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, 633 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
new file mode 100644
index 000000000..17899fc95
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
@@ -0,0 +1,633 @@
+/*
+ * Copyright 2017 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 "vmm.h"
+
+#include <core/client.h>
+#include <subdev/fb.h>
+#include <subdev/ltc.h>
+#include <subdev/timer.h>
+#include <engine/gr.h>
+
+#include <nvif/ifc00d.h>
+#include <nvif/unpack.h>
+
+static void
+gp100_vmm_pfn_unmap(struct nvkm_vmm *vmm,
+		    struct nvkm_mmu_pt *pt, u32 ptei, u32 ptes)
+{
+	struct device *dev = vmm->mmu->subdev.device->dev;
+	dma_addr_t addr;
+
+	nvkm_kmap(pt->memory);
+	while (ptes--) {
+		u32 datalo = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 0);
+		u32 datahi = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 4);
+		u64 data   = (u64)datahi << 32 | datalo;
+		if ((data & (3ULL << 1)) != 0) {
+			addr = (data >> 8) << 12;
+			dma_unmap_page(dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+		}
+		ptei++;
+	}
+	nvkm_done(pt->memory);
+}
+
+static bool
+gp100_vmm_pfn_clear(struct nvkm_vmm *vmm,
+		    struct nvkm_mmu_pt *pt, u32 ptei, u32 ptes)
+{
+	bool dma = false;
+	nvkm_kmap(pt->memory);
+	while (ptes--) {
+		u32 datalo = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 0);
+		u32 datahi = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 4);
+		u64 data   = (u64)datahi << 32 | datalo;
+		if ((data & BIT_ULL(0)) && (data & (3ULL << 1)) != 0) {
+			VMM_WO064(pt, vmm, ptei * 8, data & ~BIT_ULL(0));
+			dma = true;
+		}
+		ptei++;
+	}
+	nvkm_done(pt->memory);
+	return dma;
+}
+
+static void
+gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map)
+{
+	struct device *dev = vmm->mmu->subdev.device->dev;
+	dma_addr_t addr;
+
+	nvkm_kmap(pt->memory);
+	for (; ptes; ptes--, map->pfn++) {
+		u64 data = 0;
+
+		if (!(*map->pfn & NVKM_VMM_PFN_V))
+			continue;
+
+		if (!(*map->pfn & NVKM_VMM_PFN_W))
+			data |= BIT_ULL(6); /* RO. */
+
+		if (!(*map->pfn & NVKM_VMM_PFN_A))
+			data |= BIT_ULL(7); /* Atomic disable. */
+
+		if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) {
+			addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT;
+			addr = dma_map_page(dev, pfn_to_page(addr), 0,
+					    PAGE_SIZE, DMA_BIDIRECTIONAL);
+			if (!WARN_ON(dma_mapping_error(dev, addr))) {
+				data |= addr >> 4;
+				data |= 2ULL << 1; /* SYSTEM_COHERENT_MEMORY. */
+				data |= BIT_ULL(3); /* VOL. */
+				data |= BIT_ULL(0); /* VALID. */
+			}
+		} else {
+			data |= (*map->pfn & NVKM_VMM_PFN_ADDR) >> 4;
+			data |= BIT_ULL(0); /* VALID. */
+		}
+
+		VMM_WO064(pt, vmm, ptei++ * 8, data);
+	}
+	nvkm_done(pt->memory);
