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, 537 insertions, 0 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
new file mode 100644
index 000000000..15d04a0ec
--- /dev/null
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -0,0 +1,537 @@
+/*
+ * Copyright 2015 Advanced Micro Devices, 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 <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/completion.h>
+
+#include <drm/drm_print.h>
+#include <drm/gpu_scheduler.h>
+
+#include "gpu_scheduler_trace.h"
+
+#define to_drm_sched_job(sched_job)		\
+		container_of((sched_job), struct drm_sched_job, queue_node)
+
+/**
+ * drm_sched_entity_init - Init a context entity used by scheduler when
+ * submit to HW ring.
+ *
+ * @entity: scheduler entity to init
+ * @priority: priority of the entity
+ * @sched_list: the list of drm scheds on which jobs from this
+ *           entity can be submitted
+ * @num_sched_list: number of drm sched in sched_list
+ * @guilty: atomic_t set to 1 when a job on this queue
+ *          is found to be guilty causing a timeout
+ *
+ * Note that the &sched_list must have at least one element to schedule the entity.
+ *
+ * For changing @priority later on at runtime see
+ * drm_sched_entity_set_priority(). For changing the set of schedulers
+ * @sched_list at runtime see drm_sched_entity_modify_sched().
+ *
+ * An entity is cleaned up by callind drm_sched_entity_fini(). See also
+ * drm_sched_entity_destroy().
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int drm_sched_entity_init(struct drm_sched_entity *entity,
+			  enum drm_sched_priority priority,
+			  struct drm_gpu_scheduler **sched_list,
+			  unsigned int num_sched_list,
+			  atomic_t *guilty)
+{
+	if (!(entity && sched_list && (num_sched_list == 0 || sched_list[0])))
+		return -EINVAL;
+
+	memset(entity, 0, sizeof(struct drm_sched_entity));
+	INIT_LIST_HEAD(&entity->list);
+	entity->rq = NULL;
+	entity->guilty = guilty;
+	entity->num_sched_list = num_sched_list;
+	entity->priority = priority;
+	entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
+	entity->last_scheduled = NULL;
+	RB_CLEAR_NODE(&entity->rb_tree_node);
+
+	if(num_sched_list)
+		entity->rq = &sched_list[0]->sched_rq[entity->priority];
+
+	init_completion(&entity->entity_idle);
+
+	/* We start in an idle state. */
+	complete_all(&entity->entity_idle);
+
+	spin_lock_init(&entity->rq_lock);
+	spsc_queue_init(&entity->job_queue);
+
+	atomic_set(&entity->fence_seq, 0);
+	entity->fence_context = dma_fence_context_alloc(2);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_sched_entity_init);
+
+/**
+ * drm_sched_entity_modify_sched - Modify sched of an entity
+ * @entity: scheduler entity to init
+ * @sched_list: the list of new drm scheds which will replace
+ *		 existing entity->sched_list
+ * @num_sched_list: number of drm sched in sched_list
+ *
+ * Note that this must be called under the same common lock for @entity as
+ * drm_sched_job_arm() and drm_sched_entity_push_job(), or the driver needs to
+ * guarantee through some other means that this is never called while new jobs
+ * can be pushed to @entity.
