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, 1272 insertions, 0 deletions

diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
new file mode 100644
index 000000000..83dbf398e
--- /dev/null
+++ b/drivers/nvdimm/region_devs.c
@@ -0,0 +1,1272 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ */
+#include <linux/scatterlist.h>
+#include <linux/memregion.h>
+#include <linux/highmem.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/hash.h>
+#include <linux/sort.h>
+#include <linux/io.h>
+#include <linux/nd.h>
+#include "nd-core.h"
+#include "nd.h"
+
+/*
+ * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
+ * irrelevant.
+ */
+#include <linux/io-64-nonatomic-hi-lo.h>
+
+static DEFINE_PER_CPU(int, flush_idx);
+
+static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
+		struct nd_region_data *ndrd)
+{
+	int i, j;
+
+	dev_dbg(dev, "%s: map %d flush address%s\n", nvdimm_name(nvdimm),
+			nvdimm->num_flush, nvdimm->num_flush == 1 ? "" : "es");
+	for (i = 0; i < (1 << ndrd->hints_shift); i++) {
+		struct resource *res = &nvdimm->flush_wpq[i];
+		unsigned long pfn = PHYS_PFN(res->start);
+		void __iomem *flush_page;
+
+		/* check if flush hints share a page */
+		for (j = 0; j < i; j++) {
+			struct resource *res_j = &nvdimm->flush_wpq[j];
+			unsigned long pfn_j = PHYS_PFN(res_j->start);
+
+			if (pfn == pfn_j)
+				break;
+		}
+
+		if (j < i)
+			flush_page = (void __iomem *) ((unsigned long)
+					ndrd_get_flush_wpq(ndrd, dimm, j)
+					& PAGE_MASK);
+		else
+			flush_page = devm_nvdimm_ioremap(dev,
+					PFN_PHYS(pfn), PAGE_SIZE);
+		if (!flush_page)
+			return -ENXIO;
+		ndrd_set_flush_wpq(ndrd, dimm, i, flush_page
+				+ (res->start & ~PAGE_MASK));
+	}
+
+	return 0;
+}
+
+static int nd_region_invalidate_memregion(struct nd_region *nd_region)
+{
+	int i, incoherent = 0;
+
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+		if (test_bit(NDD_INCOHERENT, &nvdimm->flags)) {
+			incoherent++;
+			break;
+		}
+	}
+
+	if (!incoherent)
+		return 0;
+
+	if (!cpu_cache_has_invalidate_memregion()) {
+		if (IS_ENABLED(CONFIG_NVDIMM_SECURITY_TEST)) {
+			dev_warn(
+				&nd_region->dev,
+				"Bypassing cpu_cache_invalidate_memergion() for testing!\n");
+			goto out;
+		} else {
+			dev_err(&nd_region->dev,
+				"Failed to synchronize CPU cache state\n");
+			return -ENXIO;
+		}
+	}
+
+	cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY);
+out:
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+		clear_bit(NDD_INCOHERENT, &nvdimm->flags);
+	}
+
+	return 0;
+}
+
+int nd_region_activate(struct nd_region *nd_region)
+{
+	int i, j, rc, num_flush = 0;
+	struct nd_region_data *ndrd;
+	struct device *dev = &nd_region->dev;
+	size_t flush_data_size = sizeof(void *);
+
+	nvdimm_bus_lock(&nd_region->dev);
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+		if (test_bit(NDD_SECURITY_OVERWRITE, &nvdimm->flags)) {
+			nvdimm_bus_unlock(&nd_region->dev);
+			return -EBUSY;
+		}
+
+		/* at least one null hint slot per-dimm for the "no-hint" case */
+		flush_data_size += sizeof(void *);
+		num_flush = min_not_zero(num_flush, nvdimm->num_flush);
+		if (!nvdimm->num_flush)
+			continue;
+		flush_data_size += nvdimm->num_flush * sizeof(void *);
+	}
+	nvdimm_bus_unlock(&nd_region->dev);
+
+	rc = nd_region_invalidate_memregion(nd_region);
+	if (rc)
+		return rc;
+
+	ndrd = devm_kzalloc(dev, sizeof(*ndrd) + flush_data_size, GFP_KERNEL);
+	if (!ndrd)
+		return -ENOMEM;
+	dev_set_drvdata(dev, ndrd);
+
+	if (!num_flush)
+		return 0;
+
+	ndrd->hints_shift = ilog2(num_flush);
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+		int rc = nvdimm_map_flush(&nd_region->dev, nvdimm, i, ndrd);
+
+		if (rc)
+			return rc;
+	}
+
+	/*
+	 * Clear out entries that are duplicates. This should prevent the
+	 * extra flushings.