+}
+
+static inline void
+gp100_vmm_pgt_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map, u64 addr)
+{
+	u64 data = (addr >> 4) | map->type;
+
+	map->type += ptes * map->ctag;
+
+	while (ptes--) {
+		VMM_WO064(pt, vmm, ptei++ * 8, data);
+		data += map->next;
+	}
+}
+
+static void
+gp100_vmm_pgt_sgl(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map)
+{
+	VMM_MAP_ITER_SGL(vmm, pt, ptei, ptes, map, gp100_vmm_pgt_pte);
+}
+
+static void
+gp100_vmm_pgt_dma(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map)
+{
+	if (map->page->shift == PAGE_SHIFT) {
+		VMM_SPAM(vmm, "DMAA %08x %08x PTE(s)", ptei, ptes);
+		nvkm_kmap(pt->memory);
+		while (ptes--) {
+			const u64 data = (*map->dma++ >> 4) | map->type;
+			VMM_WO064(pt, vmm, ptei++ * 8, data);
+			map->type += map->ctag;
+		}
+		nvkm_done(pt->memory);
+		return;
+	}
+
+	VMM_MAP_ITER_DMA(vmm, pt, ptei, ptes, map, gp100_vmm_pgt_pte);
+}
+
+static void
+gp100_vmm_pgt_mem(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map)
+{
+	VMM_MAP_ITER_MEM(vmm, pt, ptei, ptes, map, gp100_vmm_pgt_pte);
+}
+
+static void
+gp100_vmm_pgt_sparse(struct nvkm_vmm *vmm,
+		     struct nvkm_mmu_pt *pt, u32 ptei, u32 ptes)
+{
+	/* VALID_FALSE + VOL tells the MMU to treat the PTE as sparse. */
+	VMM_FO064(pt, vmm, ptei * 8, BIT_ULL(3) /* VOL. */, ptes);
+}
+
+static const struct nvkm_vmm_desc_func
+gp100_vmm_desc_spt = {
+	.unmap = gf100_vmm_pgt_unmap,
+	.sparse = gp100_vmm_pgt_sparse,
+	.mem = gp100_vmm_pgt_mem,
+	.dma = gp100_vmm_pgt_dma,
+	.sgl = gp100_vmm_pgt_sgl,
+	.pfn = gp100_vmm_pgt_pfn,
+	.pfn_clear = gp100_vmm_pfn_clear,
+	.pfn_unmap = gp100_vmm_pfn_unmap,
+};
+
+static void
+gp100_vmm_lpt_invalid(struct nvkm_vmm *vmm,
+		      struct nvkm_mmu_pt *pt, u32 ptei, u32 ptes)
+{
+	/* VALID_FALSE + PRIV tells the MMU to ignore corresponding SPTEs. */
+	VMM_FO064(pt, vmm, ptei * 8, BIT_ULL(5) /* PRIV. */, ptes);
+}
+
+static const struct nvkm_vmm_desc_func
+gp100_vmm_desc_lpt = {
+	.invalid = gp100_vmm_lpt_invalid,
+	.unmap = gf100_vmm_pgt_unmap,
+	.sparse = gp100_vmm_pgt_sparse,
+	.mem = gp100_vmm_pgt_mem,
+};
+
+static inline void
+gp100_vmm_pd0_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map, u64 addr)
+{
+	u64 data = (addr >> 4) | map->type;
+
+	map->type += ptes * map->ctag;
+
+	while (ptes--) {
+		VMM_WO128(pt, vmm, ptei++ * 0x10, data, 0ULL);
+		data += map->next;
+	}
+}
+
+static void
+gp100_vmm_pd0_mem(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map)
+{
+	VMM_MAP_ITER_MEM(vmm, pt, ptei, ptes, map, gp100_vmm_pd0_pte);
+}
+
+static inline bool
+gp100_vmm_pde(struct nvkm_mmu_pt *pt, u64 *data)
+{
+	switch (nvkm_memory_target(pt->memory)) {
+	case NVKM_MEM_TARGET_VRAM: *data |= 1ULL << 1; break;
