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, 522 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
new file mode 100644
index 000000000..ee5e9d40c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -0,0 +1,522 @@
+/*
+ * Copyright (C) 2007 Ben Skeggs.
+ * All Rights Reserved.
+ *
+ * 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 (including the
+ * next paragraph) 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 OWNER(S) AND/OR ITS SUPPLIERS 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 <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/sched/signal.h>
+#include <trace/events/dma_fence.h>
+
+#include <nvif/if0020.h>
+
+#include "nouveau_drv.h"
+#include "nouveau_dma.h"
+#include "nouveau_fence.h"
+
+static const struct dma_fence_ops nouveau_fence_ops_uevent;
+static const struct dma_fence_ops nouveau_fence_ops_legacy;
+
+static inline struct nouveau_fence *
+from_fence(struct dma_fence *fence)
+{
+	return container_of(fence, struct nouveau_fence, base);
+}
+
+static inline struct nouveau_fence_chan *
+nouveau_fctx(struct nouveau_fence *fence)
+{
+	return container_of(fence->base.lock, struct nouveau_fence_chan, lock);
+}
+
+static int
+nouveau_fence_signal(struct nouveau_fence *fence)
+{
+	int drop = 0;
+
+	dma_fence_signal_locked(&fence->base);
+	list_del(&fence->head);
+	rcu_assign_pointer(fence->channel, NULL);
+
+	if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) {
+		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+
+		if (!--fctx->notify_ref)
+			drop = 1;
+	}
+
+	dma_fence_put(&fence->base);
+	return drop;
+}
+
+static struct nouveau_fence *
+nouveau_local_fence(struct dma_fence *fence, struct nouveau_drm *drm)
+{
+	if (fence->ops != &nouveau_fence_ops_legacy &&
+	    fence->ops != &nouveau_fence_ops_uevent)
+		return NULL;
+
+	return from_fence(fence);
+}
+
+void
+nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
+{
+	struct nouveau_fence *fence;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fctx->lock, flags);
+	while (!list_empty(&fctx->pending)) {
+		fence = list_entry(fctx->pending.next, typeof(*fence), head);
+
+		if (error)
+			dma_fence_set_error(&fence->base, error);
+
+		if (nouveau_fence_signal(fence))
+			nvif_event_block(&fctx->event);
+	}
+	spin_unlock_irqrestore(&fctx->lock, flags);
+}
+
+void
+nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
+{
+	nouveau_fence_context_kill(fctx, 0);
+	nvif_event_dtor(&fctx->event);
+	fctx->dead = 1;
+
+	/*
+	 * Ensure that all accesses to fence->channel complete before freeing
+	 * the channel.
+	 */
+	synchronize_rcu();
+}
+
+static void
+nouveau_fence_context_put(struct kref *fence_ref)
+{
+	kfree(container_of(fence_ref, struct nouveau_fence_chan, fence_ref));
+}
+
+void
+nouveau_fence_context_free(struct nouveau_fence_chan *fctx)
+{
+	kref_put(&fctx->fence_ref, nouveau_fence_context_put);
+}
+
+static int
+nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
+{
+	struct nouveau_fence *fence;
+	int drop = 0;
+	u32 seq = fctx->read(chan);
+
+	while (!list_empty(&fctx->pending)) {
+		fence = list_entry(fctx->pending.next, typeof(*fence), head);
+
+		if ((int)(seq - fence->base.seqno) < 0)
+			break;
+
+		drop |= nouveau_fence_signal(fence);
+	}
+
+	return drop;
+}
+
+static int
+nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+{
+	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	unsigned long flags;
+	int ret = NVIF_EVENT_KEEP;
+
+	spin_lock_irqsave(&fctx->lock, flags);
+	if (!list_empty(&fctx->pending)) {
+		struct nouveau_fence *fence;
+		struct nouveau_channel *chan;
+
+		fence = list_entry(fctx->pending.next, typeof(*fence), head);
+		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
+		if (nouveau_fence_update(chan, fctx))
+			ret = NVIF_EVENT_DROP;
+	}
+	spin_unlock_irqrestore(&fctx->lock, flags);
+
+	return ret;
+}
+
+void
+nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
+{
+	struct nouveau_fence_priv *priv = (void*)chan->drm->fence;
+	struct nouveau_cli *cli = (void *)chan->user.client;
+	struct {
+		struct nvif_event_v0 base;
+		struct nvif_chan_event_v0 host;
+	} args;
+	int ret;
+
+	INIT_LIST_HEAD(&fctx->flip);
+	INIT_LIST_HEAD(&fctx->pending);