+	 */
+	for (i = 0; i < nd_region->ndr_mappings - 1; i++) {
+		/* ignore if NULL already */
+		if (!ndrd_get_flush_wpq(ndrd, i, 0))
+			continue;
+
+		for (j = i + 1; j < nd_region->ndr_mappings; j++)
+			if (ndrd_get_flush_wpq(ndrd, i, 0) ==
+			    ndrd_get_flush_wpq(ndrd, j, 0))
+				ndrd_set_flush_wpq(ndrd, j, 0, NULL);
+	}
+
+	return 0;
+}
+
+static void nd_region_release(struct device *dev)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	u16 i;
+
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+		put_device(&nvdimm->dev);
+	}
+	free_percpu(nd_region->lane);
+	if (!test_bit(ND_REGION_CXL, &nd_region->flags))
+		memregion_free(nd_region->id);
+	kfree(nd_region);
+}
+
+struct nd_region *to_nd_region(struct device *dev)
+{
+	struct nd_region *nd_region = container_of(dev, struct nd_region, dev);
+
+	WARN_ON(dev->type->release != nd_region_release);
+	return nd_region;
+}
+EXPORT_SYMBOL_GPL(to_nd_region);
+
+struct device *nd_region_dev(struct nd_region *nd_region)
+{
+	if (!nd_region)
+		return NULL;
+	return &nd_region->dev;
+}
+EXPORT_SYMBOL_GPL(nd_region_dev);
+
+void *nd_region_provider_data(struct nd_region *nd_region)
+{
+	return nd_region->provider_data;
+}
+EXPORT_SYMBOL_GPL(nd_region_provider_data);
+
+/**
+ * nd_region_to_nstype() - region to an integer namespace type
+ * @nd_region: region-device to interrogate
+ *
+ * This is the 'nstype' attribute of a region as well, an input to the
+ * MODALIAS for namespace devices, and bit number for a nvdimm_bus to match
+ * namespace devices with namespace drivers.
+ */
+int nd_region_to_nstype(struct nd_region *nd_region)
+{
+	if (is_memory(&nd_region->dev)) {
+		u16 i, label;
+
+		for (i = 0, label = 0; i < nd_region->ndr_mappings; i++) {
+			struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+			struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+			if (test_bit(NDD_LABELING, &nvdimm->flags))
+				label++;
+		}
+		if (label)
+			return ND_DEVICE_NAMESPACE_PMEM;
+		else
+			return ND_DEVICE_NAMESPACE_IO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(nd_region_to_nstype);
+
+static unsigned long long region_size(struct nd_region *nd_region)
+{
+	if (is_memory(&nd_region->dev)) {
+		return nd_region->ndr_size;
+	} else if (nd_region->ndr_mappings == 1) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+
+		return nd_mapping->size;
+	}
+
+	return 0;
+}
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%llu\n", region_size(nd_region));
+}
+static DEVICE_ATTR_RO(size);
+
+static ssize_t deep_flush_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	/*
+	 * NOTE: in the nvdimm_has_flush() error case this attribute is
+	 * not visible.
+	 */
+	return sprintf(buf, "%d\n", nvdimm_has_flush(nd_region));
+}
+
+static ssize_t deep_flush_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t len)
+{
+	bool flush;
+	int rc = strtobool(buf, &flush);
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	if (rc)
+		return rc;
+	if (!flush)
+		return -EINVAL;
+	rc = nvdimm_flush(nd_region, NULL);
+	if (rc)
+		return rc;
+
+	return len;
+}
+static DEVICE_ATTR_RW(deep_flush);
+
+static ssize_t mappings_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%d\n", nd_region->ndr_mappings);
+}
+static DEVICE_ATTR_RO(mappings);
+
+static ssize_t nstype_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region));
+}
+static DEVICE_ATTR_RO(nstype);
+
+static ssize_t set_cookie_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	struct nd_interleave_set *nd_set = nd_region->nd_set;
+	ssize_t rc = 0;
+
+	if (is_memory(dev) && nd_set)
+		/* pass, should be precluded by region_visible */;
+	else
+		return -ENXIO;
+
+	/*
+	 * The cookie to show depends on which specification of the
+	 * labels we are using. If there are not labels then default to
+	 * the v1.1 namespace label cookie definition. To read all this
+	 * data we need to wait for probing to settle.
