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, 1227 insertions, 0 deletions

diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c
new file mode 100644
index 000000000..b3d7d6d8d
--- /dev/null
+++ b/drivers/mmc/host/cqhci-core.c
@@ -0,0 +1,1227 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/delay.h>
+#include <linux/highmem.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/platform_device.h>
+#include <linux/ktime.h>
+
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+
+#include "cqhci.h"
+#include "cqhci-crypto.h"
+
+#define DCMD_SLOT 31
+#define NUM_SLOTS 32
+
+struct cqhci_slot {
+	struct mmc_request *mrq;
+	unsigned int flags;
+#define CQHCI_EXTERNAL_TIMEOUT	BIT(0)
+#define CQHCI_COMPLETED		BIT(1)
+#define CQHCI_HOST_CRC		BIT(2)
+#define CQHCI_HOST_TIMEOUT	BIT(3)
+#define CQHCI_HOST_OTHER	BIT(4)
+};
+
+static inline u8 *get_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	return cq_host->desc_base + (tag * cq_host->slot_sz);
+}
+
+static inline u8 *get_link_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	u8 *desc = get_desc(cq_host, tag);
+
+	return desc + cq_host->task_desc_len;
+}
+
+static inline size_t get_trans_desc_offset(struct cqhci_host *cq_host, u8 tag)
+{
+	return cq_host->trans_desc_len * cq_host->mmc->max_segs * tag;
+}
+
+static inline dma_addr_t get_trans_desc_dma(struct cqhci_host *cq_host, u8 tag)
+{
+	size_t offset = get_trans_desc_offset(cq_host, tag);
+
+	return cq_host->trans_desc_dma_base + offset;
+}
+
+static inline u8 *get_trans_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	size_t offset = get_trans_desc_offset(cq_host, tag);
+
+	return cq_host->trans_desc_base + offset;
+}
+
+static void setup_trans_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	u8 *link_temp;
+	dma_addr_t trans_temp;
+
+	link_temp = get_link_desc(cq_host, tag);
+	trans_temp = get_trans_desc_dma(cq_host, tag);
+
+	memset(link_temp, 0, cq_host->link_desc_len);
+	if (cq_host->link_desc_len > 8)
+		*(link_temp + 8) = 0;
+
+	if (tag == DCMD_SLOT && (cq_host->mmc->caps2 & MMC_CAP2_CQE_DCMD)) {
+		*link_temp = CQHCI_VALID(0) | CQHCI_ACT(0) | CQHCI_END(1);
+		return;
+	}
+
+	*link_temp = CQHCI_VALID(1) | CQHCI_ACT(0x6) | CQHCI_END(0);
+
+	if (cq_host->dma64) {
+		__le64 *data_addr = (__le64 __force *)(link_temp + 4);
+
+		data_addr[0] = cpu_to_le64(trans_temp);
+	} else {
+		__le32 *data_addr = (__le32 __force *)(link_temp + 4);
+
+		data_addr[0] = cpu_to_le32(trans_temp);
+	}
+}
+
+static void cqhci_set_irqs(struct cqhci_host *cq_host, u32 set)
+{
+	cqhci_writel(cq_host, set, CQHCI_ISTE);
+	cqhci_writel(cq_host, set, CQHCI_ISGE);
+}
+
+#define DRV_NAME "cqhci"
+
+#define CQHCI_DUMP(f, x...) \
+	pr_err("%s: " DRV_NAME ": " f, mmc_hostname(mmc), ## x)
+
+static void cqhci_dumpregs(struct cqhci_host *cq_host)
+{
+	struct mmc_host *mmc = cq_host->mmc;
+
+	CQHCI_DUMP("============ CQHCI REGISTER DUMP ===========\n");
+
+	CQHCI_DUMP("Caps:      0x%08x | Version:  0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_CAP),
+		   cqhci_readl(cq_host, CQHCI_VER));
+	CQHCI_DUMP("Config:    0x%08x | Control:  0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_CFG),
+		   cqhci_readl(cq_host, CQHCI_CTL));
+	CQHCI_DUMP("Int stat:  0x%08x | Int enab: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_IS),
+		   cqhci_readl(cq_host, CQHCI_ISTE));
+	CQHCI_DUMP("Int sig:   0x%08x | Int Coal: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_ISGE),
+		   cqhci_readl(cq_host, CQHCI_IC));
+	CQHCI_DUMP("TDL base:  0x%08x | TDL up32: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_TDLBA),
+		   cqhci_readl(cq_host, CQHCI_TDLBAU));
+	CQHCI_DUMP("Doorbell:  0x%08x | TCN:      0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_TDBR),
+		   cqhci_readl(cq_host, CQHCI_TCN));
+	CQHCI_DUMP("Dev queue: 0x%08x | Dev Pend: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_DQS),
+		   cqhci_readl(cq_host, CQHCI_DPT));
+	CQHCI_DUMP("Task clr:  0x%08x | SSC1:     0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_TCLR),
+		   cqhci_readl(cq_host, CQHCI_SSC1));
+	CQHCI_DUMP("SSC2:      0x%08x | DCMD rsp: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_SSC2),
+		   cqhci_readl(cq_host, CQHCI_CRDCT));
+	CQHCI_DUMP("RED mask:  0x%08x | TERRI:    0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_RMEM),
+		   cqhci_readl(cq_host, CQHCI_TERRI));
+	CQHCI_DUMP("Resp idx:  0x%08x | Resp arg: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_CRI),
+		   cqhci_readl(cq_host, CQHCI_CRA));
+
+	if (cq_host->ops->dumpregs)
+		cq_host->ops->dumpregs(mmc);
+	else
+		CQHCI_DUMP(": ===========================================\n");
+}
+
+/*
+ * The allocated descriptor table for task, link & transfer descriptors
+ * looks like:
+ * |----------|
+ * |task desc |  |->|----------|
+ * |----------|  |  |trans desc|
+ * |link desc-|->|  |----------|
+ * |----------|          .
