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, 442 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/core/intr.c b/drivers/gpu/drm/nouveau/nvkm/core/intr.c
new file mode 100644
index 000000000..e20b7ca21
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/core/intr.c
@@ -0,0 +1,442 @@
+/*
+ * Copyright 2021 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.
+ */
+#include <core/intr.h>
+#include <core/device.h>
+#include <core/subdev.h>
+#include <subdev/pci.h>
+#include <subdev/top.h>
+
+static int
+nvkm_intr_xlat(struct nvkm_subdev *subdev, struct nvkm_intr *intr,
+	       enum nvkm_intr_type type, int *leaf, u32 *mask)
+{
+	struct nvkm_device *device = subdev->device;
+
+	if (type < NVKM_INTR_VECTOR_0) {
+		if (type == NVKM_INTR_SUBDEV) {
+			const struct nvkm_intr_data *data = intr->data;
+			struct nvkm_top_device *tdev;
+
+			while (data && data->mask) {
+				if (data->type == NVKM_SUBDEV_TOP) {
+					list_for_each_entry(tdev, &device->top->device, head) {
+						if (tdev->intr >= 0 &&
+						    tdev->type == subdev->type &&
+						    tdev->inst == subdev->inst) {
+							if (data->mask & BIT(tdev->intr)) {
+								*leaf = data->leaf;
+								*mask = BIT(tdev->intr);
+								return 0;
+							}
+						}
+					}
+				} else
+				if (data->type == subdev->type && data->inst == subdev->inst) {
+					*leaf = data->leaf;
+					*mask = data->mask;
+					return 0;
+				}
+
+				data++;
+			}
+		} else {
+			return -ENOSYS;
+		}
+	} else {
+		if (type < intr->leaves * sizeof(*intr->stat) * 8) {
+			*leaf = type / 32;
+			*mask = BIT(type % 32);
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static struct nvkm_intr *
+nvkm_intr_find(struct nvkm_subdev *subdev, enum nvkm_intr_type type, int *leaf, u32 *mask)
+{
+	struct nvkm_intr *intr;
+	int ret;
+
+	list_for_each_entry(intr, &subdev->device->intr.intr, head) {
+		ret = nvkm_intr_xlat(subdev, intr, type, leaf, mask);
+		if (ret == 0)
+			return intr;
+	}
+
+	return NULL;
+}
+
+static void
+nvkm_intr_allow_locked(struct nvkm_intr *intr, int leaf, u32 mask)
+{
+	intr->mask[leaf] |= mask;
+	if (intr->func->allow) {
+		if (intr->func->reset)
+			intr->func->reset(intr, leaf, mask);
+		intr->func->allow(intr, leaf, mask);
+	}
+}
+
+void
+nvkm_intr_allow(struct nvkm_subdev *subdev, enum nvkm_intr_type type)
+{
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_intr *intr;
+	unsigned long flags;
+	int leaf;
+	u32 mask;
+
+	intr = nvkm_intr_find(subdev, type, &leaf, &mask);
+	if (intr) {
+		nvkm_debug(intr->subdev, "intr %d/%08x allowed by %s\n", leaf, mask, subdev->name);
+		spin_lock_irqsave(&device->intr.lock, flags);
+		nvkm_intr_allow_locked(intr, leaf, mask);
+		spin_unlock_irqrestore(&device->intr.lock, flags);
+	}
+}
+
+static void
+nvkm_intr_block_locked(struct nvkm_intr *intr, int leaf, u32 mask)
+{
+	intr->mask[leaf] &= ~mask;
+	if (intr->func->block)
+		intr->func->block(intr, leaf, mask);
+}
+
+void
+nvkm_intr_block(struct nvkm_subdev *subdev, enum nvkm_intr_type type)
+{
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_intr *intr;
+	unsigned long flags;
+	int leaf;
+	u32 mask;
+
+	intr = nvkm_intr_find(subdev, type, &leaf, &mask);
+	if (intr) {
+		nvkm_debug(intr->subdev, "intr %d/%08x blocked by %s\n", leaf, mask, subdev->name);
+		spin_lock_irqsave(&device->intr.lock, flags);
+		nvkm_intr_block_locked(intr, leaf, mask);
+		spin_unlock_irqrestore(&device->intr.lock, flags);
+	}
+}
+
+static void
+nvkm_intr_rearm_locked(struct nvkm_device *device)
+{
+	struct nvkm_intr *intr;
+
+	list_for_each_entry(intr, &device->intr.intr, head)