+	case NVKM_MEM_TARGET_HOST: *data |= 2ULL << 1;
+		*data |= BIT_ULL(3); /* VOL. */
+		break;
+	case NVKM_MEM_TARGET_NCOH: *data |= 3ULL << 1; break;
+	default:
+		WARN_ON(1);
+		return false;
+	}
+	*data |= pt->addr >> 4;
+	return true;
+}
+
+static void
+gp100_vmm_pd0_pde(struct nvkm_vmm *vmm, struct nvkm_vmm_pt *pgd, u32 pdei)
+{
+	struct nvkm_vmm_pt *pgt = pgd->pde[pdei];
+	struct nvkm_mmu_pt *pd = pgd->pt[0];
+	u64 data[2] = {};
+
+	if (pgt->pt[0] && !gp100_vmm_pde(pgt->pt[0], &data[0]))
+		return;
+	if (pgt->pt[1] && !gp100_vmm_pde(pgt->pt[1], &data[1]))
+		return;
+
+	nvkm_kmap(pd->memory);
+	VMM_WO128(pd, vmm, pdei * 0x10, data[0], data[1]);
+	nvkm_done(pd->memory);
+}
+
+static void
+gp100_vmm_pd0_sparse(struct nvkm_vmm *vmm,
+		     struct nvkm_mmu_pt *pt, u32 pdei, u32 pdes)
+{
+	/* VALID_FALSE + VOL_BIG tells the MMU to treat the PDE as sparse. */
+	VMM_FO128(pt, vmm, pdei * 0x10, BIT_ULL(3) /* VOL_BIG. */, 0ULL, pdes);
+}
+
+static void
+gp100_vmm_pd0_unmap(struct nvkm_vmm *vmm,
+		    struct nvkm_mmu_pt *pt, u32 pdei, u32 pdes)
+{
+	VMM_FO128(pt, vmm, pdei * 0x10, 0ULL, 0ULL, pdes);
+}
+
+static void
+gp100_vmm_pd0_pfn_unmap(struct nvkm_vmm *vmm,
+			struct nvkm_mmu_pt *pt, u32 ptei, u32 ptes)
+{
+	struct device *dev = vmm->mmu->subdev.device->dev;
+	dma_addr_t addr;
+
+	nvkm_kmap(pt->memory);
+	while (ptes--) {
+		u32 datalo = nvkm_ro32(pt->memory, pt->base + ptei * 16 + 0);
+		u32 datahi = nvkm_ro32(pt->memory, pt->base + ptei * 16 + 4);
+		u64 data   = (u64)datahi << 32 | datalo;
+
+		if ((data & (3ULL << 1)) != 0) {
+			addr = (data >> 8) << 12;
+			dma_unmap_page(dev, addr, 1UL << 21, DMA_BIDIRECTIONAL);
+		}
+		ptei++;
+	}
+	nvkm_done(pt->memory);
+}
+
+static bool
+gp100_vmm_pd0_pfn_clear(struct nvkm_vmm *vmm,
+			struct nvkm_mmu_pt *pt, u32 ptei, u32 ptes)
+{
+	bool dma = false;
+
+	nvkm_kmap(pt->memory);
+	while (ptes--) {
+		u32 datalo = nvkm_ro32(pt->memory, pt->base + ptei * 16 + 0);
+		u32 datahi = nvkm_ro32(pt->memory, pt->base + ptei * 16 + 4);
+		u64 data   = (u64)datahi << 32 | datalo;
+
+		if ((data & BIT_ULL(0)) && (data & (3ULL << 1)) != 0) {
+			VMM_WO064(pt, vmm, ptei * 16, data & ~BIT_ULL(0));
+			dma = true;
+		}
+		ptei++;
+	}
+	nvkm_done(pt->memory);
+	return dma;
+}
+
+static void
+gp100_vmm_pd0_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
+		  u32 ptei, u32 ptes, struct nvkm_vmm_map *map)
+{
+	struct device *dev = vmm->mmu->subdev.device->dev;
+	dma_addr_t addr;
+
+	nvkm_kmap(pt->memory);
+	for (; ptes; ptes--, map->pfn++) {
+		u64 data = 0;
+
+		if (!(*map->pfn & NVKM_VMM_PFN_V))
+			continue;
+
+		if (!(*map->pfn & NVKM_VMM_PFN_W))
+			data |= BIT_ULL(6); /* RO. */
+
+		if (!(*map->pfn & NVKM_VMM_PFN_A))