+	spin_lock_init(&fctx->lock);
+	fctx->context = chan->drm->runl[chan->runlist].context_base + chan->chid;
+
+	if (chan == chan->drm->cechan)
+		strcpy(fctx->name, "copy engine channel");
+	else if (chan == chan->drm->channel)
+		strcpy(fctx->name, "generic kernel channel");
+	else
+		strcpy(fctx->name, nvxx_client(&cli->base)->name);
+
+	kref_init(&fctx->fence_ref);
+	if (!priv->uevent)
+		return;
+
+	args.host.version = 0;
+	args.host.type = NVIF_CHAN_EVENT_V0_NON_STALL_INTR;
+
+	ret = nvif_event_ctor(&chan->user, "fenceNonStallIntr", (chan->runlist << 16) | chan->chid,
+			      nouveau_fence_wait_uevent_handler, false,
+			      &args.base, sizeof(args), &fctx->event);
+
+	WARN_ON(ret);
+}
+
+int
+nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan)
+{
+	struct nouveau_fence_chan *fctx = chan->fence;
+	struct nouveau_fence_priv *priv = (void*)chan->drm->fence;
+	int ret;
+
+	fence->channel  = chan;
+	fence->timeout  = jiffies + (15 * HZ);
+
+	if (priv->uevent)
+		dma_fence_init(&fence->base, &nouveau_fence_ops_uevent,
+			       &fctx->lock, fctx->context, ++fctx->sequence);
+	else
+		dma_fence_init(&fence->base, &nouveau_fence_ops_legacy,
+			       &fctx->lock, fctx->context, ++fctx->sequence);
+	kref_get(&fctx->fence_ref);
+
+	ret = fctx->emit(fence);
+	if (!ret) {
+		dma_fence_get(&fence->base);
+		spin_lock_irq(&fctx->lock);
+
+		if (nouveau_fence_update(chan, fctx))
+			nvif_event_block(&fctx->event);
+
+		list_add_tail(&fence->head, &fctx->pending);
+		spin_unlock_irq(&fctx->lock);
+	}
+
+	return ret;
+}
+
+bool
+nouveau_fence_done(struct nouveau_fence *fence)
+{
+	if (fence->base.ops == &nouveau_fence_ops_legacy ||
+	    fence->base.ops == &nouveau_fence_ops_uevent) {
+		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+		struct nouveau_channel *chan;
+		unsigned long flags;
+
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->base.flags))
+			return true;
+
+		spin_lock_irqsave(&fctx->lock, flags);
+		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
+		if (chan && nouveau_fence_update(chan, fctx))
+			nvif_event_block(&fctx->event);
+		spin_unlock_irqrestore(&fctx->lock, flags);
+	}
+	return dma_fence_is_signaled(&fence->base);
+}
+
+static long
+nouveau_fence_wait_legacy(struct dma_fence *f, bool intr, long wait)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	unsigned long sleep_time = NSEC_PER_MSEC / 1000;
+	unsigned long t = jiffies, timeout = t + wait;
+
+	while (!nouveau_fence_done(fence)) {
+		ktime_t kt;
+
+		t = jiffies;
+
+		if (wait != MAX_SCHEDULE_TIMEOUT && time_after_eq(t, timeout)) {
+			__set_current_state(TASK_RUNNING);
+			return 0;
+		}
+
+		__set_current_state(intr ? TASK_INTERRUPTIBLE :
+					   TASK_UNINTERRUPTIBLE);
+
+		kt = sleep_time;
+		schedule_hrtimeout(&kt, HRTIMER_MODE_REL);
+		sleep_time *= 2;
+		if (sleep_time > NSEC_PER_MSEC)
+			sleep_time = NSEC_PER_MSEC;
+
+		if (intr && signal_pending(current))
+			return -ERESTARTSYS;
+	}
+
+	__set_current_state(TASK_RUNNING);
+
+	return timeout - t;
+}
+
+static int
+nouveau_fence_wait_busy(struct nouveau_fence *fence, bool intr)
+{
+	int ret = 0;
+
+	while (!nouveau_fence_done(fence)) {
+		if (time_after_eq(jiffies, fence->timeout)) {
+			ret = -EBUSY;
+			break;
+		}
+
+		__set_current_state(intr ?
+				    TASK_INTERRUPTIBLE :
+				    TASK_UNINTERRUPTIBLE);
+
+		if (intr && signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+	}
+
+	__set_current_state(TASK_RUNNING);
+	return ret;
+}
+
+int
+nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr)
+{
+	long ret;
+
+	if (!lazy)
+		return nouveau_fence_wait_busy(fence, intr);
+
+	ret = dma_fence_wait_timeout(&fence->base, intr, 15 * HZ);
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+	else
+		return 0;
+}
+
+int
+nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan,
+		   bool exclusive, bool intr)
+{
+	struct nouveau_fence_chan *fctx = chan->fence;
+	struct dma_resv *resv = nvbo->bo.base.resv;
+	int i, ret;
+
+	ret = dma_resv_reserve_fences(resv, 1);
+	if (ret)
+		return ret;
+
+	/* Waiting for the writes first causes performance regressions
+	 * under some circumstances. So manually wait for the reads first.