+ *      .                .
+ *  no. of slots      max-segs
+ *      .           |----------|
+ * |----------|
+ * The idea here is to create the [task+trans] table and mark & point the
+ * link desc to the transfer desc table on a per slot basis.
+ */
+static int cqhci_host_alloc_tdl(struct cqhci_host *cq_host)
+{
+	int i = 0;
+
+	/* task descriptor can be 64/128 bit irrespective of arch */
+	if (cq_host->caps & CQHCI_TASK_DESC_SZ_128) {
+		cqhci_writel(cq_host, cqhci_readl(cq_host, CQHCI_CFG) |
+			       CQHCI_TASK_DESC_SZ, CQHCI_CFG);
+		cq_host->task_desc_len = 16;
+	} else {
+		cq_host->task_desc_len = 8;
+	}
+
+	/*
+	 * 96 bits length of transfer desc instead of 128 bits which means
+	 * ADMA would expect next valid descriptor at the 96th bit
+	 * or 128th bit
+	 */
+	if (cq_host->dma64) {
+		if (cq_host->quirks & CQHCI_QUIRK_SHORT_TXFR_DESC_SZ)
+			cq_host->trans_desc_len = 12;
+		else
+			cq_host->trans_desc_len = 16;
+		cq_host->link_desc_len = 16;
+	} else {
+		cq_host->trans_desc_len = 8;
+		cq_host->link_desc_len = 8;
+	}
+
+	/* total size of a slot: 1 task & 1 transfer (link) */
+	cq_host->slot_sz = cq_host->task_desc_len + cq_host->link_desc_len;
+
+	cq_host->desc_size = cq_host->slot_sz * cq_host->num_slots;
+
+	cq_host->data_size = get_trans_desc_offset(cq_host, cq_host->mmc->cqe_qdepth);
+
+	pr_debug("%s: cqhci: desc_size: %zu data_sz: %zu slot-sz: %d\n",
+		 mmc_hostname(cq_host->mmc), cq_host->desc_size, cq_host->data_size,
+		 cq_host->slot_sz);
+
+	/*
+	 * allocate a dma-mapped chunk of memory for the descriptors
+	 * allocate a dma-mapped chunk of memory for link descriptors
+	 * setup each link-desc memory offset per slot-number to
+	 * the descriptor table.
+	 */
+	cq_host->desc_base = dmam_alloc_coherent(mmc_dev(cq_host->mmc),
+						 cq_host->desc_size,
+						 &cq_host->desc_dma_base,
+						 GFP_KERNEL);
+	if (!cq_host->desc_base)
+		return -ENOMEM;
+
+	cq_host->trans_desc_base = dmam_alloc_coherent(mmc_dev(cq_host->mmc),
+					      cq_host->data_size,
+					      &cq_host->trans_desc_dma_base,
+					      GFP_KERNEL);
+	if (!cq_host->trans_desc_base) {
+		dmam_free_coherent(mmc_dev(cq_host->mmc), cq_host->desc_size,
+				   cq_host->desc_base,
+				   cq_host->desc_dma_base);
+		cq_host->desc_base = NULL;
+		cq_host->desc_dma_base = 0;
+		return -ENOMEM;
+	}
+
+	pr_debug("%s: cqhci: desc-base: 0x%p trans-base: 0x%p\n desc_dma 0x%llx trans_dma: 0x%llx\n",
+		 mmc_hostname(cq_host->mmc), cq_host->desc_base, cq_host->trans_desc_base,
+		(unsigned long long)cq_host->desc_dma_base,
+		(unsigned long long)cq_host->trans_desc_dma_base);
+
+	for (; i < (cq_host->num_slots); i++)
+		setup_trans_desc(cq_host, i);
+
+	return 0;
+}
+
+static void __cqhci_enable(struct cqhci_host *cq_host)
+{
+	struct mmc_host *mmc = cq_host->mmc;
+	u32 cqcfg;
+
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+
+	/* Configuration must not be changed while enabled */
+	if (cqcfg & CQHCI_ENABLE) {
+		cqcfg &= ~CQHCI_ENABLE;
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+	}
+
+	cqcfg &= ~(CQHCI_DCMD | CQHCI_TASK_DESC_SZ);
+
+	if (mmc->caps2 & MMC_CAP2_CQE_DCMD)
+		cqcfg |= CQHCI_DCMD;
+
+	if (cq_host->caps & CQHCI_TASK_DESC_SZ_128)
+		cqcfg |= CQHCI_TASK_DESC_SZ;
+
+	if (mmc->caps2 & MMC_CAP2_CRYPTO)
+		cqcfg |= CQHCI_CRYPTO_GENERAL_ENABLE;
+
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cqhci_writel(cq_host, lower_32_bits(cq_host->desc_dma_base),
+		     CQHCI_TDLBA);
+	cqhci_writel(cq_host, upper_32_bits(cq_host->desc_dma_base),
+		     CQHCI_TDLBAU);
+
+	cqhci_writel(cq_host, cq_host->rca, CQHCI_SSC2);
+
+	cqhci_set_irqs(cq_host, 0);
+
+	cqcfg |= CQHCI_ENABLE;
+
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT)
+		cqhci_writel(cq_host, 0, CQHCI_CTL);
+
+	mmc->cqe_on = true;
+
+	if (cq_host->ops->enable)
+		cq_host->ops->enable(mmc);
+
+	/* Ensure all writes are done before interrupts are enabled */
+	wmb();
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_MASK);