+ */
+void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
+				    struct drm_gpu_scheduler **sched_list,
+				    unsigned int num_sched_list)
+{
+	WARN_ON(!num_sched_list || !sched_list);
+
+	entity->sched_list = sched_list;
+	entity->num_sched_list = num_sched_list;
+}
+EXPORT_SYMBOL(drm_sched_entity_modify_sched);
+
+static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
+{
+	rmb(); /* for list_empty to work without lock */
+
+	if (list_empty(&entity->list) ||
+	    spsc_queue_count(&entity->job_queue) == 0 ||
+	    entity->stopped)
+		return true;
+
+	return false;
+}
+
+/* Return true if entity could provide a job. */
+bool drm_sched_entity_is_ready(struct drm_sched_entity *entity)
+{
+	if (spsc_queue_peek(&entity->job_queue) == NULL)
+		return false;
+
+	if (READ_ONCE(entity->dependency))
+		return false;
+
+	return true;
+}
+
+static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
+{
+	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
+
+	drm_sched_fence_finished(job->s_fence);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
+/* Signal the scheduler finished fence when the entity in question is killed. */
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
+						 finish_cb);
+	int r;
+
+	dma_fence_put(f);
+
+	/* Wait for all dependencies to avoid data corruptions */
+	while (!xa_empty(&job->dependencies)) {
+		f = xa_erase(&job->dependencies, job->last_dependency++);
+		r = dma_fence_add_callback(f, &job->finish_cb,
+					   drm_sched_entity_kill_jobs_cb);
+		if (!r)
+			return;
+
+		dma_fence_put(f);
+	}
+
+	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
+	schedule_work(&job->work);
+}
+
+/* Remove the entity from the scheduler and kill all pending jobs */
+static void drm_sched_entity_kill(struct drm_sched_entity *entity)
+{
+	struct drm_sched_job *job;
+	struct dma_fence *prev;
+
+	if (!entity->rq)
+		return;
+
+	spin_lock(&entity->rq_lock);
+	entity->stopped = true;
+	drm_sched_rq_remove_entity(entity->rq, entity);
+	spin_unlock(&entity->rq_lock);
+
+	/* Make sure this entity is not used by the scheduler at the moment */
+	wait_for_completion(&entity->entity_idle);
+
+	prev = dma_fence_get(entity->last_scheduled);
+	while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) {
+		struct drm_sched_fence *s_fence = job->s_fence;
+
+		dma_fence_set_error(&s_fence->finished, -ESRCH);
+
+		dma_fence_get(&s_fence->finished);
+		if (!prev || dma_fence_add_callback(prev, &job->finish_cb,
+					   drm_sched_entity_kill_jobs_cb))
+			drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+
+		prev = &s_fence->finished;
+	}
+	dma_fence_put(prev);
+}
+
+/**
+ * drm_sched_entity_flush - Flush a context entity
+ *
+ * @entity: scheduler entity
+ * @timeout: time to wait in for Q to become empty in jiffies.
+ *
+ * Splitting drm_sched_entity_fini() into two functions, The first one does the
+ * waiting, removes the entity from the runqueue and returns an error when the
+ * process was killed.
+ *
+ * Returns the remaining time in jiffies left from the input timeout
+ */
+long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
+{
+	struct drm_gpu_scheduler *sched;
+	struct task_struct *last_user;
+	long ret = timeout;
+
+	if (!entity->rq)
+		return 0;
+
+	sched = entity->rq->sched;
+	/**
+	 * The client will not queue more IBs during this fini, consume existing
+	 * queued IBs or discard them on SIGKILL
+	 */
+	if (current->flags & PF_EXITING) {
+		if (timeout)
+			ret = wait_event_timeout(
+					sched->job_scheduled,
+					drm_sched_entity_is_idle(entity),
+					timeout);
+	} else {
+		wait_event_killable(sched->job_scheduled,
+				    drm_sched_entity_is_idle(entity));
+	}
+
+	/* For killed process disable any more IBs enqueue right now */
+	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
+	if ((!last_user || last_user == current->group_leader) &&
+	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
+		drm_sched_entity_kill(entity);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_entity_flush);
+
+/**
+ * drm_sched_entity_fini - Destroy a context entity
+ *
+ * @entity: scheduler entity
+ *
+ * Cleanups up @entity which has been initialized by drm_sched_entity_init().
+ *
+ * If there are potentially job still in flight or getting newly queued
+ * drm_sched_entity_flush() must be called first. This function then goes over
+ * the entity and signals all jobs with an error code if the process was killed.
+ */
+void drm_sched_entity_fini(struct drm_sched_entity *entity)
+{
+	/*
+	 * If consumption of existing IBs wasn't completed. Forcefully remove
+	 * them here. Also makes sure that the scheduler won't touch this entity
+	 * any more.
