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, 550 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
new file mode 100644
index 000000000..12a5d99d5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
@@ -0,0 +1,550 @@
+/*
+ * 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 "priv.h"
+#include "cgrp.h"
+#include "chan.h"
+#include "chid.h"
+#include "runl.h"
+#include "runq.h"
+
+#include <core/gpuobj.h>
+#include <subdev/top.h>
+#include <subdev/vfn.h>
+
+#include <nvif/class.h>
+
+/*TODO: allocate? */
+#define GA100_FIFO_NONSTALL_VECTOR 0
+
+static u32
+ga100_chan_doorbell_handle(struct nvkm_chan *chan)
+{
+	return (chan->cgrp->runl->doorbell << 16) | chan->id;
+}
+
+static void
+ga100_chan_stop(struct nvkm_chan *chan)
+{
+	struct nvkm_runl *runl = chan->cgrp->runl;
+
+	nvkm_wr32(runl->fifo->engine.subdev.device, runl->chan + (chan->id * 4), 0x00000003);
+}
+
+static void
+ga100_chan_start(struct nvkm_chan *chan)
+{
+	struct nvkm_runl *runl = chan->cgrp->runl;
+	struct nvkm_device *device = runl->fifo->engine.subdev.device;
+	const int gfid = 0;
+
+	nvkm_wr32(device, runl->chan + (chan->id * 4), 0x00000002);
+	nvkm_wr32(device, runl->addr + 0x0090, (gfid << 16) | chan->id); /* INTERNAL_DOORBELL. */
+}
+
+static void
+ga100_chan_unbind(struct nvkm_chan *chan)
+{
+	struct nvkm_runl *runl = chan->cgrp->runl;
+
+	nvkm_wr32(runl->fifo->engine.subdev.device, runl->chan + (chan->id * 4), 0xffffffff);
+}
+
+static int
+ga100_chan_ramfc_write(struct nvkm_chan *chan, u64 offset, u64 length, u32 devm, bool priv)
+{
+	const u32 limit2 = ilog2(length / 8);
+
+	nvkm_kmap(chan->inst);
+	nvkm_wo32(chan->inst, 0x010, 0x0000face);
+	nvkm_wo32(chan->inst, 0x030, 0x7ffff902);
+	nvkm_wo32(chan->inst, 0x048, lower_32_bits(offset));
+	nvkm_wo32(chan->inst, 0x04c, upper_32_bits(offset) | (limit2 << 16));
+	nvkm_wo32(chan->inst, 0x084, 0x20400000);
+	nvkm_wo32(chan->inst, 0x094, 0x30000000 | devm);
+	nvkm_wo32(chan->inst, 0x0e4, priv ? 0x00000020 : 0x00000000);
+	nvkm_wo32(chan->inst, 0x0e8, chan->id);
+	nvkm_wo32(chan->inst, 0x0f4, 0x00001000 | (priv ? 0x00000100 : 0x00000000));
+	nvkm_wo32(chan->inst, 0x0f8, 0x80000000 | GA100_FIFO_NONSTALL_VECTOR);
+	nvkm_mo32(chan->inst, 0x218, 0x00000000, 0x00000000);
+	nvkm_done(chan->inst);
+	return 0;
+}
+
+static const struct nvkm_chan_func_ramfc
+ga100_chan_ramfc = {
+	.write = ga100_chan_ramfc_write,
+	.devm = 0xfff,
+	.priv = true,
+};
+
+const struct nvkm_chan_func
+ga100_chan = {
+	.inst = &gf100_chan_inst,
+	.userd = &gv100_chan_userd,
+	.ramfc = &ga100_chan_ramfc,
+	.unbind = ga100_chan_unbind,
+	.start = ga100_chan_start,
+	.stop = ga100_chan_stop,
+	.preempt = gk110_chan_preempt,
+	.doorbell_handle = ga100_chan_doorbell_handle,
+};
+
+static void
+ga100_cgrp_preempt(struct nvkm_cgrp *cgrp)
+{
+	struct nvkm_runl *runl = cgrp->runl;
+
+	nvkm_wr32(runl->fifo->engine.subdev.device, runl->addr + 0x098, 0x01000000 | cgrp->id);
+}
+