+
+	cq_host->activated = true;
+}
+
+static void __cqhci_disable(struct cqhci_host *cq_host)
+{
+	u32 cqcfg;
+
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	cqcfg &= ~CQHCI_ENABLE;
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cq_host->mmc->cqe_on = false;
+
+	cq_host->activated = false;
+}
+
+int cqhci_deactivate(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	if (cq_host->enabled && cq_host->activated)
+		__cqhci_disable(cq_host);
+
+	return 0;
+}
+EXPORT_SYMBOL(cqhci_deactivate);
+
+int cqhci_resume(struct mmc_host *mmc)
+{
+	/* Re-enable is done upon first request */
+	return 0;
+}
+EXPORT_SYMBOL(cqhci_resume);
+
+static int cqhci_enable(struct mmc_host *mmc, struct mmc_card *card)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	int err;
+
+	if (!card->ext_csd.cmdq_en)
+		return -EINVAL;
+
+	if (cq_host->enabled)
+		return 0;
+
+	cq_host->rca = card->rca;
+
+	err = cqhci_host_alloc_tdl(cq_host);
+	if (err) {
+		pr_err("%s: Failed to enable CQE, error %d\n",
+		       mmc_hostname(mmc), err);
+		return err;
+	}
+
+	__cqhci_enable(cq_host);
+
+	cq_host->enabled = true;
+
+#ifdef DEBUG
+	cqhci_dumpregs(cq_host);
+#endif
+	return 0;
+}
+
+/* CQHCI is idle and should halt immediately, so set a small timeout */
+#define CQHCI_OFF_TIMEOUT 100
+
+static u32 cqhci_read_ctl(struct cqhci_host *cq_host)
+{
+	return cqhci_readl(cq_host, CQHCI_CTL);
+}
+
+static void cqhci_off(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	u32 reg;
+	int err;
+
+	if (!cq_host->enabled || !mmc->cqe_on || cq_host->recovery_halt)
+		return;
+
+	if (cq_host->ops->disable)
+		cq_host->ops->disable(mmc, false);
+
+	cqhci_writel(cq_host, CQHCI_HALT, CQHCI_CTL);
+
+	err = readx_poll_timeout(cqhci_read_ctl, cq_host, reg,
+				 reg & CQHCI_HALT, 0, CQHCI_OFF_TIMEOUT);
+	if (err < 0)
+		pr_err("%s: cqhci: CQE stuck on\n", mmc_hostname(mmc));
+	else
+		pr_debug("%s: cqhci: CQE off\n", mmc_hostname(mmc));
+
+	if (cq_host->ops->post_disable)
+		cq_host->ops->post_disable(mmc);
+
+	mmc->cqe_on = false;
+}
+
+static void cqhci_disable(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	if (!cq_host->enabled)
+		return;
+
+	cqhci_off(mmc);
+
+	__cqhci_disable(cq_host);
+
+	dmam_free_coherent(mmc_dev(mmc), cq_host->data_size,
+			   cq_host->trans_desc_base,
+			   cq_host->trans_desc_dma_base);
+
+	dmam_free_coherent(mmc_dev(mmc), cq_host->desc_size,
+			   cq_host->desc_base,
+			   cq_host->desc_dma_base);
+
+	cq_host->trans_desc_base = NULL;
+	cq_host->desc_base = NULL;
+
+	cq_host->enabled = false;
+}
+
+static void cqhci_prep_task_desc(struct mmc_request *mrq,
+				 struct cqhci_host *cq_host, int tag)
+{
+	__le64 *task_desc = (__le64 __force *)get_desc(cq_host, tag);
+	u32 req_flags = mrq->data->flags;
+	u64 desc0;
+
+	desc0 = CQHCI_VALID(1) |
+		CQHCI_END(1) |
+		CQHCI_INT(1) |
+		CQHCI_ACT(0x5) |
+		CQHCI_FORCED_PROG(!!(req_flags & MMC_DATA_FORCED_PRG)) |
+		CQHCI_DATA_TAG(!!(req_flags & MMC_DATA_DAT_TAG)) |
+		CQHCI_DATA_DIR(!!(req_flags & MMC_DATA_READ)) |
+		CQHCI_PRIORITY(!!(req_flags & MMC_DATA_PRIO)) |
+		CQHCI_QBAR(!!(req_flags & MMC_DATA_QBR)) |
+		CQHCI_REL_WRITE(!!(req_flags & MMC_DATA_REL_WR)) |
+		CQHCI_BLK_COUNT(mrq->data->blocks) |
+		CQHCI_BLK_ADDR((u64)mrq->data->blk_addr);
+
+	task_desc[0] = cpu_to_le64(desc0);
+
+	if (cq_host->caps & CQHCI_TASK_DESC_SZ_128) {
+		u64 desc1 = cqhci_crypto_prep_task_desc(mrq);
+
+		task_desc[1] = cpu_to_le64(desc1);
+
+		pr_debug("%s: cqhci: tag %d task descriptor 0x%016llx%016llx\n",
+			 mmc_hostname(mrq->host), mrq->tag, desc1, desc0);
+	} else {
+		pr_debug("%s: cqhci: tag %d task descriptor 0x%016llx\n",
+			 mmc_hostname(mrq->host), mrq->tag, desc0);
+	}
+}
+
+static int cqhci_dma_map(struct mmc_host *host, struct mmc_request *mrq)
+{
+	int sg_count;
+	struct mmc_data *data = mrq->data;
+
+	if (!data)
+		return -EINVAL;
+
+	sg_count = dma_map_sg(mmc_dev(host), data->sg,
+			      data->sg_len,
+			      (data->flags & MMC_DATA_WRITE) ?