+	 */
+	drm_sched_entity_kill(entity);
+
+	if (entity->dependency) {
+		dma_fence_remove_callback(entity->dependency, &entity->cb);
+		dma_fence_put(entity->dependency);
+		entity->dependency = NULL;
+	}
+
+	dma_fence_put(entity->last_scheduled);
+	entity->last_scheduled = NULL;
+}
+EXPORT_SYMBOL(drm_sched_entity_fini);
+
+/**
+ * drm_sched_entity_destroy - Destroy a context entity
+ * @entity: scheduler entity
+ *
+ * Calls drm_sched_entity_flush() and drm_sched_entity_fini() as a
+ * convenience wrapper.
+ */
+void drm_sched_entity_destroy(struct drm_sched_entity *entity)
+{
+	drm_sched_entity_flush(entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
+	drm_sched_entity_fini(entity);
+}
+EXPORT_SYMBOL(drm_sched_entity_destroy);
+
+/* drm_sched_entity_clear_dep - callback to clear the entities dependency */
+static void drm_sched_entity_clear_dep(struct dma_fence *f,
+				       struct dma_fence_cb *cb)
+{
+	struct drm_sched_entity *entity =
+		container_of(cb, struct drm_sched_entity, cb);
+
+	entity->dependency = NULL;
+	dma_fence_put(f);
+}
+
+/*
+ * drm_sched_entity_clear_dep - callback to clear the entities dependency and
+ * wake up scheduler
+ */
+static void drm_sched_entity_wakeup(struct dma_fence *f,
+				    struct dma_fence_cb *cb)
+{
+	struct drm_sched_entity *entity =
+		container_of(cb, struct drm_sched_entity, cb);
+
+	drm_sched_entity_clear_dep(f, cb);
+	drm_sched_wakeup(entity->rq->sched);
+}
+
+/**
+ * drm_sched_entity_set_priority - Sets priority of the entity
+ *
+ * @entity: scheduler entity
+ * @priority: scheduler priority
+ *
+ * Update the priority of runqueus used for the entity.
+ */
+void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
+				   enum drm_sched_priority priority)
+{
+	spin_lock(&entity->rq_lock);
+	entity->priority = priority;
+	spin_unlock(&entity->rq_lock);
+}
+EXPORT_SYMBOL(drm_sched_entity_set_priority);
+
+/*
+ * Add a callback to the current dependency of the entity to wake up the
+ * scheduler when the entity becomes available.
+ */
+static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
+{
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
+	struct dma_fence *fence = entity->dependency;
+	struct drm_sched_fence *s_fence;
+
+	if (fence->context == entity->fence_context ||
+	    fence->context == entity->fence_context + 1) {
+		/*
+		 * Fence is a scheduled/finished fence from a job
+		 * which belongs to the same entity, we can ignore
+		 * fences from ourself
+		 */
+		dma_fence_put(entity->dependency);
+		return false;
+	}
+
+	s_fence = to_drm_sched_fence(fence);
+	if (s_fence && s_fence->sched == sched &&
+	    !test_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &fence->flags)) {
+
+		/*
+		 * Fence is from the same scheduler, only need to wait for
+		 * it to be scheduled
+		 */
+		fence = dma_fence_get(&s_fence->scheduled);
+		dma_fence_put(entity->dependency);
+		entity->dependency = fence;
+		if (!dma_fence_add_callback(fence, &entity->cb,
+					    drm_sched_entity_clear_dep))
+			return true;
+
+		/* Ignore it when it is already scheduled */
+		dma_fence_put(fence);
+		return false;
+	}
+
+	if (!dma_fence_add_callback(entity->dependency, &entity->cb,
+				    drm_sched_entity_wakeup))
+		return true;
+
+	dma_fence_put(entity->dependency);
+	return false;
+}
+
+static struct dma_fence *
+drm_sched_job_dependency(struct drm_sched_job *job,
+			 struct drm_sched_entity *entity)
+{
+	if (!xa_empty(&job->dependencies))
+		return xa_erase(&job->dependencies, job->last_dependency++);
+
+	if (job->sched->ops->prepare_job)
+		return job->sched->ops->prepare_job(job, entity);
+
+	return NULL;
+}
+
+struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
+{
+	struct drm_sched_job *sched_job;
+
+	sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
+	if (!sched_job)
+		return NULL;
+
+	while ((entity->dependency =
+			drm_sched_job_dependency(sched_job, entity))) {
+		trace_drm_sched_job_wait_dep(sched_job, entity->dependency);
+
+		if (drm_sched_entity_add_dependency_cb(entity))
+			return NULL;
+	}
+
+	/* skip jobs from entity that marked guilty */
+	if (entity->guilty && atomic_read(entity->guilty))
+		dma_fence_set_error(&sched_job->s_fence->finished, -ECANCELED);
+
+	dma_fence_put(entity->last_scheduled);
+
+	entity->last_scheduled = dma_fence_get(&sched_job->s_fence->finished);
+
+	/*
+	 * If the queue is empty we allow drm_sched_entity_select_rq() to
+	 * locklessly access ->last_scheduled. This only works if we set the
+	 * pointer before we dequeue and if we a write barrier here.
