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, 624 insertions, 0 deletions

diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c
new file mode 100644
index 000000000..e682bc7ee
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/iova_domain.c
@@ -0,0 +1,624 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MMU-based software IOTLB.
+ *
+ * Copyright (C) 2020-2021 Bytedance Inc. and/or its affiliates. All rights reserved.
+ *
+ * Author: Xie Yongji <xieyongji@bytedance.com>
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/anon_inodes.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+#include <linux/vdpa.h>
+
+#include "iova_domain.h"
+
+static int vduse_iotlb_add_range(struct vduse_iova_domain *domain,
+				 u64 start, u64 last,
+				 u64 addr, unsigned int perm,
+				 struct file *file, u64 offset)
+{
+	struct vdpa_map_file *map_file;
+	int ret;
+
+	map_file = kmalloc(sizeof(*map_file), GFP_ATOMIC);
+	if (!map_file)
+		return -ENOMEM;
+
+	map_file->file = get_file(file);
+	map_file->offset = offset;
+
+	ret = vhost_iotlb_add_range_ctx(domain->iotlb, start, last,
+					addr, perm, map_file);
+	if (ret) {
+		fput(map_file->file);
+		kfree(map_file);
+		return ret;
+	}
+	return 0;
+}
+
+static void vduse_iotlb_del_range(struct vduse_iova_domain *domain,
+				  u64 start, u64 last)
+{
+	struct vdpa_map_file *map_file;
+	struct vhost_iotlb_map *map;
+
+	while ((map = vhost_iotlb_itree_first(domain->iotlb, start, last))) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		fput(map_file->file);
+		kfree(map_file);
+		vhost_iotlb_map_free(domain->iotlb, map);
+	}
+}
+
+int vduse_domain_set_map(struct vduse_iova_domain *domain,
+			 struct vhost_iotlb *iotlb)
+{
+	struct vdpa_map_file *map_file;
+	struct vhost_iotlb_map *map;
+	u64 start = 0ULL, last = ULLONG_MAX;
+	int ret;
+
+	spin_lock(&domain->iotlb_lock);
+	vduse_iotlb_del_range(domain, start, last);
+
+	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
+	     map = vhost_iotlb_itree_next(map, start, last)) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		ret = vduse_iotlb_add_range(domain, map->start, map->last,
+					    map->addr, map->perm,
+					    map_file->file,
+					    map_file->offset);
+		if (ret)
+			goto err;
+	}
+	spin_unlock(&domain->iotlb_lock);
+
+	return 0;
+err:
+	vduse_iotlb_del_range(domain, start, last);
+	spin_unlock(&domain->iotlb_lock);
+	return ret;
+}
+
+void vduse_domain_clear_map(struct vduse_iova_domain *domain,
+			    struct vhost_iotlb *iotlb)
+{
+	struct vhost_iotlb_map *map;
+	u64 start = 0ULL, last = ULLONG_MAX;
+
+	spin_lock(&domain->iotlb_lock);
+	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
+	     map = vhost_iotlb_itree_next(map, start, last)) {
+		vduse_iotlb_del_range(domain, map->start, map->last);
+	}
+	spin_unlock(&domain->iotlb_lock);
+}
+
+static int vduse_domain_map_bounce_page(struct vduse_iova_domain *domain,
+					 u64 iova, u64 size, u64 paddr)
+{
+	struct vduse_bounce_map *map;
+	u64 last = iova + size - 1;
+
+	while (iova <= last) {
+		map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+		if (!map->bounce_page) {
+			map->bounce_page = alloc_page(GFP_ATOMIC);