+const struct nvkm_cgrp_func
+ga100_cgrp = {
+	.preempt = ga100_cgrp_preempt,
+};
+
+static int
+ga100_engn_cxid(struct nvkm_engn *engn, bool *cgid)
+{
+	struct nvkm_runl *runl = engn->runl;
+	struct nvkm_device *device = runl->fifo->engine.subdev.device;
+	u32 stat = nvkm_rd32(device, runl->addr + 0x200 + engn->id * 0x40);
+
+	ENGN_DEBUG(engn, "status %08x", stat);
+	*cgid = true;
+
+	switch ((stat & 0x0000e000) >> 13) {
+	case 0 /* INVALID */: return -ENODEV;
+	case 1 /*   VALID */:
+	case 5 /*    SAVE */: return (stat & 0x00000fff);
+	case 6 /*    LOAD */: return (stat & 0x0fff0000) >> 16;
+	case 7 /*  SWITCH */:
+		if (nvkm_engine_chsw_load(engn->engine))
+			return (stat & 0x0fff0000) >> 16;
+		return (stat & 0x00000fff);
+	default:
+		WARN_ON(1);
+		break;
+	}
+
+	return -ENODEV;
+}
+
+const struct nvkm_engn_func
+ga100_engn = {
+	.cxid = ga100_engn_cxid,
+	.ctor = gk104_ectx_ctor,
+	.bind = gv100_ectx_bind,
+};
+
+const struct nvkm_engn_func
+ga100_engn_ce = {
+	.cxid = ga100_engn_cxid,
+	.ctor = gv100_ectx_ce_ctor,
+	.bind = gv100_ectx_ce_bind,
+};
+
+static bool
+ga100_runq_idle(struct nvkm_runq *runq)
+{
+	struct nvkm_device *device = runq->fifo->engine.subdev.device;
+
+	return !(nvkm_rd32(device, 0x04015c + (runq->id * 0x800)) & 0x0000e000);
+}
+
+static bool
+ga100_runq_intr_1(struct nvkm_runq *runq, struct nvkm_runl *runl)
+{
+	struct nvkm_device *device = runq->fifo->engine.subdev.device;
+	u32 inte = nvkm_rd32(device, 0x040180 + (runq->id * 0x800));
+	u32 intr = nvkm_rd32(device, 0x040148 + (runq->id * 0x800));
+	u32 stat = intr & inte;
+
+	if (!stat) {
+		RUNQ_DEBUG(runq, "inte1 %08x %08x", intr, inte);
+		return false;
+	}
+
+	if (stat & 0x80000000) {
+		u32 chid = nvkm_rd32(device, 0x040120 + (runq->id * 0x0800)) & runl->chid->mask;
+		struct nvkm_chan *chan;
+		unsigned long flags;
+
+		RUNQ_ERROR(runq, "CTXNOTVALID chid:%d", chid);
+		chan = nvkm_runl_chan_get_chid(runl, chid, &flags);
+		if (chan) {
+			nvkm_chan_error(chan, true);
+			nvkm_chan_put(&chan, flags);
+		}
+
+		nvkm_mask(device, 0x0400ac + (runq->id * 0x800), 0x00030000, 0x00030000);
+		stat &= ~0x80000000;
+	}
+
+	if (stat) {
+		RUNQ_ERROR(runq, "intr1 %08x", stat);
+		nvkm_wr32(device, 0x0401a0 + (runq->id * 0x800), stat);
+	}
+
+	nvkm_wr32(device, 0x040148 + (runq->id * 0x800), intr);
+	return true;
+}
+
+static bool
+ga100_runq_intr_0(struct nvkm_runq *runq, struct nvkm_runl *runl)
+{
+	struct nvkm_device *device = runq->fifo->engine.subdev.device;
+	u32 inte = nvkm_rd32(device, 0x040170 + (runq->id * 0x800));
+	u32 intr = nvkm_rd32(device, 0x040108 + (runq->id * 0x800));
+	u32 stat = intr & inte;
+
+	if (!stat) {
+		RUNQ_DEBUG(runq, "inte0 %08x %08x", intr, inte);
+		return false;
+	}
+
+	/*TODO: expand on this when fixing up gf100's version. */
+	if (stat & 0xc6afe000) {
+		u32 chid = nvkm_rd32(device, 0x040120 + (runq->id * 0x0800)) & runl->chid->mask;
+		struct nvkm_chan *chan;
+		unsigned long flags;
