURCE;
+		}
+		break;
+	default:
+		/*
+		 * Timeouts are handled by mmc core, and we don't have a host
+		 * API to abort requests, so we can't handle the timeout anyway.
+		 * However, when the timeout happens, blk_mq_complete_request()
+		 * no longer works (to stop the request disappearing under us).
+		 * To avoid racing with that, set a large timeout.
+		 */
+		req->timeout = 600 * HZ;
+		break;
+	}
+
+	/* Parallel dispatch of requests is not supported at the moment */
+	mq->busy = true;
+
+	mq->in_flight[issue_type] += 1;
+	get_card = (mmc_tot_in_flight(mq) == 1);
+	cqe_retune_ok = (mmc_cqe_qcnt(mq) == 1);
+
+	spin_unlock_irq(&mq->lock);
+
+	if (!(req->rq_flags & RQF_DONTPREP)) {
+		req_to_mmc_queue_req(req)->retries = 0;
+		req->rq_flags |= RQF_DONTPREP;
+	}
+
+	if (get_card)
+		mmc_get_card(card, &mq->ctx);
+
+	if (host->cqe_enabled) {
+		host->retune_now = host->need_retune && cqe_retune_ok &&
+				   !host->hold_retune;
+	}
+
+	blk_mq_start_request(req);
+
+	issued = mmc_blk_mq_issue_rq(mq, req);
+
+	switch (issued) {
+	case MMC_REQ_BUSY:
+		ret = BLK_STS_RESOURCE;
+		break;
+	case MMC_REQ_FAILED_TO_START:
+		ret = BLK_STS_IOERR;
+		break;
+	default:
+		ret = BLK_STS_OK;
+		break;
+	}
+
+	if (issued != MMC_REQ_STARTED) {
+		bool put_card = false;
+
+		spin_lock_irq(&mq->lock);
+		mq->in_flight[issue_type] -= 1;
+		if (mmc_tot_in_flight(mq) == 0)
+			put_card = true;
+		mq->busy = false;
+		spin_unlock_irq(&mq->lock);
+		if (put_card)
+			mmc_put_card(card, &mq->ctx);
+	} else {
+		WRITE_ONCE(mq->busy, false);
+	}
+
+	return ret;
+}
+
+static const struct blk_mq_ops mmc_mq_ops = {
+	.queue_rq	= mmc_mq_queue_rq,
+	.init_request	= mmc_mq_init_request,
+	.exit_request	= mmc_mq_exit_request,
+	.complete	= mmc_blk_mq_complete,
+	.timeout	= mmc_mq_timed_out,
+};
+
+static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	unsigned block_size = 512;
+
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
+	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
+	if (mmc_can_erase(card))
+		mmc_queue_setup_discard(mq->queue, card);
+
+	if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask)
+		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH);
+	blk_queue_max_hw_sectors(mq->queue,
+		min(host->max_blk_count, host->max_req_size / 512));
+	if (host->can_dma_map_merge)
+		WARN(!blk_queue_can_use_dma_map_merging(mq->queue,
+							mmc_dev(host)),
+		     "merging was advertised but not possible");
+	blk_queue_max_segments(mq->queue, mmc_get_max_segments(host));
+
+	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) {
+		block_size = card->ext_csd.data_sector_size;
+		WARN_ON(block_size != 512 && block_size != 4096);
+	}
+
+	blk_queue_logical_block_size(mq->queue, block_size);
+	/*
+	 * After blk_queue_can_use_dma_map_merging() was called with succeed,
+	 * since it calls blk_queue_virt_boundary(), the mmc should not call
+	 * both blk_queue_max_segment_size().
+	 */
+	if (!host->can_dma_map_merge)
+		blk_queue_max_segment_size(mq->queue,
+			round_down(host->max_seg_size, block_size));
+
+	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
+
+	INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
+	INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work);
+
+	mutex_init(&mq->complete_lock);
+
+	init_waitqueue_head(&mq->wait);
+
+	mmc_crypto_setup_queue(mq->queue, host);
+}
+
+static inline bool mmc_merge_capable(struct mmc_host *host)
+{
+	return host->caps2 & MMC_CAP2_MERGE_CAPABLE;
+}
+
+/* Set queue depth to get a reasonable value for q->nr_requests */
+#define MMC_QUEUE_DEPTH 64
+
+/**
+ * mmc_init_queue - initialise a queue structure.