+			      DMA_TO_DEVICE : DMA_FROM_DEVICE);
+	if (!sg_count) {
+		pr_err("%s: sg-len: %d\n", __func__, data->sg_len);
+		return -ENOMEM;
+	}
+
+	return sg_count;
+}
+
+static void cqhci_set_tran_desc(u8 *desc, dma_addr_t addr, int len, bool end,
+				bool dma64)
+{
+	__le32 *attr = (__le32 __force *)desc;
+
+	*attr = (CQHCI_VALID(1) |
+		 CQHCI_END(end ? 1 : 0) |
+		 CQHCI_INT(0) |
+		 CQHCI_ACT(0x4) |
+		 CQHCI_DAT_LENGTH(len));
+
+	if (dma64) {
+		__le64 *dataddr = (__le64 __force *)(desc + 4);
+
+		dataddr[0] = cpu_to_le64(addr);
+	} else {
+		__le32 *dataddr = (__le32 __force *)(desc + 4);
+
+		dataddr[0] = cpu_to_le32(addr);
+	}
+}
+
+static int cqhci_prep_tran_desc(struct mmc_request *mrq,
+			       struct cqhci_host *cq_host, int tag)
+{
+	struct mmc_data *data = mrq->data;
+	int i, sg_count, len;
+	bool end = false;
+	bool dma64 = cq_host->dma64;
+	dma_addr_t addr;
+	u8 *desc;
+	struct scatterlist *sg;
+
+	sg_count = cqhci_dma_map(mrq->host, mrq);
+	if (sg_count < 0) {
+		pr_err("%s: %s: unable to map sg lists, %d\n",
+				mmc_hostname(mrq->host), __func__, sg_count);
+		return sg_count;
+	}
+
+	desc = get_trans_desc(cq_host, tag);
+
+	for_each_sg(data->sg, sg, sg_count, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+
+		if ((i+1) == sg_count)
+			end = true;
+		cqhci_set_tran_desc(desc, addr, len, end, dma64);
+		desc += cq_host->trans_desc_len;
+	}
+
+	return 0;
+}
+
+static void cqhci_prep_dcmd_desc(struct mmc_host *mmc,
+				   struct mmc_request *mrq)
+{
+	u64 *task_desc = NULL;
+	u64 data = 0;
+	u8 resp_type;
+	u8 *desc;
+	__le64 *dataddr;
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	u8 timing;
+
+	if (!(mrq->cmd->flags & MMC_RSP_PRESENT)) {
+		resp_type = 0x0;
+		timing = 0x1;
+	} else {
+		if (mrq->cmd->flags & MMC_RSP_R1B) {
+			resp_type = 0x3;
+			timing = 0x0;
+		} else {
+			resp_type = 0x2;
+			timing = 0x1;
+		}
+	}
+
+	task_desc = (__le64 __force *)get_desc(cq_host, cq_host->dcmd_slot);
+	memset(task_desc, 0, cq_host->task_desc_len);
+	data |= (CQHCI_VALID(1) |
+		 CQHCI_END(1) |
+		 CQHCI_INT(1) |
+		 CQHCI_QBAR(1) |
+		 CQHCI_ACT(0x5) |
+		 CQHCI_CMD_INDEX(mrq->cmd->opcode) |
+		 CQHCI_CMD_TIMING(timing) | CQHCI_RESP_TYPE(resp_type));
+	if (cq_host->ops->update_dcmd_desc)
+		cq_host->ops->update_dcmd_desc(mmc, mrq, &data);
+	*task_desc |= data;
+	desc = (u8 *)task_desc;
+	pr_debug("%s: cqhci: dcmd: cmd: %d timing: %d resp: %d\n",
+		 mmc_hostname(mmc), mrq->cmd->opcode, timing, resp_type);
+	dataddr = (__le64 __force *)(desc + 4);
+	dataddr[0] = cpu_to_le64((u64)mrq->cmd->arg);
+
+}
+
+static void cqhci_post_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (data) {
+		dma_unmap_sg(mmc_dev(host), data->sg, data->sg_len,
+			     (data->flags & MMC_DATA_READ) ?
