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, 417 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
new file mode 100644
index 000000000..4b2d7465d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
@@ -0,0 +1,417 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#define nv50_instmem(p) container_of((p), struct nv50_instmem, base)
+#include "priv.h"
+
+#include <core/memory.h>
+#include <subdev/bar.h>
+#include <subdev/fb.h>
+#include <subdev/mmu.h>
+
+struct nv50_instmem {
+	struct nvkm_instmem base;
+	u64 addr;
+
+	/* Mappings that can be evicted when BAR2 space has been exhausted. */
+	struct list_head lru;
+};
+
+/******************************************************************************
+ * instmem object implementation
+ *****************************************************************************/
+#define nv50_instobj(p) container_of((p), struct nv50_instobj, base.memory)
+
+struct nv50_instobj {
+	struct nvkm_instobj base;
+	struct nv50_instmem *imem;
+	struct nvkm_memory *ram;
+	struct nvkm_vma *bar;
+	refcount_t maps;
+	void *map;
+	struct list_head lru;
+};
+
+static void
+nv50_instobj_wr32_slow(struct nvkm_memory *memory, u64 offset, u32 data)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	struct nv50_instmem *imem = iobj->imem;
+	struct nvkm_device *device = imem->base.subdev.device;
+	u64 base = (nvkm_memory_addr(iobj->ram) + offset) & 0xffffff00000ULL;
+	u64 addr = (nvkm_memory_addr(iobj->ram) + offset) & 0x000000fffffULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&imem->base.lock, flags);
+	if (unlikely(imem->addr != base)) {
+		nvkm_wr32(device, 0x001700, base >> 16);
+		imem->addr = base;
+	}
+	nvkm_wr32(device, 0x700000 + addr, data);
+	spin_unlock_irqrestore(&imem->base.lock, flags);
+}
+
+static u32
+nv50_instobj_rd32_slow(struct nvkm_memory *memory, u64 offset)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	struct nv50_instmem *imem = iobj->imem;
+	struct nvkm_device *device = imem->base.subdev.device;
+	u64 base = (nvkm_memory_addr(iobj->ram) + offset) & 0xffffff00000ULL;
+	u64 addr = (nvkm_memory_addr(iobj->ram) + offset) & 0x000000fffffULL;
+	u32 data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&imem->base.lock, flags);
+	if (unlikely(imem->addr != base)) {
+		nvkm_wr32(device, 0x001700, base >> 16);
+		imem->addr = base;
+	}
+	data = nvkm_rd32(device, 0x700000 + addr);
+	spin_unlock_irqrestore(&imem->base.lock, flags);
+	return data;
+}
+
+static const struct nvkm_memory_ptrs
+nv50_instobj_slow = {
+	.rd32 = nv50_instobj_rd32_slow,
+	.wr32 = nv50_instobj_wr32_slow,
+};
+
+static void
+nv50_instobj_wr32(struct nvkm_memory *memory, u64 offset, u32 data)
+{
+	iowrite32_native(data, nv50_instobj(memory)->map + offset);
+}
+
+static u32
+nv50_instobj_rd32(struct nvkm_memory *memory, u64 offset)
+{
+	return ioread32_native(nv50_instobj(memory)->map + offset);
+}
+
+static const struct nvkm_memory_ptrs
+nv50_instobj_fast = {
+	.rd32 = nv50_instobj_rd32,
+	.wr32 = nv50_instobj_wr32,
+};
+
+static void
+nv50_instobj_kmap(struct nv50_instobj *iobj, struct nvkm_vmm *vmm)
+{
+	struct nv50_instmem *imem = iobj->imem;
+	struct nv50_instobj *eobj;
+	struct nvkm_memory *memory = &iobj->base.memory;
+	struct nvkm_subdev *subdev = &imem->base.subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_vma *bar = NULL, *ebar;
+	u64 size = nvkm_memory_size(memory);
+	void *emap;
+	int ret;
+
+	/* Attempt to allocate BAR2 address-space and map the object
+	 * into it.  The lock has to be dropped while doing this due
+	 * to the possibility of recursion for page table allocation.
+	 */
+	mutex_unlock(&imem->base.mutex);
+	while ((ret = nvkm_vmm_get(vmm, 12, size, &bar))) {
+		/* Evict unused mappings, and keep retrying until we either
+		 * succeed,or there's no more objects left on the LRU.