+
+		RUNQ_ERROR(runq, "intr0 %08x", stat);
+		chan = nvkm_runl_chan_get_chid(runl, chid, &flags);
+		if (chan) {
+			nvkm_chan_error(chan, true);
+			nvkm_chan_put(&chan, flags);
+		}
+
+		stat &= ~0xc6afe000;
+	}
+
+	if (stat) {
+		RUNQ_ERROR(runq, "intr0 %08x", stat);
+		nvkm_wr32(device, 0x040190 + (runq->id * 0x800), stat);
+	}
+
+	nvkm_wr32(device, 0x040108 + (runq->id * 0x800), intr);
+	return true;
+}
+
+static bool
+ga100_runq_intr(struct nvkm_runq *runq, struct nvkm_runl *runl)
+{
+	bool intr0 = ga100_runq_intr_0(runq, runl);
+	bool intr1 = ga100_runq_intr_1(runq, runl);
+
+	return intr0 || intr1;
+}
+
+static void
+ga100_runq_init(struct nvkm_runq *runq)
+{
+	struct nvkm_device *device = runq->fifo->engine.subdev.device;
+
+	nvkm_wr32(device, 0x040108 + (runq->id * 0x800), 0xffffffff); /* INTR_0 */
+	nvkm_wr32(device, 0x040148 + (runq->id * 0x800), 0xffffffff); /* INTR_1 */
+	nvkm_wr32(device, 0x040170 + (runq->id * 0x800), 0xffffffff); /* INTR_0_EN_SET_TREE */
+	nvkm_wr32(device, 0x040180 + (runq->id * 0x800), 0xffffffff); /* INTR_1_EN_SET_TREE */
+}
+
+const struct nvkm_runq_func
+ga100_runq = {
+	.init = ga100_runq_init,
+	.intr = ga100_runq_intr,
+	.idle = ga100_runq_idle,
+};
+
+static bool
+ga100_runl_preempt_pending(struct nvkm_runl *runl)
+{
+	return nvkm_rd32(runl->fifo->engine.subdev.device, runl->addr + 0x098) & 0x00100000;
+}
+
+static void
+ga100_runl_preempt(struct nvkm_runl *runl)
+{
+	nvkm_wr32(runl->fifo->engine.subdev.device, runl->addr + 0x098, 0x00000000);
+}
+
+static void
+ga100_runl_allow(struct nvkm_runl *runl, u32 engm)
+{
+	nvkm_mask(runl->fifo->engine.subdev.device, runl->addr + 0x094, 0x00000001, 0x00000000);
+}
+
+static void
+ga100_runl_block(struct nvkm_runl *runl, u32 engm)
+{
+	nvkm_mask(runl->fifo->engine.subdev.device, runl->addr + 0x094, 0x00000001, 0x00000001);
+}
+
+static bool
+ga100_runl_pending(struct nvkm_runl *runl)
+{
+	struct nvkm_device *device = runl->fifo->engine.subdev.device;
+
+	return nvkm_rd32(device, runl->addr + 0x08c) & 0x00008000;
+}
+
+static void
+ga100_runl_commit(struct nvkm_runl *runl, struct nvkm_memory *memory, u32 start, int count)
+{
+	struct nvkm_device *device = runl->fifo->engine.subdev.device;
+	u64 addr = nvkm_memory_addr(memory) + start;
+
+	nvkm_wr32(device, runl->addr + 0x080, lower_32_bits(addr));
+	nvkm_wr32(device, runl->addr + 0x084, upper_32_bits(addr));
+	nvkm_wr32(device, runl->addr + 0x088, count);
+}
+
+static irqreturn_t
+ga100_runl_intr(struct nvkm_inth *inth)
+{
+	struct nvkm_runl *runl = container_of(inth, typeof(*runl), inth);
+	struct nvkm_engn *engn;
+	struct nvkm_device *device = runl->fifo->engine.subdev.device;
+	u32 inte = nvkm_rd32(device, runl->addr + 0x120);
+	u32 intr = nvkm_rd32(device, runl->addr + 0x100);
+	u32 stat = intr & inte;
+	u32 info;
+
+	if (!stat) {
+		RUNL_DEBUG(runl, "inte %08x %08x", intr, inte);
+		return IRQ_NONE;
+	}
+
+	if (stat & 0x00000007) {