+	 */
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	if (nd_region->ndr_mappings) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+
+		if (ndd) {
+			struct nd_namespace_index *nsindex;
+
+			nsindex = to_namespace_index(ndd, ndd->ns_current);
+			rc = sprintf(buf, "%#llx\n",
+					nd_region_interleave_set_cookie(nd_region,
+						nsindex));
+		}
+	}
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	if (rc)
+		return rc;
+	return sprintf(buf, "%#llx\n", nd_set->cookie1);
+}
+static DEVICE_ATTR_RO(set_cookie);
+
+resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
+{
+	resource_size_t available;
+	int i;
+
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+
+	available = 0;
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+
+		/* if a dimm is disabled the available capacity is zero */
+		if (!ndd)
+			return 0;
+
+		available += nd_pmem_available_dpa(nd_region, nd_mapping);
+	}
+
+	return available;
+}
+
+resource_size_t nd_region_allocatable_dpa(struct nd_region *nd_region)
+{
+	resource_size_t avail = 0;
+	int i;
+
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+
+		avail = min_not_zero(avail, nd_pmem_max_contiguous_dpa(
+						    nd_region, nd_mapping));
+	}
+	return avail * nd_region->ndr_mappings;
+}
+
+static ssize_t available_size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	unsigned long long available = 0;
+
+	/*
+	 * Flush in-flight updates and grab a snapshot of the available
+	 * size.  Of course, this value is potentially invalidated the
+	 * memory nvdimm_bus_lock() is dropped, but that's userspace's
+	 * problem to not race itself.
+	 */
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	available = nd_region_available_dpa(nd_region);
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return sprintf(buf, "%llu\n", available);
+}
+static DEVICE_ATTR_RO(available_size);
+
+static ssize_t max_available_extent_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	unsigned long long available = 0;
+
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	available = nd_region_allocatable_dpa(nd_region);
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return sprintf(buf, "%llu\n", available);
+}
+static DEVICE_ATTR_RO(max_available_extent);
+
+static ssize_t init_namespaces_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region_data *ndrd = dev_get_drvdata(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	if (ndrd)
+		rc = sprintf(buf, "%d/%d\n", ndrd->ns_active, ndrd->ns_count);
+	else
+		rc = -ENXIO;
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(init_namespaces);
+
+static ssize_t namespace_seed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	if (nd_region->ns_seed)
+		rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed));
+	else
+		rc = sprintf(buf, "\n");
+	nvdimm_bus_unlock(dev);
+	return rc;
+}
+static DEVICE_ATTR_RO(namespace_seed);
+
+static ssize_t btt_seed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	if (nd_region->btt_seed)
+		rc = sprintf(buf, "%s\n", dev_name(nd_region->btt_seed));
+	else
+		rc = sprintf(buf, "\n");
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(btt_seed);
+
+static ssize_t pfn_seed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	if (nd_region->pfn_seed)
+		rc = sprintf(buf, "%s\n", dev_name(nd_region->pfn_seed));
+	else
+		rc = sprintf(buf, "\n");
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(pfn_seed);
+
+static ssize_t dax_seed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	if (nd_region->dax_seed)
+		rc = sprintf(buf, "%s\n", dev_name(nd_region->dax_seed));
+	else
+		rc = sprintf(buf, "\n");
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(dax_seed);
+
+static ssize_t read_only_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%d\n", nd_region->ro);
+}
+
+static int revalidate_read_only(struct device *dev, void *data)
+{
+	nd_device_notify(dev, NVDIMM_REVALIDATE_REGION);
+	return 0;
+}
+
+static ssize_t read_only_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	bool ro;
+	int rc = strtobool(buf, &ro);
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	if (rc)
+		return rc;
+
+	nd_region->ro = ro;
+	device_for_each_child(dev, NULL, revalidate_read_only);
+	return len;
+}
+static DEVICE_ATTR_RW(read_only);
+
+static ssize_t align_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%#lx\n", nd_region->align);
+}
+
+static ssize_t align_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	unsigned long val, dpa;
+	u32 mappings, remainder;
+	int rc;
+
+	rc = kstrtoul(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	/*
+	 * Ensure space-align is evenly divisible by the region
+	 * interleave-width because the kernel typically has no facility
+	 * to determine which DIMM(s), dimm-physical-addresses, would
+	 * contribute to the tail capacity in system-physical-address
+	 * space for the namespace.
+	 */
+	mappings = max_t(u32, 1, nd_region->ndr_mappings);
+	dpa = div_u64_rem(val, mappings, &remainder);
+	if (!is_power_of_2(dpa) || dpa < PAGE_SIZE
+			|| val > region_size(nd_region) || remainder)
+		return -EINVAL;
+
+	/*
+	 * Given that space allocation consults this value multiple
+	 * times ensure it does not change for the duration of the
+	 * allocation.