+			data |= BIT_ULL(7); /* Atomic disable. */
+
+		if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) {
+			addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT;
+			addr = dma_map_page(dev, pfn_to_page(addr), 0,
+					    1UL << 21, DMA_BIDIRECTIONAL);
+			if (!WARN_ON(dma_mapping_error(dev, addr))) {
+				data |= addr >> 4;
+				data |= 2ULL << 1; /* SYSTEM_COHERENT_MEMORY. */
+				data |= BIT_ULL(3); /* VOL. */
+				data |= BIT_ULL(0); /* VALID. */
+			}
+		} else {
+			data |= (*map->pfn & NVKM_VMM_PFN_ADDR) >> 4;
+			data |= BIT_ULL(0); /* VALID. */
+		}
+
+		VMM_WO064(pt, vmm, ptei++ * 16, data);
+	}
+	nvkm_done(pt->memory);
+}
+
+static const struct nvkm_vmm_desc_func
+gp100_vmm_desc_pd0 = {
+	.unmap = gp100_vmm_pd0_unmap,
+	.sparse = gp100_vmm_pd0_sparse,
+	.pde = gp100_vmm_pd0_pde,
+	.mem = gp100_vmm_pd0_mem,
+	.pfn = gp100_vmm_pd0_pfn,
+	.pfn_clear = gp100_vmm_pd0_pfn_clear,
+	.pfn_unmap = gp100_vmm_pd0_pfn_unmap,
+};
+
+static void
+gp100_vmm_pd1_pde(struct nvkm_vmm *vmm, struct nvkm_vmm_pt *pgd, u32 pdei)
+{
+	struct nvkm_vmm_pt *pgt = pgd->pde[pdei];
+	struct nvkm_mmu_pt *pd = pgd->pt[0];
+	u64 data = 0;
+
+	if (!gp100_vmm_pde(pgt->pt[0], &data))
+		return;
+
+	nvkm_kmap(pd->memory);
+	VMM_WO064(pd, vmm, pdei * 8, data);
+	nvkm_done(pd->memory);
+}
+
+static const struct nvkm_vmm_desc_func
+gp100_vmm_desc_pd1 = {
+	.unmap = gf100_vmm_pgt_unmap,
+	.sparse = gp100_vmm_pgt_sparse,
+	.pde = gp100_vmm_pd1_pde,
+};
+
+const struct nvkm_vmm_desc
+gp100_vmm_desc_16[] = {
+	{ LPT, 5,  8, 0x0100, &gp100_vmm_desc_lpt },
+	{ PGD, 8, 16, 0x1000, &gp100_vmm_desc_pd0 },
+	{ PGD, 9,  8, 0x1000, &gp100_vmm_desc_pd1 },
+	{ PGD, 9,  8, 0x1000, &gp100_vmm_desc_pd1 },
+	{ PGD, 2,  8, 0x1000, &gp100_vmm_desc_pd1 },
+	{}
+};
+
+const struct nvkm_vmm_desc
+gp100_vmm_desc_12[] = {
+	{ SPT, 9,  8, 0x1000, &gp100_vmm_desc_spt },
+	{ PGD, 8, 16, 0x1000, &gp100_vmm_desc_pd0 },
+	{ PGD, 9,  8, 0x1000, &gp100_vmm_desc_pd1 },
+	{ PGD, 9,  8, 0x1000, &gp100_vmm_desc_pd1 },
+	{ PGD, 2,  8, 0x1000, &gp100_vmm_desc_pd1 },
+	{}
+};
+
+int
+gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
+		struct nvkm_vmm_map *map)
+{
+	const enum nvkm_memory_target target = nvkm_memory_target(map->memory);
+	const struct nvkm_vmm_page *page = map->page;
+	union {
+		struct gp100_vmm_map_vn vn;
+		struct gp100_vmm_map_v0 v0;
+	} *args = argv;
+	struct nvkm_device *device = vmm->mmu->subdev.device;
+	struct nvkm_memory *memory = map->memory;
+	u8  kind, kind_inv, priv, ro, vol;
+	int kindn, aper, ret = -ENOSYS;
+	const u8 *kindm;
+
+	map->next = (1ULL << page->shift) >> 4;
+	map->type = 0;
+
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
+		vol  = !!args->v0.vol;