+			     DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static inline int cqhci_tag(struct mmc_request *mrq)
+{
+	return mrq->cmd ? DCMD_SLOT : mrq->tag;
+}
+
+static int cqhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	int err = 0;
+	int tag = cqhci_tag(mrq);
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	unsigned long flags;
+
+	if (!cq_host->enabled) {
+		pr_err("%s: cqhci: not enabled\n", mmc_hostname(mmc));
+		return -EINVAL;
+	}
+
+	/* First request after resume has to re-enable */
+	if (!cq_host->activated)
+		__cqhci_enable(cq_host);
+
+	if (!mmc->cqe_on) {
+		if (cq_host->ops->pre_enable)
+			cq_host->ops->pre_enable(mmc);
+
+		cqhci_writel(cq_host, 0, CQHCI_CTL);
+		mmc->cqe_on = true;
+		pr_debug("%s: cqhci: CQE on\n", mmc_hostname(mmc));
+		if (cqhci_readl(cq_host, CQHCI_CTL) && CQHCI_HALT) {
+			pr_err("%s: cqhci: CQE failed to exit halt state\n",
+			       mmc_hostname(mmc));
+		}
+		if (cq_host->ops->enable)
+			cq_host->ops->enable(mmc);
+	}
+
+	if (mrq->data) {
+		cqhci_prep_task_desc(mrq, cq_host, tag);
+
+		err = cqhci_prep_tran_desc(mrq, cq_host, tag);
+		if (err) {
+			pr_err("%s: cqhci: failed to setup tx desc: %d\n",
+			       mmc_hostname(mmc), err);
+			return err;
+		}
+	} else {
+		cqhci_prep_dcmd_desc(mmc, mrq);
+	}
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+
+	if (cq_host->recovery_halt) {
+		err = -EBUSY;
+		goto out_unlock;
+	}
+
+	cq_host->slot[tag].mrq = mrq;
+	cq_host->slot[tag].flags = 0;
+
+	cq_host->qcnt += 1;
+	/* Make sure descriptors are ready before ringing the doorbell */
+	wmb();
+	cqhci_writel(cq_host, 1 << tag, CQHCI_TDBR);
+	if (!(cqhci_readl(cq_host, CQHCI_TDBR) & (1 << tag)))
+		pr_debug("%s: cqhci: doorbell not set for tag %d\n",
+			 mmc_hostname(mmc), tag);
+out_unlock:
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	if (err)
+		cqhci_post_req(mmc, mrq);
+
+	return err;
+}
+
+static void cqhci_recovery_needed(struct mmc_host *mmc, struct mmc_request *mrq,
+				  bool notify)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	if (!cq_host->recovery_halt) {
+		cq_host->recovery_halt = true;
+		pr_debug("%s: cqhci: recovery needed\n", mmc_hostname(mmc));
+		wake_up(&cq_host->wait_queue);
+		if (notify && mrq->recovery_notifier)
+			mrq->recovery_notifier(mrq);
+	}
+}
+
+static unsigned int cqhci_error_flags(int error1, int error2)
+{
+	int error = error1 ? error1 : error2;
+
+	switch (error) {
+	case -EILSEQ:
+		return CQHCI_HOST_CRC;
+	case -ETIMEDOUT:
+		return CQHCI_HOST_TIMEOUT;
+	default:
+		return CQHCI_HOST_OTHER;
+	}
+}
+
+static void cqhci_error_irq(struct mmc_host *mmc, u32 status, int cmd_error,
+			    int data_error)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	struct cqhci_slot *slot;
+	u32 terri;
+	u32 tdpe;
+	int tag;
+
+	spin_lock(&cq_host->lock);
+
+	terri = cqhci_readl(cq_host, CQHCI_TERRI);
+
+	pr_debug("%s: cqhci: error IRQ status: 0x%08x cmd error %d data error %d TERRI: 0x%08x\n",
+		 mmc_hostname(mmc), status, cmd_error, data_error, terri);
+
+	/* Forget about errors when recovery has already been triggered */
+	if (cq_host->recovery_halt)
+		goto out_unlock;
+
+	if (!cq_host->qcnt) {
+		WARN_ONCE(1, "%s: cqhci: error when idle. IRQ status: 0x%08x cmd error %d data error %d TERRI: 0x%08x\n",
+			  mmc_hostname(mmc), status, cmd_error, data_error,
+			  terri);
+		goto out_unlock;
+	}
+
+	if (CQHCI_TERRI_C_VALID(terri)) {
+		tag = CQHCI_TERRI_C_TASK(terri);
+		slot = &cq_host->slot[tag];
+		if (slot->mrq) {
+			slot->flags = cqhci_error_flags(cmd_error, data_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+		}
+	}
+
+	if (CQHCI_TERRI_D_VALID(terri)) {
+		tag = CQHCI_TERRI_D_TASK(terri);
+		slot = &cq_host->slot[tag];
+		if (slot->mrq) {
+			slot->flags = cqhci_error_flags(data_error, cmd_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+		}
+	}
+
+	/*
+	 * Handle ICCE ("Invalid Crypto Configuration Error").  This should
+	 * never happen, since the block layer ensures that all crypto-enabled
+	 * I/O requests have a valid keyslot before they reach the driver.
+	 *
+	 * Note that GCE ("General Crypto Error") is different; it already got
+	 * handled above by checking TERRI.