+	 */
+	nvdimm_bus_lock(dev);
+	nd_region->align = val;
+	nvdimm_bus_unlock(dev);
+
+	return len;
+}
+static DEVICE_ATTR_RW(align);
+
+static ssize_t region_badblocks_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
+
+	device_lock(dev);
+	if (dev->driver)
+		rc = badblocks_show(&nd_region->bb, buf, 0);
+	else
+		rc = -ENXIO;
+	device_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR(badblocks, 0444, region_badblocks_show, NULL);
+
+static ssize_t resource_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%#llx\n", nd_region->ndr_start);
+}
+static DEVICE_ATTR_ADMIN_RO(resource);
+
+static ssize_t persistence_domain_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	if (test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags))
+		return sprintf(buf, "cpu_cache\n");
+	else if (test_bit(ND_REGION_PERSIST_MEMCTRL, &nd_region->flags))
+		return sprintf(buf, "memory_controller\n");
+	else
+		return sprintf(buf, "\n");
+}
+static DEVICE_ATTR_RO(persistence_domain);
+
+static struct attribute *nd_region_attributes[] = {
+	&dev_attr_size.attr,
+	&dev_attr_align.attr,
+	&dev_attr_nstype.attr,
+	&dev_attr_mappings.attr,
+	&dev_attr_btt_seed.attr,
+	&dev_attr_pfn_seed.attr,
+	&dev_attr_dax_seed.attr,
+	&dev_attr_deep_flush.attr,
+	&dev_attr_read_only.attr,
+	&dev_attr_set_cookie.attr,
+	&dev_attr_available_size.attr,
+	&dev_attr_max_available_extent.attr,
+	&dev_attr_namespace_seed.attr,
+	&dev_attr_init_namespaces.attr,
+	&dev_attr_badblocks.attr,
+	&dev_attr_resource.attr,
+	&dev_attr_persistence_domain.attr,
+	NULL,
+};
+
+static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct nd_region *nd_region = to_nd_region(dev);
+	struct nd_interleave_set *nd_set = nd_region->nd_set;
+	int type = nd_region_to_nstype(nd_region);
+
+	if (!is_memory(dev) && a == &dev_attr_pfn_seed.attr)
+		return 0;
+
+	if (!is_memory(dev) && a == &dev_attr_dax_seed.attr)
+		return 0;
+
+	if (!is_memory(dev) && a == &dev_attr_badblocks.attr)
+		return 0;
+
+	if (a == &dev_attr_resource.attr && !is_memory(dev))
+		return 0;
+
+	if (a == &dev_attr_deep_flush.attr) {
+		int has_flush = nvdimm_has_flush(nd_region);
+
+		if (has_flush == 1)
+			return a->mode;
+		else if (has_flush == 0)
+			return 0444;
+		else
+			return 0;
+	}
+
+	if (a == &dev_attr_persistence_domain.attr) {
+		if ((nd_region->flags & (BIT(ND_REGION_PERSIST_CACHE)
+					| BIT(ND_REGION_PERSIST_MEMCTRL))) == 0)
+			return 0;
+		return a->mode;
+	}
+
+	if (a == &dev_attr_align.attr)
+		return a->mode;
+
+	if (a != &dev_attr_set_cookie.attr
+			&& a != &dev_attr_available_size.attr)
+		return a->mode;
+
+	if (type == ND_DEVICE_NAMESPACE_PMEM &&
+	    a == &dev_attr_available_size.attr)
+		return a->mode;
+	else if (is_memory(dev) && nd_set)
+		return a->mode;
+
+	return 0;
+}
+
+static ssize_t mappingN(struct device *dev, char *buf, int n)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	struct nd_mapping *nd_mapping;
+	struct nvdimm *nvdimm;
+
+	if (n >= nd_region->ndr_mappings)
+		return -ENXIO;
+	nd_mapping = &nd_region->mapping[n];
+	nvdimm = nd_mapping->nvdimm;
+
+	return sprintf(buf, "%s,%llu,%llu,%d\n", dev_name(&nvdimm->dev),
+			nd_mapping->start, nd_mapping->size,
+			nd_mapping->position);
+}
+
+#define REGION_MAPPING(idx) \
+static ssize_t mapping##idx##_show(struct device *dev,		\
+		struct device_attribute *attr, char *buf)	\
+{								\
+	return mappingN(dev, buf, idx);				\
+}								\
+static DEVICE_ATTR_RO(mapping##idx)
+
+/*
+ * 32 should be enough for a while, even in the presence of socket
+ * interleave a 32-way interleave set is a degenerate case.