+			if (!map->bounce_page)
+				return -ENOMEM;
+		}
+		map->orig_phys = paddr;
+		paddr += PAGE_SIZE;
+		iova += PAGE_SIZE;
+	}
+	return 0;
+}
+
+static void vduse_domain_unmap_bounce_page(struct vduse_iova_domain *domain,
+					   u64 iova, u64 size)
+{
+	struct vduse_bounce_map *map;
+	u64 last = iova + size - 1;
+
+	while (iova <= last) {
+		map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+		map->orig_phys = INVALID_PHYS_ADDR;
+		iova += PAGE_SIZE;
+	}
+}
+
+static void do_bounce(phys_addr_t orig, void *addr, size_t size,
+		      enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(orig);
+	unsigned int offset = offset_in_page(orig);
+	struct page *page;
+	unsigned int sz = 0;
+
+	while (size) {
+		sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+		page = pfn_to_page(pfn);
+		if (dir == DMA_TO_DEVICE)
+			memcpy_from_page(addr, page, offset, sz);
+		else
+			memcpy_to_page(page, offset, addr, sz);
+
+		size -= sz;
+		pfn++;
+		addr += sz;
+		offset = 0;
+	}
+}
+
+static void vduse_domain_bounce(struct vduse_iova_domain *domain,
+				dma_addr_t iova, size_t size,
+				enum dma_data_direction dir)
+{
+	struct vduse_bounce_map *map;
+	unsigned int offset;
+	void *addr;
+	size_t sz;
+
+	if (iova >= domain->bounce_size)
+		return;
+
+	while (size) {
+		map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+		offset = offset_in_page(iova);
+		sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+		if (WARN_ON(!map->bounce_page ||
+			    map->orig_phys == INVALID_PHYS_ADDR))
+			return;
+
+		addr = kmap_local_page(map->bounce_page);
+		do_bounce(map->orig_phys + offset, addr + offset, sz, dir);
+		kunmap_local(addr);
+		size -= sz;
+		iova += sz;
+	}
+}
+
+static struct page *
+vduse_domain_get_coherent_page(struct vduse_iova_domain *domain, u64 iova)
+{
+	u64 start = iova & PAGE_MASK;
+	u64 last = start + PAGE_SIZE - 1;
+	struct vhost_iotlb_map *map;
+	struct page *page = NULL;
+
+	spin_lock(&domain->iotlb_lock);
+	map = vhost_iotlb_itree_first(domain->iotlb, start, last);
+	if (!map)
+		goto out;
+
+	page = pfn_to_page((map->addr + iova - map->start) >> PAGE_SHIFT);
+	get_page(page);
+out:
+	spin_unlock(&domain->iotlb_lock);
+
+	return page;
+}
+
+static struct page *
+vduse_domain_get_bounce_page(struct vduse_iova_domain *domain, u64 iova)
+{
+	struct vduse_bounce_map *map;
+	struct page *page = NULL;
+
+	read_lock(&domain->bounce_lock);
+	map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+	if (domain->user_bounce_pages || !map->bounce_page)
+		goto out;
+
+	page = map->bounce_page;
+	get_page(page);
+out:
+	read_unlock(&domain->bounce_lock);
+
+	return page;
+}
+
+static void
+vduse_domain_free_kernel_bounce_pages(struct vduse_iova_domain *domain)
+{
+	struct vduse_bounce_map *map;
+	unsigned long pfn, bounce_pfns;
+
+	bounce_pfns = domain->bounce_size >> PAGE_SHIFT;
+
+	for (pfn = 0; pfn < bounce_pfns; pfn++) {
+		map = &domain->bounce_maps[pfn];
+		if (WARN_ON(map->orig_phys != INVALID_PHYS_ADDR))
+			continue;
+
+		if (!map->bounce_page)
+			continue;
+
+		__free_page(map->bounce_page);
+		map->bounce_page = NULL;
+	}
+}
+
+int vduse_domain_add_user_bounce_pages(struct vduse_iova_domain *domain,