+		ro   = !!args->v0.ro;
+		priv = !!args->v0.priv;
+		kind =   args->v0.kind;
+	} else
+	if (!(ret = nvif_unvers(ret, &argv, &argc, args->vn))) {
+		vol  = target == NVKM_MEM_TARGET_HOST;
+		ro   = 0;
+		priv = 0;
+		kind = 0x00;
+	} else {
+		VMM_DEBUG(vmm, "args");
+		return ret;
+	}
+
+	aper = vmm->func->aper(target);
+	if (WARN_ON(aper < 0))
+		return aper;
+
+	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn, &kind_inv);
+	if (kind >= kindn || kindm[kind] == kind_inv) {
+		VMM_DEBUG(vmm, "kind %02x", kind);
+		return -EINVAL;
+	}
+
+	if (kindm[kind] != kind) {
+		u64 tags = nvkm_memory_size(memory) >> 16;
+		if (aper != 0 || !(page->type & NVKM_VMM_PAGE_COMP)) {
+			VMM_DEBUG(vmm, "comp %d %02x", aper, page->type);
+			return -EINVAL;
+		}
+
+		ret = nvkm_memory_tags_get(memory, device, tags,
+					   nvkm_ltc_tags_clear,
+					   &map->tags);
+		if (ret) {
+			VMM_DEBUG(vmm, "comp %d", ret);
+			return ret;
+		}
+
+		if (map->tags->mn) {
+			tags = map->tags->mn->offset + (map->offset >> 16);
+			map->ctag |= ((1ULL << page->shift) >> 16) << 36;
+			map->type |= tags << 36;
+			map->next |= map->ctag;
+		} else {
+			kind = kindm[kind];
+		}
+	}
+
+	map->type |= BIT(0);
+	map->type |= (u64)aper << 1;
+	map->type |= (u64) vol << 3;
+	map->type |= (u64)priv << 5;
+	map->type |= (u64)  ro << 6;
+	map->type |= (u64)kind << 56;
+	return 0;
+}
+
+static int
+gp100_vmm_fault_cancel(struct nvkm_vmm *vmm, void *argv, u32 argc)
+{
+	struct nvkm_device *device = vmm->mmu->subdev.device;
+	union {
+		struct gp100_vmm_fault_cancel_v0 v0;
+	} *args = argv;
+	int ret = -ENOSYS;
+	u32 aper;
+
+	if ((ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false)))
+		return ret;
+
+	/* Translate MaxwellFaultBufferA instance pointer to the same
+	 * format as the NV_GR_FECS_CURRENT_CTX register.
+	 */
+	aper = (args->v0.inst >> 8) & 3;
+	args->v0.inst >>= 12;
+	args->v0.inst |= aper << 28;
+	args->v0.inst |= 0x80000000;
+
+	if (!WARN_ON(nvkm_gr_ctxsw_pause(device))) {
+		if (nvkm_gr_ctxsw_inst(device) == args->v0.inst) {
+			gf100_vmm_invalidate(vmm, 0x0000001b
+					     /* CANCEL_TARGETED. */ |
+					     (args->v0.hub    << 20) |
+					     (args->v0.gpc    << 15) |
+					     (args->v0.client << 9));
+		}
+		WARN_ON(nvkm_gr_ctxsw_resume(device));
+	}
+
+	return 0;
+}
+
+static int
+gp100_vmm_fault_replay(struct nvkm_vmm *vmm, void *argv, u32 argc)
+{
+	union {
+		struct gp100_vmm_fault_replay_vn vn;
+	} *args = argv;
+	int ret = -ENOSYS;
+
+	if (!(ret = nvif_unvers(ret, &argv, &argc, args->vn))) {
+		gf100_vmm_invalidate(vmm, 0x0000000b); /* REPLAY_GLOBAL. */
+	}
+
+	return ret;
+}
+
+int
+gp100_vmm_mthd(struct nvkm_vmm *vmm,
+	       struct nvkm_client *client, u32 mthd, void *argv, u32 argc)