+ */
+REGION_MAPPING(0);
+REGION_MAPPING(1);
+REGION_MAPPING(2);
+REGION_MAPPING(3);
+REGION_MAPPING(4);
+REGION_MAPPING(5);
+REGION_MAPPING(6);
+REGION_MAPPING(7);
+REGION_MAPPING(8);
+REGION_MAPPING(9);
+REGION_MAPPING(10);
+REGION_MAPPING(11);
+REGION_MAPPING(12);
+REGION_MAPPING(13);
+REGION_MAPPING(14);
+REGION_MAPPING(15);
+REGION_MAPPING(16);
+REGION_MAPPING(17);
+REGION_MAPPING(18);
+REGION_MAPPING(19);
+REGION_MAPPING(20);
+REGION_MAPPING(21);
+REGION_MAPPING(22);
+REGION_MAPPING(23);
+REGION_MAPPING(24);
+REGION_MAPPING(25);
+REGION_MAPPING(26);
+REGION_MAPPING(27);
+REGION_MAPPING(28);
+REGION_MAPPING(29);
+REGION_MAPPING(30);
+REGION_MAPPING(31);
+
+static umode_t mapping_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	if (n < nd_region->ndr_mappings)
+		return a->mode;
+	return 0;
+}
+
+static struct attribute *mapping_attributes[] = {
+	&dev_attr_mapping0.attr,
+	&dev_attr_mapping1.attr,
+	&dev_attr_mapping2.attr,
+	&dev_attr_mapping3.attr,
+	&dev_attr_mapping4.attr,
+	&dev_attr_mapping5.attr,
+	&dev_attr_mapping6.attr,
+	&dev_attr_mapping7.attr,
+	&dev_attr_mapping8.attr,
+	&dev_attr_mapping9.attr,
+	&dev_attr_mapping10.attr,
+	&dev_attr_mapping11.attr,
+	&dev_attr_mapping12.attr,
+	&dev_attr_mapping13.attr,
+	&dev_attr_mapping14.attr,
+	&dev_attr_mapping15.attr,
+	&dev_attr_mapping16.attr,
+	&dev_attr_mapping17.attr,
+	&dev_attr_mapping18.attr,
+	&dev_attr_mapping19.attr,
+	&dev_attr_mapping20.attr,
+	&dev_attr_mapping21.attr,
+	&dev_attr_mapping22.attr,
+	&dev_attr_mapping23.attr,
+	&dev_attr_mapping24.attr,
+	&dev_attr_mapping25.attr,
+	&dev_attr_mapping26.attr,
+	&dev_attr_mapping27.attr,
+	&dev_attr_mapping28.attr,
+	&dev_attr_mapping29.attr,
+	&dev_attr_mapping30.attr,
+	&dev_attr_mapping31.attr,
+	NULL,
+};
+
+static const struct attribute_group nd_mapping_attribute_group = {
+	.is_visible = mapping_visible,
+	.attrs = mapping_attributes,
+};
+
+static const struct attribute_group nd_region_attribute_group = {
+	.attrs = nd_region_attributes,
+	.is_visible = region_visible,
+};
+
+static const struct attribute_group *nd_region_attribute_groups[] = {
+	&nd_device_attribute_group,
+	&nd_region_attribute_group,
+	&nd_numa_attribute_group,
+	&nd_mapping_attribute_group,
+	NULL,
+};
+
+static const struct device_type nd_pmem_device_type = {
+	.name = "nd_pmem",
+	.release = nd_region_release,
+	.groups = nd_region_attribute_groups,
+};
+
+static const struct device_type nd_volatile_device_type = {
+	.name = "nd_volatile",
+	.release = nd_region_release,
+	.groups = nd_region_attribute_groups,
+};
+
+bool is_nd_pmem(struct device *dev)
+{
+	return dev ? dev->type == &nd_pmem_device_type : false;
+}
+
+bool is_nd_volatile(struct device *dev)
+{
+	return dev ? dev->type == &nd_volatile_device_type : false;
+}
+
+u64 nd_region_interleave_set_cookie(struct nd_region *nd_region,
+		struct nd_namespace_index *nsindex)
+{
+	struct nd_interleave_set *nd_set = nd_region->nd_set;
+
+	if (!nd_set)
+		return 0;
+
+	if (nsindex && __le16_to_cpu(nsindex->major) == 1
+			&& __le16_to_cpu(nsindex->minor) == 1)
+		return nd_set->cookie1;
+	return nd_set->cookie2;
+}
+
+u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region)
+{
+	struct nd_interleave_set *nd_set = nd_region->nd_set;
+
+	if (nd_set)
+		return nd_set->altcookie;
+	return 0;
+}
+
+void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
+{
+	struct nd_label_ent *label_ent, *e;
+
+	lockdep_assert_held(&nd_mapping->lock);
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		list_del(&label_ent->list);
+		kfree(label_ent);
+	}
+}
+
+/*
+ * When a namespace is activated create new seeds for the next
+ * namespace, or namespace-personality to be configured.