+		 */
+		mutex_lock(&imem->base.mutex);
+		eobj = list_first_entry_or_null(&imem->lru, typeof(*eobj), lru);
+		if (eobj) {
+			nvkm_debug(subdev, "evict %016llx %016llx @ %016llx\n",
+				   nvkm_memory_addr(&eobj->base.memory),
+				   nvkm_memory_size(&eobj->base.memory),
+				   eobj->bar->addr);
+			list_del_init(&eobj->lru);
+			ebar = eobj->bar;
+			eobj->bar = NULL;
+			emap = eobj->map;
+			eobj->map = NULL;
+		}
+		mutex_unlock(&imem->base.mutex);
+		if (!eobj)
+			break;
+		iounmap(emap);
+		nvkm_vmm_put(vmm, &ebar);
+	}
+
+	if (ret == 0)
+		ret = nvkm_memory_map(memory, 0, vmm, bar, NULL, 0);
+	mutex_lock(&imem->base.mutex);
+	if (ret || iobj->bar) {
+		/* We either failed, or another thread beat us. */
+		mutex_unlock(&imem->base.mutex);
+		nvkm_vmm_put(vmm, &bar);
+		mutex_lock(&imem->base.mutex);
+		return;
+	}
+
+	/* Make the mapping visible to the host. */
+	iobj->bar = bar;
+	iobj->map = ioremap_wc(device->func->resource_addr(device, 3) +
+			       (u32)iobj->bar->addr, size);
+	if (!iobj->map) {
+		nvkm_warn(subdev, "PRAMIN ioremap failed\n");
+		nvkm_vmm_put(vmm, &iobj->bar);
+	}
+}
+
+static int
+nv50_instobj_map(struct nvkm_memory *memory, u64 offset, struct nvkm_vmm *vmm,
+		 struct nvkm_vma *vma, void *argv, u32 argc)
+{
+	memory = nv50_instobj(memory)->ram;
+	return nvkm_memory_map(memory, offset, vmm, vma, argv, argc);
+}
+
+static void
+nv50_instobj_release(struct nvkm_memory *memory)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	struct nv50_instmem *imem = iobj->imem;
+	struct nvkm_subdev *subdev = &imem->base.subdev;
+
+	wmb();
+	nvkm_bar_flush(subdev->device->bar);
+
+	if (refcount_dec_and_mutex_lock(&iobj->maps, &imem->base.mutex)) {
+		/* Add the now-unused mapping to the LRU instead of directly
+		 * unmapping it here, in case we need to map it again later.
+		 */
+		if (likely(iobj->lru.next) && iobj->map) {
+			BUG_ON(!list_empty(&iobj->lru));
+			list_add_tail(&iobj->lru, &imem->lru);
+		}
+
+		/* Switch back to NULL accessors when last map is gone. */
+		iobj->base.memory.ptrs = NULL;
+		mutex_unlock(&imem->base.mutex);
+	}
+}
+
+static void __iomem *
+nv50_instobj_acquire(struct nvkm_memory *memory)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	struct nvkm_instmem *imem = &iobj->imem->base;
+	struct nvkm_vmm *vmm;
+	void __iomem *map = NULL;
+
+	/* Already mapped? */
+	if (refcount_inc_not_zero(&iobj->maps))
+		return iobj->map;
+
+	/* Take the lock, and re-check that another thread hasn't
+	 * already mapped the object in the meantime.
+	 */
+	mutex_lock(&imem->mutex);
+	if (refcount_inc_not_zero(&iobj->maps)) {
+		mutex_unlock(&imem->mutex);
+		return iobj->map;
+	}
+
+	/* Attempt to get a direct CPU mapping of the object. */
+	if ((vmm = nvkm_bar_bar2_vmm(imem->subdev.device))) {
+		if (!iobj->map)
+			nv50_instobj_kmap(iobj, vmm);
+		map = iobj->map;
+	}
+
+	if (!refcount_inc_not_zero(&iobj->maps)) {
+		/* Exclude object from eviction while it's being accessed. */
+		if (likely(iobj->lru.next))
+			list_del_init(&iobj->lru);
+
+		if (map)
+			iobj->base.memory.ptrs = &nv50_instobj_fast;
+		else
+			iobj->base.memory.ptrs = &nv50_instobj_slow;
+		refcount_set(&iobj->maps, 1);
+	}
+
+	mutex_unlock(&imem->mutex);
+	return map;
+}
+
+static void
+nv50_instobj_boot(struct nvkm_memory *memory, struct nvkm_vmm *vmm)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	struct nvkm_instmem *imem = &iobj->imem->base;
+
+	/* Exclude bootstrapped objects (ie. the page tables for the
+	 * instmem BAR itself) from eviction.