+{
+	switch (mthd) {
+	case GP100_VMM_VN_FAULT_REPLAY:
+		return gp100_vmm_fault_replay(vmm, argv, argc);
+	case GP100_VMM_VN_FAULT_CANCEL:
+		return gp100_vmm_fault_cancel(vmm, argv, argc);
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
+void
+gp100_vmm_invalidate_pdb(struct nvkm_vmm *vmm, u64 addr)
+{
+	struct nvkm_device *device = vmm->mmu->subdev.device;
+	nvkm_wr32(device, 0x100cb8, lower_32_bits(addr));
+	nvkm_wr32(device, 0x100cec, upper_32_bits(addr));
+}
+
+void
+gp100_vmm_flush(struct nvkm_vmm *vmm, int depth)
+{
+	u32 type = (5 /* CACHE_LEVEL_UP_TO_PDE3 */ - depth) << 24;
+	if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR]))
+		type |= 0x00000004; /* HUB_ONLY */
+	type |= 0x00000001; /* PAGE_ALL */
+	gf100_vmm_invalidate(vmm, type);
+}
+
+int
+gp100_vmm_join(struct nvkm_vmm *vmm, struct nvkm_memory *inst)
+{
+	u64 base = BIT_ULL(10) /* VER2 */ | BIT_ULL(11) /* 64KiB */;
+	if (vmm->replay) {
+		base |= BIT_ULL(4); /* FAULT_REPLAY_TEX */
+		base |= BIT_ULL(5); /* FAULT_REPLAY_GCC */
+	}
+	return gf100_vmm_join_(vmm, inst, base);
+}
+
+static const struct nvkm_vmm_func
+gp100_vmm = {
+	.join = gp100_vmm_join,
+	.part = gf100_vmm_part,
+	.aper = gf100_vmm_aper,
+	.valid = gp100_vmm_valid,
+	.flush = gp100_vmm_flush,
+	.mthd = gp100_vmm_mthd,
+	.invalidate_pdb = gp100_vmm_invalidate_pdb,
+	.page = {
+		{ 47, &gp100_vmm_desc_16[4], NVKM_VMM_PAGE_Sxxx },
+		{ 38, &gp100_vmm_desc_16[3], NVKM_VMM_PAGE_Sxxx },
+		{ 29, &gp100_vmm_desc_16[2], NVKM_VMM_PAGE_Sxxx },
+		{ 21, &gp100_vmm_desc_16[1], NVKM_VMM_PAGE_SVxC },
+		{ 16, &gp100_vmm_desc_16[0], NVKM_VMM_PAGE_SVxC },
+		{ 12, &gp100_vmm_desc_12[0], NVKM_VMM_PAGE_SVHx },
+		{}
+	}
+};
+
+int
+gp100_vmm_new_(const struct nvkm_vmm_func *func,
+	       struct nvkm_mmu *mmu, bool managed, u64 addr, u64 size,
+	       void *argv, u32 argc, struct lock_class_key *key,
+	       const char *name, struct nvkm_vmm **pvmm)
+{
+	union {
+		struct gp100_vmm_vn vn;
+		struct gp100_vmm_v0 v0;
+	} *args = argv;
+	int ret = -ENOSYS;
+	bool replay;
+
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
+		replay = args->v0.fault_replay != 0;
+	} else
+	if (!(ret = nvif_unvers(ret, &argv, &argc, args->vn))) {
+		replay = false;
+	} else
+		return ret;
+
+	ret = nvkm_vmm_new_(func, mmu, 0, managed, addr, size, key, name, pvmm);
+	if (ret)
+		return ret;
+
+	(*pvmm)->replay = replay;
+	return 0;
+}
+
+int
+gp100_vmm_new(struct nvkm_mmu *mmu, bool managed, u64 addr, u64 size,
+	      void *argv, u32 argc, struct lock_class_key *key,
+	      const char *name, struct nvkm_vmm **pvmm)
+{
+	return gp100_vmm_new_(&gp100_vmm, mmu, managed, addr, size,
+			      argv, argc, key, name, pvmm);
+}