+ */
+void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev)
+{
+	nvdimm_bus_lock(dev);
+	if (nd_region->ns_seed == dev) {
+		nd_region_create_ns_seed(nd_region);
+	} else if (is_nd_btt(dev)) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+
+		if (nd_region->btt_seed == dev)
+			nd_region_create_btt_seed(nd_region);
+		if (nd_region->ns_seed == &nd_btt->ndns->dev)
+			nd_region_create_ns_seed(nd_region);
+	} else if (is_nd_pfn(dev)) {
+		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+		if (nd_region->pfn_seed == dev)
+			nd_region_create_pfn_seed(nd_region);
+		if (nd_region->ns_seed == &nd_pfn->ndns->dev)
+			nd_region_create_ns_seed(nd_region);
+	} else if (is_nd_dax(dev)) {
+		struct nd_dax *nd_dax = to_nd_dax(dev);
+
+		if (nd_region->dax_seed == dev)
+			nd_region_create_dax_seed(nd_region);
+		if (nd_region->ns_seed == &nd_dax->nd_pfn.ndns->dev)
+			nd_region_create_ns_seed(nd_region);
+	}
+	nvdimm_bus_unlock(dev);
+}
+
+/**
+ * nd_region_acquire_lane - allocate and lock a lane
+ * @nd_region: region id and number of lanes possible
+ *
+ * A lane correlates to a BLK-data-window and/or a log slot in the BTT.
+ * We optimize for the common case where there are 256 lanes, one
+ * per-cpu.  For larger systems we need to lock to share lanes.  For now
+ * this implementation assumes the cost of maintaining an allocator for
+ * free lanes is on the order of the lock hold time, so it implements a
+ * static lane = cpu % num_lanes mapping.
+ *
+ * In the case of a BTT instance on top of a BLK namespace a lane may be
+ * acquired recursively.  We lock on the first instance.
+ *
+ * In the case of a BTT instance on top of PMEM, we only acquire a lane
+ * for the BTT metadata updates.
+ */
+unsigned int nd_region_acquire_lane(struct nd_region *nd_region)
+{
+	unsigned int cpu, lane;
+
+	cpu = get_cpu();
+	if (nd_region->num_lanes < nr_cpu_ids) {
+		struct nd_percpu_lane *ndl_lock, *ndl_count;
+
+		lane = cpu % nd_region->num_lanes;
+		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
+		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
+		if (ndl_count->count++ == 0)
+			spin_lock(&ndl_lock->lock);
+	} else
+		lane = cpu;
+
+	return lane;
+}
+EXPORT_SYMBOL(nd_region_acquire_lane);
+
+void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane)
+{
+	if (nd_region->num_lanes < nr_cpu_ids) {
+		unsigned int cpu = get_cpu();
+		struct nd_percpu_lane *ndl_lock, *ndl_count;
+
+		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
+		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
+		if (--ndl_count->count == 0)
+			spin_unlock(&ndl_lock->lock);
+		put_cpu();
+	}
+	put_cpu();
+}
+EXPORT_SYMBOL(nd_region_release_lane);
+
+/*
+ * PowerPC requires this alignment for memremap_pages(). All other archs
+ * should be ok with SUBSECTION_SIZE (see memremap_compat_align()).