+				       struct page **pages, int count)
+{
+	struct vduse_bounce_map *map;
+	int i, ret;
+
+	/* Now we don't support partial mapping */
+	if (count != (domain->bounce_size >> PAGE_SHIFT))
+		return -EINVAL;
+
+	write_lock(&domain->bounce_lock);
+	ret = -EEXIST;
+	if (domain->user_bounce_pages)
+		goto out;
+
+	for (i = 0; i < count; i++) {
+		map = &domain->bounce_maps[i];
+		if (map->bounce_page) {
+			/* Copy kernel page to user page if it's in use */
+			if (map->orig_phys != INVALID_PHYS_ADDR)
+				memcpy_to_page(pages[i], 0,
+					       page_address(map->bounce_page),
+					       PAGE_SIZE);
+			__free_page(map->bounce_page);
+		}
+		map->bounce_page = pages[i];
+		get_page(pages[i]);
+	}
+	domain->user_bounce_pages = true;
+	ret = 0;
+out:
+	write_unlock(&domain->bounce_lock);
+
+	return ret;
+}
+
+void vduse_domain_remove_user_bounce_pages(struct vduse_iova_domain *domain)
+{
+	struct vduse_bounce_map *map;
+	unsigned long i, count;
+
+	write_lock(&domain->bounce_lock);
+	if (!domain->user_bounce_pages)
+		goto out;
+
+	count = domain->bounce_size >> PAGE_SHIFT;
+	for (i = 0; i < count; i++) {
+		struct page *page = NULL;
+
+		map = &domain->bounce_maps[i];
+		if (WARN_ON(!map->bounce_page))
+			continue;
+
+		/* Copy user page to kernel page if it's in use */
+		if (map->orig_phys != INVALID_PHYS_ADDR) {
+			page = alloc_page(GFP_ATOMIC | __GFP_NOFAIL);
+			memcpy_from_page(page_address(page),
+					 map->bounce_page, 0, PAGE_SIZE);
+		}
+		put_page(map->bounce_page);
+		map->bounce_page = page;
+	}
+	domain->user_bounce_pages = false;
+out:
+	write_unlock(&domain->bounce_lock);
+}
+
+void vduse_domain_reset_bounce_map(struct vduse_iova_domain *domain)
+{
+	if (!domain->bounce_map)
+		return;
+
+	spin_lock(&domain->iotlb_lock);
+	if (!domain->bounce_map)
+		goto unlock;
+
+	vduse_iotlb_del_range(domain, 0, domain->bounce_size - 1);
+	domain->bounce_map = 0;
+unlock:
+	spin_unlock(&domain->iotlb_lock);
+}
+
+static int vduse_domain_init_bounce_map(struct vduse_iova_domain *domain)
+{
+	int ret = 0;
+
+	if (domain->bounce_map)
+		return 0;
+
+	spin_lock(&domain->iotlb_lock);
+	if (domain->bounce_map)
+		goto unlock;
+
+	ret = vduse_iotlb_add_range(domain, 0, domain->bounce_size - 1,
+				    0, VHOST_MAP_RW, domain->file, 0);
+	if (ret)
+		goto unlock;
+
+	domain->bounce_map = 1;
+unlock:
+	spin_unlock(&domain->iotlb_lock);
+	return ret;
+}
+
+static dma_addr_t
+vduse_domain_alloc_iova(struct iova_domain *iovad,
+			unsigned long size, unsigned long limit)
+{
+	unsigned long shift = iova_shift(iovad);
+	unsigned long iova_len = iova_align(iovad, size) >> shift;
+	unsigned long iova_pfn;
+
+	iova_pfn = alloc_iova_fast(iovad, iova_len, limit >> shift, true);
+
+	return (dma_addr_t)iova_pfn << shift;
+}
+
+static void vduse_domain_free_iova(struct iova_domain *iovad,
+				   dma_addr_t iova, size_t size)
+{
+	unsigned long shift = iova_shift(iovad);
+	unsigned long iova_len = iova_align(iovad, size) >> shift;
+
+	free_iova_fast(iovad, iova >> shift, iova_len);
+}
+
+dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
+				 struct page *page, unsigned long offset,
+				 size_t size, enum dma_data_direction dir,