+	 */
+	smp_wmb();
+
+	spsc_queue_pop(&entity->job_queue);
+
+	/*
+	 * Update the entity's location in the min heap according to
+	 * the timestamp of the next job, if any.
+	 */
+	if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) {
+		struct drm_sched_job *next;
+
+		next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
+		if (next)
+			drm_sched_rq_update_fifo(entity, next->submit_ts);
+	}
+
+	return sched_job;
+}
+
+void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
+{
+	struct dma_fence *fence;
+	struct drm_gpu_scheduler *sched;
+	struct drm_sched_rq *rq;
+
+	/* single possible engine and already selected */
+	if (!entity->sched_list)
+		return;
+
+	/* queue non-empty, stay on the same engine */
+	if (spsc_queue_count(&entity->job_queue))
+		return;
+
+	/*
+	 * Only when the queue is empty are we guaranteed that the scheduler
+	 * thread cannot change ->last_scheduled. To enforce ordering we need
+	 * a read barrier here. See drm_sched_entity_pop_job() for the other
+	 * side.
+	 */
+	smp_rmb();
+
+	fence = entity->last_scheduled;
+
+	/* stay on the same engine if the previous job hasn't finished */
+	if (fence && !dma_fence_is_signaled(fence))
+		return;
+
+	spin_lock(&entity->rq_lock);
+	sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list);
+	rq = sched ? &sched->sched_rq[entity->priority] : NULL;
+	if (rq != entity->rq) {
+		drm_sched_rq_remove_entity(entity->rq, entity);
+		entity->rq = rq;
+	}
+	spin_unlock(&entity->rq_lock);
+
+	if (entity->num_sched_list == 1)
+		entity->sched_list = NULL;
+}
+
+/**
+ * drm_sched_entity_push_job - Submit a job to the entity's job queue
+ * @sched_job: job to submit
+ *
+ * Note: To guarantee that the order of insertion to queue matches the job's
+ * fence sequence number this function should be called with drm_sched_job_arm()
+ * under common lock for the struct drm_sched_entity that was set up for
+ * @sched_job in drm_sched_job_init().
+ *
+ * Returns 0 for success, negative error code otherwise.
+ */
+void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
+{
+	struct drm_sched_entity *entity = sched_job->entity;
+	bool first;
+
+	trace_drm_sched_job(sched_job, entity);
+	atomic_inc(entity->rq->sched->score);
+	WRITE_ONCE(entity->last_user, current->group_leader);
+	first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
+	sched_job->submit_ts = ktime_get();
+
+	/* first job wakes up scheduler */
+	if (first) {
+		/* Add the entity to the run queue */
+		spin_lock(&entity->rq_lock);
+		if (entity->stopped) {
+			spin_unlock(&entity->rq_lock);
+
+			DRM_ERROR("Trying to push to a killed entity\n");
+			return;
+		}
+
+		drm_sched_rq_add_entity(entity->rq, entity);
+		spin_unlock(&entity->rq_lock);
+
+		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
+			drm_sched_rq_update_fifo(entity, sched_job->submit_ts);
+
+		drm_sched_wakeup(entity->rq->sched);
+	}
+}
+EXPORT_SYMBOL(drm_sched_entity_push_job);