+ */
+#define MEMREMAP_COMPAT_ALIGN_MAX SZ_16M
+
+static unsigned long default_align(struct nd_region *nd_region)
+{
+	unsigned long align;
+	u32 remainder;
+	int mappings;
+
+	align = MEMREMAP_COMPAT_ALIGN_MAX;
+	if (nd_region->ndr_size < MEMREMAP_COMPAT_ALIGN_MAX)
+		align = PAGE_SIZE;
+
+	mappings = max_t(u16, 1, nd_region->ndr_mappings);
+	div_u64_rem(align, mappings, &remainder);
+	if (remainder)
+		align *= mappings;
+
+	return align;
+}
+
+static struct lock_class_key nvdimm_region_key;
+
+static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
+		struct nd_region_desc *ndr_desc,
+		const struct device_type *dev_type, const char *caller)
+{
+	struct nd_region *nd_region;
+	struct device *dev;
+	unsigned int i;
+	int ro = 0;
+
+	for (i = 0; i < ndr_desc->num_mappings; i++) {
+		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
+		struct nvdimm *nvdimm = mapping->nvdimm;
+
+		if ((mapping->start | mapping->size) % PAGE_SIZE) {
+			dev_err(&nvdimm_bus->dev,
+				"%s: %s mapping%d is not %ld aligned\n",
+				caller, dev_name(&nvdimm->dev), i, PAGE_SIZE);
+			return NULL;
+		}
+
+		if (test_bit(NDD_UNARMED, &nvdimm->flags))
+			ro = 1;
+
+	}
+
+	nd_region =
+		kzalloc(struct_size(nd_region, mapping, ndr_desc->num_mappings),
+			GFP_KERNEL);
+
+	if (!nd_region)
+		return NULL;
+	/* CXL pre-assigns memregion ids before creating nvdimm regions */
+	if (test_bit(ND_REGION_CXL, &ndr_desc->flags)) {
+		nd_region->id = ndr_desc->memregion;
+	} else {
+		nd_region->id = memregion_alloc(GFP_KERNEL);
+		if (nd_region->id < 0)
+			goto err_id;
+	}
+
+	nd_region->lane = alloc_percpu(struct nd_percpu_lane);
+	if (!nd_region->lane)
+		goto err_percpu;
+
+        for (i = 0; i < nr_cpu_ids; i++) {
+		struct nd_percpu_lane *ndl;
+
+		ndl = per_cpu_ptr(nd_region->lane, i);
+		spin_lock_init(&ndl->lock);
+		ndl->count = 0;
+	}
+
+	for (i = 0; i < ndr_desc->num_mappings; i++) {
+		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
+		struct nvdimm *nvdimm = mapping->nvdimm;
+
+		nd_region->mapping[i].nvdimm = nvdimm;
+		nd_region->mapping[i].start = mapping->start;
+		nd_region->mapping[i].size = mapping->size;
+		nd_region->mapping[i].position = mapping->position;
+		INIT_LIST_HEAD(&nd_region->mapping[i].labels);
+		mutex_init(&nd_region->mapping[i].lock);
+
+		get_device(&nvdimm->dev);
+	}
+	nd_region->ndr_mappings = ndr_desc->num_mappings;
+	nd_region->provider_data = ndr_desc->provider_data;
+	nd_region->nd_set = ndr_desc->nd_set;
+	nd_region->num_lanes = ndr_desc->num_lanes;
+	nd_region->flags = ndr_desc->flags;
+	nd_region->ro = ro;
+	nd_region->numa_node = ndr_desc->numa_node;
+	nd_region->target_node = ndr_desc->target_node;
+	ida_init(&nd_region->ns_ida);
+	ida_init(&nd_region->btt_ida);
+	ida_init(&nd_region->pfn_ida);
+	ida_init(&nd_region->dax_ida);
+	dev = &nd_region->dev;
+	dev_set_name(dev, "region%d", nd_region->id);
+	dev->parent = &nvdimm_bus->dev;
+	dev->type = dev_type;
+	dev->groups = ndr_desc->attr_groups;
+	dev->of_node = ndr_desc->of_node;
+	nd_region->ndr_size = resource_size(ndr_desc->res);
+	nd_region->ndr_start = ndr_desc->res->start;
+	nd_region->align = default_align(nd_region);
+	if (ndr_desc->flush)
+		nd_region->flush = ndr_desc->flush;
+	else
+		nd_region->flush = NULL;
+
+	device_initialize(dev);
+	lockdep_set_class(&dev->mutex, &nvdimm_region_key);
+	nd_device_register(dev);
+
+	return nd_region;
+
+err_percpu:
+	if (!test_bit(ND_REGION_CXL, &ndr_desc->flags))
+		memregion_free(nd_region->id);
+err_id:
+	kfree(nd_region);
+	return NULL;
+}
+
+struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus,
+		struct nd_region_desc *ndr_desc)
+{
+	ndr_desc->num_lanes = ND_MAX_LANES;
+	return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type,
+			__func__);
+}
+EXPORT_SYMBOL_GPL(nvdimm_pmem_region_create);
+
+struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
+		struct nd_region_desc *ndr_desc)
+{
+	ndr_desc->num_lanes = ND_MAX_LANES;
+	return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type,
+			__func__);
+}
+EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
+
+void nvdimm_region_delete(struct nd_region *nd_region)
+{
+	if (nd_region)
+		nd_device_unregister(&nd_region->dev, ND_SYNC);
+}
+EXPORT_SYMBOL_GPL(nvdimm_region_delete);
+
+int nvdimm_flush(struct nd_region *nd_region, struct bio *bio)
+{
+	int rc = 0;
+
+	if (!nd_region->flush)
+		rc = generic_nvdimm_flush(nd_region);
+	else {
+		if (nd_region->flush(nd_region, bio))
+			rc = -EIO;
+	}
+
+	return rc;
+}
+/**
+ * generic_nvdimm_flush() - flush any posted write queues between the cpu and pmem media
+ * @nd_region: interleaved pmem region
+ */
+int generic_nvdimm_flush(struct nd_region *nd_region)
+{
+	struct nd_region_data *ndrd = dev_get_drvdata(&nd_region->dev);
+	int i, idx;
+
+	/*
+	 * Try to encourage some diversity in flush hint addresses
+	 * across cpus assuming a limited number of flush hints.