+	 */
+	if (status & CQHCI_IS_ICCE) {
+		tdpe = cqhci_readl(cq_host, CQHCI_TDPE);
+		WARN_ONCE(1,
+			  "%s: cqhci: invalid crypto configuration error. IRQ status: 0x%08x TDPE: 0x%08x\n",
+			  mmc_hostname(mmc), status, tdpe);
+		while (tdpe != 0) {
+			tag = __ffs(tdpe);
+			tdpe &= ~(1 << tag);
+			slot = &cq_host->slot[tag];
+			if (!slot->mrq)
+				continue;
+			slot->flags = cqhci_error_flags(data_error, cmd_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+		}
+	}
+
+	if (!cq_host->recovery_halt) {
+		/*
+		 * The only way to guarantee forward progress is to mark at
+		 * least one task in error, so if none is indicated, pick one.
+		 */
+		for (tag = 0; tag < NUM_SLOTS; tag++) {
+			slot = &cq_host->slot[tag];
+			if (!slot->mrq)
+				continue;
+			slot->flags = cqhci_error_flags(data_error, cmd_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+			break;
+		}
+	}
+
+out_unlock:
+	spin_unlock(&cq_host->lock);
+}
+
+static void cqhci_finish_mrq(struct mmc_host *mmc, unsigned int tag)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	struct cqhci_slot *slot = &cq_host->slot[tag];
+	struct mmc_request *mrq = slot->mrq;
+	struct mmc_data *data;
+
+	if (!mrq) {
+		WARN_ONCE(1, "%s: cqhci: spurious TCN for tag %d\n",
+			  mmc_hostname(mmc), tag);
+		return;
+	}
+
+	/* No completions allowed during recovery */
+	if (cq_host->recovery_halt) {
+		slot->flags |= CQHCI_COMPLETED;
+		return;
+	}
+
+	slot->mrq = NULL;
+
+	cq_host->qcnt -= 1;
+
+	data = mrq->data;
+	if (data) {
+		if (data->error)
+			data->bytes_xfered = 0;
+		else
+			data->bytes_xfered = data->blksz * data->blocks;
+	}
+
+	mmc_cqe_request_done(mmc, mrq);
+}
+
+irqreturn_t cqhci_irq(struct mmc_host *mmc, u32 intmask, int cmd_error,
+		      int data_error)
+{
+	u32 status;
+	unsigned long tag = 0, comp_status;
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	status = cqhci_readl(cq_host, CQHCI_IS);
+	cqhci_writel(cq_host, status, CQHCI_IS);
+
+	pr_debug("%s: cqhci: IRQ status: 0x%08x\n", mmc_hostname(mmc), status);
+
+	if ((status & (CQHCI_IS_RED | CQHCI_IS_GCE | CQHCI_IS_ICCE)) ||
+	    cmd_error || data_error) {
+		if (status & CQHCI_IS_RED)
+			mmc_debugfs_err_stats_inc(mmc, MMC_ERR_CMDQ_RED);
+		if (status & CQHCI_IS_GCE)
+			mmc_debugfs_err_stats_inc(mmc, MMC_ERR_CMDQ_GCE);
+		if (status & CQHCI_IS_ICCE)
+			mmc_debugfs_err_stats_inc(mmc, MMC_ERR_CMDQ_ICCE);
+		cqhci_error_irq(mmc, status, cmd_error, data_error);
+	}
+
+	if (status & CQHCI_IS_TCC) {
+		/* read TCN and complete the request */
+		comp_status = cqhci_readl(cq_host, CQHCI_TCN);
+		cqhci_writel(cq_host, comp_status, CQHCI_TCN);
+		pr_debug("%s: cqhci: TCN: 0x%08lx\n",
+			 mmc_hostname(mmc), comp_status);
+
+		spin_lock(&cq_host->lock);
+
+		for_each_set_bit(tag, &comp_status, cq_host->num_slots) {
+			/* complete the corresponding mrq */
+			pr_debug("%s: cqhci: completing tag %lu\n",
+				 mmc_hostname(mmc), tag);
+			cqhci_finish_mrq(mmc, tag);
+		}
+
+		if (cq_host->waiting_for_idle && !cq_host->qcnt) {
+			cq_host->waiting_for_idle = false;
+			wake_up(&cq_host->wait_queue);
+		}
+
+		spin_unlock(&cq_host->lock);
+	}
+
+	if (status & CQHCI_IS_TCL)
+		wake_up(&cq_host->wait_queue);
+
+	if (status & CQHCI_IS_HAC)
+		wake_up(&cq_host->wait_queue);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL(cqhci_irq);
+
+static bool cqhci_is_idle(struct cqhci_host *cq_host, int *ret)
+{
+	unsigned long flags;
+	bool is_idle;
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+	is_idle = !cq_host->qcnt || cq_host->recovery_halt;
+	*ret = cq_host->recovery_halt ? -EBUSY : 0;
+	cq_host->waiting_for_idle = !is_idle;
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	return is_idle;
+}
+
+static int cqhci_wait_for_idle(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	int ret;
+
+	wait_event(cq_host->wait_queue, cqhci_is_idle(cq_host, &ret));
+
+	return ret;
+}
+
+static bool cqhci_timeout(struct mmc_host *mmc, struct mmc_request *mrq,
+			  bool *recovery_needed)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	int tag = cqhci_tag(mrq);
+	struct cqhci_slot *slot = &cq_host->slot[tag];
+	unsigned long flags;
+	bool timed_out;
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+	timed_out = slot->mrq == mrq;
+	if (timed_out) {
+		slot->flags |= CQHCI_EXTERNAL_TIMEOUT;
+		cqhci_recovery_needed(mmc, mrq, false);