+		nvkm_runl_foreach_engn_cond(engn, runl, stat & BIT(engn->id)) {
+			info = nvkm_rd32(device, runl->addr + 0x224 + (engn->id * 0x40));
+
+			tu102_fifo_intr_ctxsw_timeout_info(engn, info);
+
+			nvkm_wr32(device, runl->addr + 0x100, BIT(engn->id));
+			stat &= ~BIT(engn->id);
+		}
+	}
+
+	if (stat & 0x00000300) {
+		nvkm_wr32(device, runl->addr + 0x100, stat & 0x00000300);
+		stat &= ~0x00000300;
+	}
+
+	if (stat & 0x00010000) {
+		if (runl->runq[0]) {
+			if (runl->runq[0]->func->intr(runl->runq[0], runl))
+				stat &= ~0x00010000;
+		}
+	}
+
+	if (stat & 0x00020000) {
+		if (runl->runq[1]) {
+			if (runl->runq[1]->func->intr(runl->runq[1], runl))
+				stat &= ~0x00020000;
+		}
+	}
+
+	if (stat) {
+		RUNL_ERROR(runl, "intr %08x", stat);
+		nvkm_wr32(device, runl->addr + 0x140, stat);
+	}
+
+	nvkm_wr32(device, runl->addr + 0x180, 0x00000001);
+	return IRQ_HANDLED;
+}
+
+static void
+ga100_runl_fini(struct nvkm_runl *runl)
+{
+	nvkm_mask(runl->fifo->engine.subdev.device, runl->addr + 0x300, 0x80000000, 0x00000000);
+	nvkm_inth_block(&runl->inth);
+}
+
+static void
+ga100_runl_init(struct nvkm_runl *runl)
+{
+	struct nvkm_fifo *fifo = runl->fifo;
+	struct nvkm_runq *runq;
+	struct nvkm_device *device = fifo->engine.subdev.device;
+	int i;
+
+	/* Submit NULL runlist and preempt. */
+	nvkm_wr32(device, runl->addr + 0x088, 0x00000000);
+	runl->func->preempt(runl);
+
+	/* Enable doorbell. */
+	nvkm_mask(device, runl->addr + 0x300, 0x80000000, 0x80000000);
+
+	nvkm_wr32(device, runl->addr + 0x100, 0xffffffff); /* INTR_0 */
+	nvkm_wr32(device, runl->addr + 0x140, 0xffffffff); /* INTR_0_EN_CLEAR_TREE(0) */
+	nvkm_wr32(device, runl->addr + 0x120, 0x000f1307); /* INTR_0_EN_SET_TREE(0) */
+	nvkm_wr32(device, runl->addr + 0x148, 0xffffffff); /* INTR_0_EN_CLEAR_TREE(1) */
+	nvkm_wr32(device, runl->addr + 0x128, 0x00000000); /* INTR_0_EN_SET_TREE(1) */
+
+	/* Init PBDMA(s). */
+	for (i = 0; i < runl->runq_nr; i++) {
+		runq = runl->runq[i];
+		runq->func->init(runq);
+	}
+
+	nvkm_inth_allow(&runl->inth);
+}
+
+const struct nvkm_runl_func
+ga100_runl = {
+	.init = ga100_runl_init,
+	.fini = ga100_runl_fini,
+	.size = 16,
+	.update = nv50_runl_update,
+	.insert_cgrp = gv100_runl_insert_cgrp,
+	.insert_chan = gv100_runl_insert_chan,
+	.commit = ga100_runl_commit,
+	.wait = nv50_runl_wait,
+	.pending = ga100_runl_pending,
+	.block = ga100_runl_block,
+	.allow = ga100_runl_allow,
+	.preempt = ga100_runl_preempt,
+	.preempt_pending = ga100_runl_preempt_pending,
+};
+
+static int
+ga100_runl_new(struct nvkm_fifo *fifo, int id, u32 addr, struct nvkm_runl **prunl)
+{
+	struct nvkm_device *device = fifo->engine.subdev.device;
+	struct nvkm_runl *runl;
+	u32 chcfg  = nvkm_rd32(device, addr + 0x004);
+	u32 chnum  = 1 << (chcfg & 0x0000000f);
+	u32 chaddr = (chcfg & 0xfffffff0);
+	u32 dbcfg  = nvkm_rd32(device, addr + 0x008);
+	u32 vector = nvkm_rd32(device, addr + 0x160);
+	int i, ret;
+