+	 */
+	idx = this_cpu_read(flush_idx);
+	idx = this_cpu_add_return(flush_idx, hash_32(current->pid + idx, 8));
+
+	/*
+	 * The pmem_wmb() is needed to 'sfence' all
+	 * previous writes such that they are architecturally visible for
+	 * the platform buffer flush. Note that we've already arranged for pmem
+	 * writes to avoid the cache via memcpy_flushcache().  The final
+	 * wmb() ensures ordering for the NVDIMM flush write.
+	 */
+	pmem_wmb();
+	for (i = 0; i < nd_region->ndr_mappings; i++)
+		if (ndrd_get_flush_wpq(ndrd, i, 0))
+			writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
+	wmb();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvdimm_flush);
+
+/**
+ * nvdimm_has_flush - determine write flushing requirements
+ * @nd_region: interleaved pmem region
+ *
+ * Returns 1 if writes require flushing
+ * Returns 0 if writes do not require flushing
+ * Returns -ENXIO if flushing capability can not be determined
+ */
+int nvdimm_has_flush(struct nd_region *nd_region)
+{
+	int i;
+
+	/* no nvdimm or pmem api == flushing capability unknown */
+	if (nd_region->ndr_mappings == 0
+			|| !IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API))
+		return -ENXIO;
+
+	/* Test if an explicit flush function is defined */
+	if (test_bit(ND_REGION_ASYNC, &nd_region->flags) && nd_region->flush)
+		return 1;
+
+	/* Test if any flush hints for the region are available */
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+		/* flush hints present / available */
+		if (nvdimm->num_flush)
+			return 1;
+	}
+
+	/*
+	 * The platform defines dimm devices without hints nor explicit flush,
+	 * assume platform persistence mechanism like ADR
+	 */
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvdimm_has_flush);
+
+int nvdimm_has_cache(struct nd_region *nd_region)
+{
+	return is_nd_pmem(&nd_region->dev) &&
+		!test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags);
+}
+EXPORT_SYMBOL_GPL(nvdimm_has_cache);
+
+bool is_nvdimm_sync(struct nd_region *nd_region)
+{
+	if (is_nd_volatile(&nd_region->dev))
+		return true;
+
+	return is_nd_pmem(&nd_region->dev) &&
+		!test_bit(ND_REGION_ASYNC, &nd_region->flags);
+}
+EXPORT_SYMBOL_GPL(is_nvdimm_sync);
+
+struct conflict_context {
+	struct nd_region *nd_region;
+	resource_size_t start, size;
+};
+
+static int region_conflict(struct device *dev, void *data)
+{
+	struct nd_region *nd_region;
+	struct conflict_context *ctx = data;
+	resource_size_t res_end, region_end, region_start;
+
+	if (!is_memory(dev))
+		return 0;
+
+	nd_region = to_nd_region(dev);
+	if (nd_region == ctx->nd_region)
+		return 0;
+
+	res_end = ctx->start + ctx->size;
+	region_start = nd_region->ndr_start;
+	region_end = region_start + nd_region->ndr_size;
+	if (ctx->start >= region_start && ctx->start < region_end)
+		return -EBUSY;
+	if (res_end > region_start && res_end <= region_end)
+		return -EBUSY;
+	return 0;
+}
+
+int nd_region_conflict(struct nd_region *nd_region, resource_size_t start,
+		resource_size_t size)
+{
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+	struct conflict_context ctx = {
+		.nd_region = nd_region,
+		.start = start,
+		.size = size,
+	};
+
+	return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict);
+}
+
+MODULE_IMPORT_NS(DEVMEM);