+		*recovery_needed = cq_host->recovery_halt;
+	}
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	if (timed_out) {
+		pr_err("%s: cqhci: timeout for tag %d, qcnt %d\n",
+		       mmc_hostname(mmc), tag, cq_host->qcnt);
+		cqhci_dumpregs(cq_host);
+	}
+
+	return timed_out;
+}
+
+static bool cqhci_tasks_cleared(struct cqhci_host *cq_host)
+{
+	return !(cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_CLEAR_ALL_TASKS);
+}
+
+static bool cqhci_clear_all_tasks(struct mmc_host *mmc, unsigned int timeout)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	bool ret;
+	u32 ctl;
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_TCL);
+
+	ctl = cqhci_readl(cq_host, CQHCI_CTL);
+	ctl |= CQHCI_CLEAR_ALL_TASKS;
+	cqhci_writel(cq_host, ctl, CQHCI_CTL);
+
+	wait_event_timeout(cq_host->wait_queue, cqhci_tasks_cleared(cq_host),
+			   msecs_to_jiffies(timeout) + 1);
+
+	cqhci_set_irqs(cq_host, 0);
+
+	ret = cqhci_tasks_cleared(cq_host);
+
+	if (!ret)
+		pr_debug("%s: cqhci: Failed to clear tasks\n",
+			 mmc_hostname(mmc));
+
+	return ret;
+}
+
+static bool cqhci_halted(struct cqhci_host *cq_host)
+{
+	return cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT;
+}
+
+static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	bool ret;
+	u32 ctl;
+
+	if (cqhci_halted(cq_host))
+		return true;
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_HAC);
+
+	ctl = cqhci_readl(cq_host, CQHCI_CTL);
+	ctl |= CQHCI_HALT;
+	cqhci_writel(cq_host, ctl, CQHCI_CTL);
+
+	wait_event_timeout(cq_host->wait_queue, cqhci_halted(cq_host),
+			   msecs_to_jiffies(timeout) + 1);
+
+	cqhci_set_irqs(cq_host, 0);
+
+	ret = cqhci_halted(cq_host);
+
+	if (!ret)
+		pr_debug("%s: cqhci: Failed to halt\n", mmc_hostname(mmc));
+
+	return ret;
+}
+
+/*
+ * After halting we expect to be able to use the command line. We interpret the
+ * failure to halt to mean the data lines might still be in use (and the upper
+ * layers will need to send a STOP command), so we set the timeout based on a
+ * generous command timeout.
+ */
+#define CQHCI_START_HALT_TIMEOUT	5
+
+static void cqhci_recovery_start(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	pr_debug("%s: cqhci: %s\n", mmc_hostname(mmc), __func__);
+
+	WARN_ON(!cq_host->recovery_halt);
+
+	cqhci_halt(mmc, CQHCI_START_HALT_TIMEOUT);
+
+	if (cq_host->ops->disable)
+		cq_host->ops->disable(mmc, true);
+
+	mmc->cqe_on = false;
+}
+
+static int cqhci_error_from_flags(unsigned int flags)
+{
+	if (!flags)
+		return 0;
+
+	/* CRC errors might indicate re-tuning so prefer to report that */
+	if (flags & CQHCI_HOST_CRC)
+		return -EILSEQ;
+
+	if (flags & (CQHCI_EXTERNAL_TIMEOUT | CQHCI_HOST_TIMEOUT))
+		return -ETIMEDOUT;
+
+	return -EIO;
+}
+
+static void cqhci_recover_mrq(struct cqhci_host *cq_host, unsigned int tag)
+{
+	struct cqhci_slot *slot = &cq_host->slot[tag];
+	struct mmc_request *mrq = slot->mrq;
+	struct mmc_data *data;
+
+	if (!mrq)
+		return;
+
+	slot->mrq = NULL;
+
+	cq_host->qcnt -= 1;
+
+	data = mrq->data;
+	if (data) {
+		data->bytes_xfered = 0;
+		data->error = cqhci_error_from_flags(slot->flags);
+	} else {
+		mrq->cmd->error = cqhci_error_from_flags(slot->flags);
+	}
+
+	mmc_cqe_request_done(cq_host->mmc, mrq);
+}
+
+static void cqhci_recover_mrqs(struct cqhci_host *cq_host)
+{
+	int i;
+
+	for (i = 0; i < cq_host->num_slots; i++)
+		cqhci_recover_mrq(cq_host, i);
+}
+
+/*
+ * By now the command and data lines should be unused so there is no reason for
+ * CQHCI to take a long time to halt, but if it doesn't halt there could be
+ * problems clearing tasks, so be generous.
+ */
+#define CQHCI_FINISH_HALT_TIMEOUT	20
+
+/* CQHCI could be expected to clear it's internal state pretty quickly */
+#define CQHCI_CLEAR_TIMEOUT		20
+
+static void cqhci_recovery_finish(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	unsigned long flags;
+	u32 cqcfg;
+	bool ok;
+
+	pr_debug("%s: cqhci: %s\n", mmc_hostname(mmc), __func__);
+
+	WARN_ON(!cq_host->recovery_halt);
+
+	ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
+
+	if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
+		ok = false;
+
+	/*
+	 * The specification contradicts itself, by saying that tasks cannot be
+	 * cleared if CQHCI does not halt, but if CQHCI does not halt, it should
+	 * be disabled/re-enabled, but not to disable before clearing tasks.