+	 */
+	for (i = 0; i < 2; ++i) {
+		struct dma_resv_iter cursor;
+		struct dma_fence *fence;
+
+		dma_resv_for_each_fence(&cursor, resv,
+					dma_resv_usage_rw(exclusive),
+					fence) {
+			enum dma_resv_usage usage;
+			struct nouveau_fence *f;
+
+			usage = dma_resv_iter_usage(&cursor);
+			if (i == 0 && usage == DMA_RESV_USAGE_WRITE)
+				continue;
+
+			f = nouveau_local_fence(fence, chan->drm);
+			if (f) {
+				struct nouveau_channel *prev;
+				bool must_wait = true;
+
+				rcu_read_lock();
+				prev = rcu_dereference(f->channel);
+				if (prev && (prev == chan ||
+					     fctx->sync(f, prev, chan) == 0))
+					must_wait = false;
+				rcu_read_unlock();
+				if (!must_wait)
+					continue;
+			}
+
+			ret = dma_fence_wait(fence, intr);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+void
+nouveau_fence_unref(struct nouveau_fence **pfence)
+{
+	if (*pfence)
+		dma_fence_put(&(*pfence)->base);
+	*pfence = NULL;
+}
+
+int
+nouveau_fence_new(struct nouveau_channel *chan, bool sysmem,
+		  struct nouveau_fence **pfence)
+{
+	struct nouveau_fence *fence;
+	int ret = 0;
+
+	if (unlikely(!chan->fence))
+		return -ENODEV;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return -ENOMEM;
+
+	ret = nouveau_fence_emit(fence, chan);
+	if (ret)
+		nouveau_fence_unref(&fence);
+
+	*pfence = fence;
+	return ret;
+}
+
+static const char *nouveau_fence_get_get_driver_name(struct dma_fence *fence)
+{
+	return "nouveau";
+}
+
+static const char *nouveau_fence_get_timeline_name(struct dma_fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+
+	return !fctx->dead ? fctx->name : "dead channel";
+}
+
+/*
+ * In an ideal world, read would not assume the channel context is still alive.
+ * This function may be called from another device, running into free memory as a
+ * result. The drm node should still be there, so we can derive the index from
+ * the fence context.
+ */
+static bool nouveau_fence_is_signaled(struct dma_fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+	struct nouveau_channel *chan;
+	bool ret = false;
+
+	rcu_read_lock();
+	chan = rcu_dereference(fence->channel);
+	if (chan)
+		ret = (int)(fctx->read(chan) - fence->base.seqno) >= 0;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static bool nouveau_fence_no_signaling(struct dma_fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+
+	/*
+	 * caller should have a reference on the fence,
+	 * else fence could get freed here
+	 */
+	WARN_ON(kref_read(&fence->base.refcount) <= 1);
+
+	/*
+	 * This needs uevents to work correctly, but dma_fence_add_callback relies on
+	 * being able to enable signaling. It will still get signaled eventually,
+	 * just not right away.
+	 */
+	if (nouveau_fence_is_signaled(f)) {
+		list_del(&fence->head);
+
+		dma_fence_put(&fence->base);
+		return false;
+	}
+
+	return true;
+}
+
+static void nouveau_fence_release(struct dma_fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+
+	kref_put(&fctx->fence_ref, nouveau_fence_context_put);
+	dma_fence_free(&fence->base);
+}
+
+static const struct dma_fence_ops nouveau_fence_ops_legacy = {
+	.get_driver_name = nouveau_fence_get_get_driver_name,
+	.get_timeline_name = nouveau_fence_get_timeline_name,
+	.enable_signaling = nouveau_fence_no_signaling,
+	.signaled = nouveau_fence_is_signaled,
+	.wait = nouveau_fence_wait_legacy,
+	.release = nouveau_fence_release
+};
+
+static bool nouveau_fence_enable_signaling(struct dma_fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+	bool ret;
+
+	if (!fctx->notify_ref++)
+		nvif_event_allow(&fctx->event);
+
+	ret = nouveau_fence_no_signaling(f);
+	if (ret)
+		set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags);
+	else if (!--fctx->notify_ref)
+		nvif_event_block(&fctx->event);
+
+	return ret;
+}
+
+static const struct dma_fence_ops nouveau_fence_ops_uevent = {
+	.get_driver_name = nouveau_fence_get_get_driver_name,
+	.get_timeline_name = nouveau_fence_get_timeline_name,
+	.enable_signaling = nouveau_fence_enable_signaling,
+	.signaled = nouveau_fence_is_signaled,
+	.release = nouveau_fence_release
+};