+	 */
+	mutex_lock(&imem->mutex);
+	if (likely(iobj->lru.next)) {
+		list_del_init(&iobj->lru);
+		iobj->lru.next = NULL;
+	}
+
+	nv50_instobj_kmap(iobj, vmm);
+	nvkm_instmem_boot(imem);
+	mutex_unlock(&imem->mutex);
+}
+
+static u64
+nv50_instobj_size(struct nvkm_memory *memory)
+{
+	return nvkm_memory_size(nv50_instobj(memory)->ram);
+}
+
+static u64
+nv50_instobj_addr(struct nvkm_memory *memory)
+{
+	return nvkm_memory_addr(nv50_instobj(memory)->ram);
+}
+
+static u64
+nv50_instobj_bar2(struct nvkm_memory *memory)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	u64 addr = ~0ULL;
+	if (nv50_instobj_acquire(&iobj->base.memory)) {
+		iobj->lru.next = NULL; /* Exclude from eviction. */
+		addr = iobj->bar->addr;
+	}
+	nv50_instobj_release(&iobj->base.memory);
+	return addr;
+}
+
+static enum nvkm_memory_target
+nv50_instobj_target(struct nvkm_memory *memory)
+{
+	return nvkm_memory_target(nv50_instobj(memory)->ram);
+}
+
+static void *
+nv50_instobj_dtor(struct nvkm_memory *memory)
+{
+	struct nv50_instobj *iobj = nv50_instobj(memory);
+	struct nvkm_instmem *imem = &iobj->imem->base;
+	struct nvkm_vma *bar;
+	void *map;
+
+	mutex_lock(&imem->mutex);
+	if (likely(iobj->lru.next))
+		list_del(&iobj->lru);
+	map = iobj->map;
+	bar = iobj->bar;
+	mutex_unlock(&imem->mutex);
+
+	if (map) {
+		struct nvkm_vmm *vmm = nvkm_bar_bar2_vmm(imem->subdev.device);
+		iounmap(map);
+		if (likely(vmm)) /* Can be NULL during BAR destructor. */
+			nvkm_vmm_put(vmm, &bar);
+	}
+
+	nvkm_memory_unref(&iobj->ram);
+	nvkm_instobj_dtor(imem, &iobj->base);
+	return iobj;
+}
+
+static const struct nvkm_memory_func
+nv50_instobj_func = {
+	.dtor = nv50_instobj_dtor,
+	.target = nv50_instobj_target,
+	.bar2 = nv50_instobj_bar2,
+	.addr = nv50_instobj_addr,
+	.size = nv50_instobj_size,
+	.boot = nv50_instobj_boot,
+	.acquire = nv50_instobj_acquire,
+	.release = nv50_instobj_release,
+	.map = nv50_instobj_map,
+};
+
+static int
+nv50_instobj_wrap(struct nvkm_instmem *base,
+		  struct nvkm_memory *memory, struct nvkm_memory **pmemory)
+{
+	struct nv50_instmem *imem = nv50_instmem(base);
+	struct nv50_instobj *iobj;
+
+	if (!(iobj = kzalloc(sizeof(*iobj), GFP_KERNEL)))
+		return -ENOMEM;
+	*pmemory = &iobj->base.memory;
+
+	nvkm_instobj_ctor(&nv50_instobj_func, &imem->base, &iobj->base);
+	iobj->imem = imem;
+	refcount_set(&iobj->maps, 0);
+	INIT_LIST_HEAD(&iobj->lru);
+
+	iobj->ram = nvkm_memory_ref(memory);
+	return 0;
+}
+
+static int
+nv50_instobj_new(struct nvkm_instmem *imem, u32 size, u32 align, bool zero,
+		 struct nvkm_memory **pmemory)
+{
+	u8 page = max(order_base_2(align), 12);
+	struct nvkm_memory *ram;
+	int ret;
+
+	ret = nvkm_ram_get(imem->subdev.device, 0, 1, page, size, true, true, &ram);
+	if (ret)
+		return ret;
+
+	ret = nv50_instobj_wrap(imem, ram, pmemory);
+	nvkm_memory_unref(&ram);
+	return ret;
+}
+
+/******************************************************************************
+ * instmem subdev implementation
+ *****************************************************************************/
+
+static void
+nv50_instmem_fini(struct nvkm_instmem *base)
+{
+	nv50_instmem(base)->addr = ~0ULL;
+}
+
+static const struct nvkm_instmem_func
+nv50_instmem = {
+	.fini = nv50_instmem_fini,
+	.memory_new = nv50_instobj_new,
+	.memory_wrap = nv50_instobj_wrap,
+	.zero = false,
+};
+
+int
+nv50_instmem_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+		 struct nvkm_instmem **pimem)
+{
+	struct nv50_instmem *imem;
+
+	if (!(imem = kzalloc(sizeof(*imem), GFP_KERNEL)))
+		return -ENOMEM;
+	nvkm_instmem_ctor(&nv50_instmem, device, type, inst, &imem->base);
+	INIT_LIST_HEAD(&imem->lru);
+	*pimem = &imem->base;
+	return 0;
+}