+		intr->func->rearm(intr);
+}
+
+static void
+nvkm_intr_unarm_locked(struct nvkm_device *device)
+{
+	struct nvkm_intr *intr;
+
+	list_for_each_entry(intr, &device->intr.intr, head)
+		intr->func->unarm(intr);
+}
+
+static irqreturn_t
+nvkm_intr(int irq, void *arg)
+{
+	struct nvkm_device *device = arg;
+	struct nvkm_intr *intr;
+	struct nvkm_inth *inth;
+	irqreturn_t ret = IRQ_NONE;
+	bool pending = false;
+	int prio, leaf;
+
+	/* Disable all top-level interrupt sources, and re-arm MSI interrupts. */
+	spin_lock(&device->intr.lock);
+	if (!device->intr.armed)
+		goto done_unlock;
+
+	nvkm_intr_unarm_locked(device);
+	nvkm_pci_msi_rearm(device);
+
+	/* Fetch pending interrupt masks. */
+	list_for_each_entry(intr, &device->intr.intr, head) {
+		if (intr->func->pending(intr))
+			pending = true;
+	}
+
+	if (!pending)
+		goto done;
+
+	/* Check that GPU is still on the bus by reading NV_PMC_BOOT_0. */
+	if (WARN_ON(nvkm_rd32(device, 0x000000) == 0xffffffff))
+		goto done;
+
+	/* Execute handlers. */
+	for (prio = 0; prio < ARRAY_SIZE(device->intr.prio); prio++) {
+		list_for_each_entry(inth, &device->intr.prio[prio], head) {
+			struct nvkm_intr *intr = inth->intr;
+
+			if (intr->stat[inth->leaf] & inth->mask) {
+				if (atomic_read(&inth->allowed)) {
+					if (intr->func->reset)
+						intr->func->reset(intr, inth->leaf, inth->mask);
+					if (inth->func(inth) == IRQ_HANDLED)
+						ret = IRQ_HANDLED;
+				}
+			}
+		}
+	}
+
+	/* Nothing handled?  Some debugging/protection from IRQ storms is in order... */
+	if (ret == IRQ_NONE) {
+		list_for_each_entry(intr, &device->intr.intr, head) {
+			for (leaf = 0; leaf < intr->leaves; leaf++) {
+				if (intr->stat[leaf]) {
+					nvkm_warn(intr->subdev, "intr%d: %08x\n",
+						  leaf, intr->stat[leaf]);
+					nvkm_intr_block_locked(intr, leaf, intr->stat[leaf]);
+				}
+			}
+		}
+	}
+
+done:
+	/* Re-enable all top-level interrupt sources. */
+	nvkm_intr_rearm_locked(device);
+done_unlock:
+	spin_unlock(&device->intr.lock);
+	return ret;
+}
+
+int
+nvkm_intr_add(const struct nvkm_intr_func *func, const struct nvkm_intr_data *data,
+	      struct nvkm_subdev *subdev, int leaves, struct nvkm_intr *intr)
+{
+	struct nvkm_device *device = subdev->device;
+	int i;
+
+	intr->func = func;
+	intr->data = data;
+	intr->subdev = subdev;
+	intr->leaves = leaves;
+	intr->stat = kcalloc(leaves, sizeof(*intr->stat), GFP_KERNEL);
+	intr->mask = kcalloc(leaves, sizeof(*intr->mask), GFP_KERNEL);
+	if (!intr->stat || !intr->mask) {
+		kfree(intr->stat);
+		return -ENOMEM;
+	}
+
+	if (intr->subdev->debug >= NV_DBG_DEBUG) {
+		for (i = 0; i < intr->leaves; i++)
+			intr->mask[i] = ~0;
+	}
+
+	spin_lock_irq(&device->intr.lock);
+	list_add_tail(&intr->head, &device->intr.intr);
+	spin_unlock_irq(&device->intr.lock);
+	return 0;
+}
+
+static irqreturn_t
+nvkm_intr_subdev(struct nvkm_inth *inth)
+{
+	struct nvkm_subdev *subdev = container_of(inth, typeof(*subdev), inth);
+
+	nvkm_subdev_intr(subdev);
+	return IRQ_HANDLED;
+}
+
+static void
+nvkm_intr_subdev_add_dev(struct nvkm_intr *intr, enum nvkm_subdev_type type, int inst)
+{
+	struct nvkm_subdev *subdev;
+	enum nvkm_intr_prio prio;
+	int ret;
+
+	subdev = nvkm_device_subdev(intr->subdev->device, type, inst);
+	if (!subdev || !subdev->func->intr)
+		return;
+
+	if (type == NVKM_ENGINE_DISP)
+		prio = NVKM_INTR_PRIO_VBLANK;
+	else
+		prio = NVKM_INTR_PRIO_NORMAL;
+
+	ret = nvkm_inth_add(intr, NVKM_INTR_SUBDEV, prio, subdev, nvkm_intr_subdev, &subdev->inth);
+	if (WARN_ON(ret))
+		return;
+
+	nvkm_inth_allow(&subdev->inth);