+	runl = *prunl = nvkm_runl_new(fifo, id, addr, chnum);
+	if (IS_ERR(runl))
+		return PTR_ERR(runl);
+
+	for (i = 0; i < 2; i++) {
+		u32 pbcfg = nvkm_rd32(device, addr + 0x010 + (i * 0x04));
+		if (pbcfg & 0x80000000) {
+			runl->runq[runl->runq_nr] =
+				nvkm_runq_new(fifo, ((pbcfg & 0x03fffc00) - 0x040000) / 0x800);
+			if (!runl->runq[runl->runq_nr])
+				return -ENOMEM;
+
+			runl->runq_nr++;
+		}
+	}
+
+	ret = nvkm_inth_add(&device->vfn->intr, vector & 0x00000fff, NVKM_INTR_PRIO_NORMAL,
+			    &fifo->engine.subdev, ga100_runl_intr, &runl->inth);
+	if (ret)
+		return ret;
+
+	runl->chan = chaddr;
+	runl->doorbell = dbcfg >> 16;
+	return 0;
+}
+
+static irqreturn_t
+ga100_fifo_nonstall_intr(struct nvkm_inth *inth)
+{
+	struct nvkm_fifo *fifo = container_of(inth, typeof(*fifo), nonstall.intr);
+
+	nvkm_event_ntfy(&fifo->nonstall.event, 0, NVKM_FIFO_NONSTALL_EVENT);
+	return IRQ_HANDLED;
+}
+
+static void
+ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index)
+{
+	struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
+
+	nvkm_inth_block(&fifo->nonstall.intr);
+}
+
+static void
+ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index)
+{
+	struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
+
+	nvkm_inth_allow(&fifo->nonstall.intr);
+}
+
+const struct nvkm_event_func
+ga100_fifo_nonstall = {
+	.init = ga100_fifo_nonstall_allow,
+	.fini = ga100_fifo_nonstall_block,
+};
+
+int
+ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo)
+{
+	return nvkm_inth_add(&fifo->engine.subdev.device->vfn->intr, GA100_FIFO_NONSTALL_VECTOR,
+			     NVKM_INTR_PRIO_NORMAL, &fifo->engine.subdev, ga100_fifo_nonstall_intr,
+			     &fifo->nonstall.intr);
+}
+
+int
+ga100_fifo_runl_ctor(struct nvkm_fifo *fifo)
+{
+	struct nvkm_device *device = fifo->engine.subdev.device;
+	struct nvkm_top_device *tdev;
+	struct nvkm_runl *runl;
+	int id = 0, ret;
+
+	nvkm_list_foreach(tdev, &device->top->device, head, tdev->runlist >= 0) {
+		runl = nvkm_runl_get(fifo, -1, tdev->runlist);
+		if (!runl) {
+			ret = ga100_runl_new(fifo, id++, tdev->runlist, &runl);
+			if (ret)
+				return ret;
+		}
+
+		if (tdev->engine < 0)
+			continue;
+
+		nvkm_runl_add(runl, tdev->engine, (tdev->type == NVKM_ENGINE_CE) ?
+			      fifo->func->engn_ce : fifo->func->engn, tdev->type, tdev->inst);
+	}
+
+	return 0;
+}
+
+static const struct nvkm_fifo_func
+ga100_fifo = {
+	.runl_ctor = ga100_fifo_runl_ctor,
+	.mmu_fault = &tu102_fifo_mmu_fault,
+	.nonstall_ctor = ga100_fifo_nonstall_ctor,
+	.nonstall = &ga100_fifo_nonstall,
+	.runl = &ga100_runl,
+	.runq = &ga100_runq,
+	.engn = &ga100_engn,
+	.engn_ce = &ga100_engn_ce,
+	.cgrp = {{ 0, 0, KEPLER_CHANNEL_GROUP_A  }, &ga100_cgrp, .force = true },
+	.chan = {{ 0, 0, AMPERE_CHANNEL_GPFIFO_A }, &ga100_chan },
+};
+
+int
+ga100_fifo_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+	       struct nvkm_fifo **pfifo)
+{
+	return nvkm_fifo_new_(&ga100_fifo, device, type, inst, pfifo);
+}