+	 * Have a go anyway.
+	 */
+	if (!ok) {
+		pr_debug("%s: cqhci: disable / re-enable\n", mmc_hostname(mmc));
+		cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+		cqcfg &= ~CQHCI_ENABLE;
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+		cqcfg |= CQHCI_ENABLE;
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+		/* Be sure that there are no tasks */
+		ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
+		if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
+			ok = false;
+		WARN_ON(!ok);
+	}
+
+	cqhci_recover_mrqs(cq_host);
+
+	WARN_ON(cq_host->qcnt);
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+	cq_host->qcnt = 0;
+	cq_host->recovery_halt = false;
+	mmc->cqe_on = false;
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	/* Ensure all writes are done before interrupts are re-enabled */
+	wmb();
+
+	cqhci_writel(cq_host, CQHCI_IS_HAC | CQHCI_IS_TCL, CQHCI_IS);
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_MASK);
+
+	pr_debug("%s: cqhci: recovery done\n", mmc_hostname(mmc));
+}
+
+static const struct mmc_cqe_ops cqhci_cqe_ops = {
+	.cqe_enable = cqhci_enable,
+	.cqe_disable = cqhci_disable,
+	.cqe_request = cqhci_request,
+	.cqe_post_req = cqhci_post_req,
+	.cqe_off = cqhci_off,
+	.cqe_wait_for_idle = cqhci_wait_for_idle,
+	.cqe_timeout = cqhci_timeout,
+	.cqe_recovery_start = cqhci_recovery_start,
+	.cqe_recovery_finish = cqhci_recovery_finish,
+};
+
+struct cqhci_host *cqhci_pltfm_init(struct platform_device *pdev)
+{
+	struct cqhci_host *cq_host;
+	struct resource *cqhci_memres = NULL;
+
+	/* check and setup CMDQ interface */
+	cqhci_memres = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   "cqhci");
+	if (!cqhci_memres) {
+		dev_dbg(&pdev->dev, "CMDQ not supported\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	cq_host = devm_kzalloc(&pdev->dev, sizeof(*cq_host), GFP_KERNEL);
+	if (!cq_host)
+		return ERR_PTR(-ENOMEM);
+	cq_host->mmio = devm_ioremap(&pdev->dev,
+				     cqhci_memres->start,
+				     resource_size(cqhci_memres));
+	if (!cq_host->mmio) {
+		dev_err(&pdev->dev, "failed to remap cqhci regs\n");
+		return ERR_PTR(-EBUSY);
+	}
+	dev_dbg(&pdev->dev, "CMDQ ioremap: done\n");
+
+	return cq_host;
+}
+EXPORT_SYMBOL(cqhci_pltfm_init);
+
+static unsigned int cqhci_ver_major(struct cqhci_host *cq_host)
+{
+	return CQHCI_VER_MAJOR(cqhci_readl(cq_host, CQHCI_VER));
+}
+
+static unsigned int cqhci_ver_minor(struct cqhci_host *cq_host)
+{
+	u32 ver = cqhci_readl(cq_host, CQHCI_VER);
+
+	return CQHCI_VER_MINOR1(ver) * 10 + CQHCI_VER_MINOR2(ver);
+}
+
+int cqhci_init(struct cqhci_host *cq_host, struct mmc_host *mmc,
+	      bool dma64)
+{
+	int err;
+
+	cq_host->dma64 = dma64;
+	cq_host->mmc = mmc;
+	cq_host->mmc->cqe_private = cq_host;
+
+	cq_host->num_slots = NUM_SLOTS;
+	cq_host->dcmd_slot = DCMD_SLOT;
+
+	mmc->cqe_ops = &cqhci_cqe_ops;
+
+	mmc->cqe_qdepth = NUM_SLOTS;
+	if (mmc->caps2 & MMC_CAP2_CQE_DCMD)
+		mmc->cqe_qdepth -= 1;
+
+	cq_host->slot = devm_kcalloc(mmc_dev(mmc), cq_host->num_slots,
+				     sizeof(*cq_host->slot), GFP_KERNEL);
+	if (!cq_host->slot) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	err = cqhci_crypto_init(cq_host);
+	if (err) {
+		pr_err("%s: CQHCI crypto initialization failed\n",
+		       mmc_hostname(mmc));
+		goto out_err;
+	}
+
+	spin_lock_init(&cq_host->lock);
+
+	init_completion(&cq_host->halt_comp);
+	init_waitqueue_head(&cq_host->wait_queue);
+
+	pr_info("%s: CQHCI version %u.%02u\n",
+		mmc_hostname(mmc), cqhci_ver_major(cq_host),
+		cqhci_ver_minor(cq_host));
+
+	return 0;
+
+out_err:
+	pr_err("%s: CQHCI version %u.%02u failed to initialize, error %d\n",
+	       mmc_hostname(mmc), cqhci_ver_major(cq_host),
+	       cqhci_ver_minor(cq_host), err);
+	return err;
+}
+EXPORT_SYMBOL(cqhci_init);
+
+MODULE_AUTHOR("Venkat Gopalakrishnan <venkatg@codeaurora.org>");
+MODULE_DESCRIPTION("Command Queue Host Controller Interface driver");
+MODULE_LICENSE("GPL v2");