+}
+
+static void
+nvkm_intr_subdev_add(struct nvkm_intr *intr)
+{
+	const struct nvkm_intr_data *data;
+	struct nvkm_device *device = intr->subdev->device;
+	struct nvkm_top_device *tdev;
+
+	for (data = intr->data; data && data->mask; data++) {
+		if (data->legacy) {
+			if (data->type == NVKM_SUBDEV_TOP) {
+				list_for_each_entry(tdev, &device->top->device, head) {
+					if (tdev->intr < 0 || !(data->mask & BIT(tdev->intr)))
+						continue;
+
+					nvkm_intr_subdev_add_dev(intr, tdev->type, tdev->inst);
+				}
+			} else {
+				nvkm_intr_subdev_add_dev(intr, data->type, data->inst);
+			}
+		}
+	}
+}
+
+void
+nvkm_intr_rearm(struct nvkm_device *device)
+{
+	struct nvkm_intr *intr;
+	int i;
+
+	if (unlikely(!device->intr.legacy_done)) {
+		list_for_each_entry(intr, &device->intr.intr, head)
+			nvkm_intr_subdev_add(intr);
+		device->intr.legacy_done = true;
+	}
+
+	spin_lock_irq(&device->intr.lock);
+	list_for_each_entry(intr, &device->intr.intr, head) {
+		for (i = 0; intr->func->block && i < intr->leaves; i++) {
+			intr->func->block(intr, i, ~0);
+			intr->func->allow(intr, i, intr->mask[i]);
+		}
+	}
+
+	nvkm_intr_rearm_locked(device);
+	device->intr.armed = true;
+	spin_unlock_irq(&device->intr.lock);
+}
+
+void
+nvkm_intr_unarm(struct nvkm_device *device)
+{
+	spin_lock_irq(&device->intr.lock);
+	nvkm_intr_unarm_locked(device);
+	device->intr.armed = false;
+	spin_unlock_irq(&device->intr.lock);
+}
+
+int
+nvkm_intr_install(struct nvkm_device *device)
+{
+	int ret;
+
+	device->intr.irq = device->func->irq(device);
+	if (device->intr.irq < 0)
+		return device->intr.irq;
+
+	ret = request_irq(device->intr.irq, nvkm_intr, IRQF_SHARED, "nvkm", device);
+	if (ret)
+		return ret;
+
+	device->intr.alloc = true;
+	return 0;
+}
+
+void
+nvkm_intr_dtor(struct nvkm_device *device)
+{
+	struct nvkm_intr *intr, *intt;
+
+	list_for_each_entry_safe(intr, intt, &device->intr.intr, head) {
+		list_del(&intr->head);
+		kfree(intr->mask);
+		kfree(intr->stat);
+	}
+
+	if (device->intr.alloc)
+		free_irq(device->intr.irq, device);
+}
+
+void
+nvkm_intr_ctor(struct nvkm_device *device)
+{
+	int i;
+
+	INIT_LIST_HEAD(&device->intr.intr);
+	for (i = 0; i < ARRAY_SIZE(device->intr.prio); i++)
+		INIT_LIST_HEAD(&device->intr.prio[i]);
+
+	spin_lock_init(&device->intr.lock);
+	device->intr.armed = false;
+}
+
+void
+nvkm_inth_block(struct nvkm_inth *inth)
+{
+	if (unlikely(!inth->intr))
+		return;
+
+	atomic_set(&inth->allowed, 0);
+}
+
+void
+nvkm_inth_allow(struct nvkm_inth *inth)
+{
+	struct nvkm_intr *intr = inth->intr;
+	unsigned long flags;
+
+	if (unlikely(!inth->intr))
+		return;
+
+	spin_lock_irqsave(&intr->subdev->device->intr.lock, flags);
+	if (!atomic_xchg(&inth->allowed, 1)) {
+		if ((intr->mask[inth->leaf] & inth->mask) != inth->mask)
+			nvkm_intr_allow_locked(intr, inth->leaf, inth->mask);
+	}
+	spin_unlock_irqrestore(&intr->subdev->device->intr.lock, flags);
+}
+
+int
+nvkm_inth_add(struct nvkm_intr *intr, enum nvkm_intr_type type, enum nvkm_intr_prio prio,
+	      struct nvkm_subdev *subdev, nvkm_inth_func func, struct nvkm_inth *inth)
+{
+	struct nvkm_device *device = subdev->device;
+	int ret;
+
+	if (WARN_ON(inth->mask))
+		return -EBUSY;
+
+	ret = nvkm_intr_xlat(subdev, intr, type, &inth->leaf, &inth->mask);
+	if (ret)
+		return ret;
+
+	nvkm_debug(intr->subdev, "intr %d/%08x requested by %s\n",
+		   inth->leaf, inth->mask, subdev->name);
+
+	inth->intr = intr;
+	inth->func = func;
+	atomic_set(&inth->allowed, 0);
+	list_add_tail(&inth->head, &device->intr.prio[prio]);
+	return 0;
+}