+ * @mq: mmc queue
+ * @card: mmc card to attach this queue
+ *
+ * Initialise a MMC card request queue.
+ */
+struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	struct gendisk *disk;
+	int ret;
+
+	mq->card = card;
+	
+	spin_lock_init(&mq->lock);
+
+	memset(&mq->tag_set, 0, sizeof(mq->tag_set));
+	mq->tag_set.ops = &mmc_mq_ops;
+	/*
+	 * The queue depth for CQE must match the hardware because the request
+	 * tag is used to index the hardware queue.
+	 */
+	if (host->cqe_enabled && !host->hsq_enabled)
+		mq->tag_set.queue_depth =
+			min_t(int, card->ext_csd.cmdq_depth, host->cqe_qdepth);
+	else
+		mq->tag_set.queue_depth = MMC_QUEUE_DEPTH;
+	mq->tag_set.numa_node = NUMA_NO_NODE;
+	mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
+	mq->tag_set.nr_hw_queues = 1;
+	mq->tag_set.cmd_size = sizeof(struct mmc_queue_req);
+	mq->tag_set.driver_data = mq;
+
+	/*
+	 * Since blk_mq_alloc_tag_set() calls .init_request() of mmc_mq_ops,
+	 * the host->can_dma_map_merge should be set before to get max_segs
+	 * from mmc_get_max_segments().
+	 */
+	if (mmc_merge_capable(host) &&
+	    host->max_segs < MMC_DMA_MAP_MERGE_SEGMENTS &&
+	    dma_get_merge_boundary(mmc_dev(host)))
+		host->can_dma_map_merge = 1;
+	else
+		host->can_dma_map_merge = 0;
+
+	ret = blk_mq_alloc_tag_set(&mq->tag_set);
+	if (ret)
+		return ERR_PTR(ret);
+		
+
+	disk = blk_mq_alloc_disk(&mq->tag_set, mq);
+	if (IS_ERR(disk)) {
+		blk_mq_free_tag_set(&mq->tag_set);
+		return disk;
+	}
+	mq->queue = disk->queue;
+
+	if (mmc_host_is_spi(host) && host->use_spi_crc)
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
+	blk_queue_rq_timeout(mq->queue, 60 * HZ);
+
+	mmc_setup_queue(mq, card);
+	return disk;
+}
+
+void mmc_queue_suspend(struct mmc_queue *mq)
+{
+	blk_mq_quiesce_queue(mq->queue);
+
+	/*
+	 * The host remains claimed while there are outstanding requests, so
+	 * simply claiming and releasing here ensures there are none.
+	 */
+	mmc_claim_host(mq->card->host);
+	mmc_release_host(mq->card->host);
+}
+
+void mmc_queue_resume(struct mmc_queue *mq)
+{
+	blk_mq_unquiesce_queue(mq->queue);
+}
+
+void mmc_cleanup_queue(struct mmc_queue *mq)
+{
+	struct request_queue *q = mq->queue;
+
+	/*
+	 * The legacy code handled the possibility of being suspended,
+	 * so do that here too.
+	 */
+	if (blk_queue_quiesced(q))
+		blk_mq_unquiesce_queue(q);
+
+	/*
+	 * If the recovery completes the last (and only remaining) request in
+	 * the queue, and the card has been removed, we could end up here with
+	 * the recovery not quite finished yet, so cancel it.
+	 */
+	cancel_work_sync(&mq->recovery_work);
+
+	blk_mq_free_tag_set(&mq->tag_set);
+
+	/*
+	 * A request can be completed before the next request, potentially
+	 * leaving a complete_work with nothing to do. Such a work item might
+	 * still be queued at this point. Flush it.
+	 */
+	flush_work(&mq->complete_work);
+
+	mq->card = NULL;
+}
+
+/*
+ * Prepare the sg list(s) to be handed of to the host driver
+ */
+unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
+{
+	struct request *req = mmc_queue_req_to_req(mqrq);
+
+	return blk_rq_map_sg(mq->queue, req, mqrq->sg);
+}