+				 unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->stream_iovad;
+	unsigned long limit = domain->bounce_size - 1;
+	phys_addr_t pa = page_to_phys(page) + offset;
+	dma_addr_t iova = vduse_domain_alloc_iova(iovad, size, limit);
+
+	if (!iova)
+		return DMA_MAPPING_ERROR;
+
+	if (vduse_domain_init_bounce_map(domain))
+		goto err;
+
+	read_lock(&domain->bounce_lock);
+	if (vduse_domain_map_bounce_page(domain, (u64)iova, (u64)size, pa))
+		goto err_unlock;
+
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+		vduse_domain_bounce(domain, iova, size, DMA_TO_DEVICE);
+
+	read_unlock(&domain->bounce_lock);
+
+	return iova;
+err_unlock:
+	read_unlock(&domain->bounce_lock);
+err:
+	vduse_domain_free_iova(iovad, iova, size);
+	return DMA_MAPPING_ERROR;
+}
+
+void vduse_domain_unmap_page(struct vduse_iova_domain *domain,
+			     dma_addr_t dma_addr, size_t size,
+			     enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->stream_iovad;
+
+	read_lock(&domain->bounce_lock);
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		vduse_domain_bounce(domain, dma_addr, size, DMA_FROM_DEVICE);
+
+	vduse_domain_unmap_bounce_page(domain, (u64)dma_addr, (u64)size);
+	read_unlock(&domain->bounce_lock);
+	vduse_domain_free_iova(iovad, dma_addr, size);
+}
+
+void *vduse_domain_alloc_coherent(struct vduse_iova_domain *domain,
+				  size_t size, dma_addr_t *dma_addr,
+				  gfp_t flag, unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->consistent_iovad;
+	unsigned long limit = domain->iova_limit;
+	dma_addr_t iova = vduse_domain_alloc_iova(iovad, size, limit);
+	void *orig = alloc_pages_exact(size, flag);
+
+	if (!iova || !orig)
+		goto err;
+
+	spin_lock(&domain->iotlb_lock);
+	if (vduse_iotlb_add_range(domain, (u64)iova, (u64)iova + size - 1,
+				  virt_to_phys(orig), VHOST_MAP_RW,
+				  domain->file, (u64)iova)) {
+		spin_unlock(&domain->iotlb_lock);
+		goto err;
+	}
+	spin_unlock(&domain->iotlb_lock);
+
+	*dma_addr = iova;
+
+	return orig;
+err:
+	*dma_addr = DMA_MAPPING_ERROR;
+	if (orig)
+		free_pages_exact(orig, size);
+	if (iova)
+		vduse_domain_free_iova(iovad, iova, size);
+
+	return NULL;
+}
+
+void vduse_domain_free_coherent(struct vduse_iova_domain *domain, size_t size,
+				void *vaddr, dma_addr_t dma_addr,
+				unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->consistent_iovad;
+	struct vhost_iotlb_map *map;
+	struct vdpa_map_file *map_file;
+	phys_addr_t pa;
+
+	spin_lock(&domain->iotlb_lock);
+	map = vhost_iotlb_itree_first(domain->iotlb, (u64)dma_addr,
+				      (u64)dma_addr + size - 1);
+	if (WARN_ON(!map)) {
+		spin_unlock(&domain->iotlb_lock);
+		return;
+	}
+	map_file = (struct vdpa_map_file *)map->opaque;
+	fput(map_file->file);
+	kfree(map_file);
+	pa = map->addr;
+	vhost_iotlb_map_free(domain->iotlb, map);
+	spin_unlock(&domain->iotlb_lock);
+
+	vduse_domain_free_iova(iovad, dma_addr, size);
+	free_pages_exact(phys_to_virt(pa), size);
+}
+
+static vm_fault_t vduse_domain_mmap_fault(struct vm_fault *vmf)
+{
+	struct vduse_iova_domain *domain = vmf->vma->vm_private_data;
+	unsigned long iova = vmf->pgoff << PAGE_SHIFT;
+	struct page *page;
+
+	if (!domain)
+		return VM_FAULT_SIGBUS;
+
+	if (iova < domain->bounce_size)
+		page = vduse_domain_get_bounce_page(domain, iova);
+	else
+		page = vduse_domain_get_coherent_page(domain, iova);
+
+	if (!page)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = page;
+
+	return 0;
+}
+
+static const struct vm_operations_struct vduse_domain_mmap_ops = {
+	.fault = vduse_domain_mmap_fault,
+};
+
+static int vduse_domain_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct vduse_iova_domain *domain = file->private_data;
+
+	vma->vm_flags |= VM_DONTDUMP | VM_DONTEXPAND;
+	vma->vm_private_data = domain;
+	vma->vm_ops = &vduse_domain_mmap_ops;
+
+	return 0;
+}
+
+static int vduse_domain_release(struct inode *inode, struct file *file)
+{
+	struct vduse_iova_domain *domain = file->private_data;
+
+	spin_lock(&domain->iotlb_lock);
+	vduse_iotlb_del_range(domain, 0, ULLONG_MAX);
+	vduse_domain_remove_user_bounce_pages(domain);
+	vduse_domain_free_kernel_bounce_pages(domain);
+	spin_unlock(&domain->iotlb_lock);
+	put_iova_domain(&domain->stream_iovad);
+	put_iova_domain(&domain->consistent_iovad);
+	vhost_iotlb_free(domain->iotlb);
+	vfree(domain->bounce_maps);
+	kfree(domain);
+
+	return 0;
+}
+
+static const struct file_operations vduse_domain_fops = {
+	.owner = THIS_MODULE,
+	.mmap = vduse_domain_mmap,
+	.release = vduse_domain_release,
+};
+
+void vduse_domain_destroy(struct vduse_iova_domain *domain)
+{
+	fput(domain->file);
+}
+
+struct vduse_iova_domain *
+vduse_domain_create(unsigned long iova_limit, size_t bounce_size)
+{
+	struct vduse_iova_domain *domain;
+	struct file *file;
+	struct vduse_bounce_map *map;
+	unsigned long pfn, bounce_pfns;
+	int ret;
+
+	bounce_pfns = PAGE_ALIGN(bounce_size) >> PAGE_SHIFT;
+	if (iova_limit <= bounce_size)
+		return NULL;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	domain->iotlb = vhost_iotlb_alloc(0, 0);
+	if (!domain->iotlb)
+		goto err_iotlb;
+
+	domain->iova_limit = iova_limit;
+	domain->bounce_size = PAGE_ALIGN(bounce_size);
+	domain->bounce_maps = vzalloc(bounce_pfns *
+				sizeof(struct vduse_bounce_map));
+	if (!domain->bounce_maps)
+		goto err_map;
+
+	for (pfn = 0; pfn < bounce_pfns; pfn++) {
+		map = &domain->bounce_maps[pfn];
+		map->orig_phys = INVALID_PHYS_ADDR;
+	}
+	file = anon_inode_getfile("[vduse-domain]", &vduse_domain_fops,
+				domain, O_RDWR);
+	if (IS_ERR(file))
+		goto err_file;
+
+	domain->file = file;
+	rwlock_init(&domain->bounce_lock);
+	spin_lock_init(&domain->iotlb_lock);
+	init_iova_domain(&domain->stream_iovad,
+			PAGE_SIZE, IOVA_START_PFN);
+	ret = iova_domain_init_rcaches(&domain->stream_iovad);
+	if (ret)
+		goto err_iovad_stream;
+	init_iova_domain(&domain->consistent_iovad,
+			PAGE_SIZE, bounce_pfns);
+	ret = iova_domain_init_rcaches(&domain->consistent_iovad);
+	if (ret)
+		goto err_iovad_consistent;
+
+	return domain;
+err_iovad_consistent:
+	put_iova_domain(&domain->stream_iovad);
+err_iovad_stream:
+	fput(file);
+err_file:
+	vfree(domain->bounce_maps);
+err_map:
+	vhost_iotlb_free(domain->iotlb);
+err_iotlb:
+	kfree(domain);
+	return NULL;
+}
+
+int vduse_domain_init(void)
+{
+	return iova_cache_get();
+}
+
+void vduse_domain_exit(void)
+{
+	iova_cache_put();
+}