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, 480 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
new file mode 100644
index 000000000..c077fb467
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -0,0 +1,480 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. 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 AUTHORS OR COPYRIGHT HOLDERS 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.
+ *
+ * Authors:
+ *    Anhua Xu
+ *    Kevin Tian <kevin.tian@intel.com>
+ *
+ * Contributors:
+ *    Min He <min.he@intel.com>
+ *    Bing Niu <bing.niu@intel.com>
+ *    Zhi Wang <zhi.a.wang@intel.com>
+ *
+ */
+
+#include "i915_drv.h"
+#include "gvt.h"
+
+static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu)
+{
+	enum intel_engine_id i;
+	struct intel_engine_cs *engine;
+
+	for_each_engine(engine, vgpu->gvt->gt, i) {
+		if (!list_empty(workload_q_head(vgpu, engine)))
+			return true;
+	}
+
+	return false;
+}
+
+/* We give 2 seconds higher prio for vGPU during start */
+#define GVT_SCHED_VGPU_PRI_TIME  2
+
+struct vgpu_sched_data {
+	struct list_head lru_list;
+	struct intel_vgpu *vgpu;
+	bool active;
+	bool pri_sched;
+	ktime_t pri_time;
+	ktime_t sched_in_time;
+	ktime_t sched_time;
+	ktime_t left_ts;
+	ktime_t allocated_ts;
+
+	struct vgpu_sched_ctl sched_ctl;
+};
+
+struct gvt_sched_data {
+	struct intel_gvt *gvt;
+	struct hrtimer timer;
+	unsigned long period;
+	struct list_head lru_runq_head;
+	ktime_t expire_time;
+};
+
+static void vgpu_update_timeslice(struct intel_vgpu *vgpu, ktime_t cur_time)
+{
+	ktime_t delta_ts;
+	struct vgpu_sched_data *vgpu_data;
+
+	if (!vgpu || vgpu == vgpu->gvt->idle_vgpu)
+		return;
+
+	vgpu_data = vgpu->sched_data;
+	delta_ts = ktime_sub(cur_time, vgpu_data->sched_in_time);
+	vgpu_data->sched_time = ktime_add(vgpu_data->sched_time, delta_ts);
+	vgpu_data->left_ts = ktime_sub(vgpu_data->left_ts, delta_ts);
+	vgpu_data->sched_in_time = cur_time;
+}
+
+#define GVT_TS_BALANCE_PERIOD_MS 100
+#define GVT_TS_BALANCE_STAGE_NUM 10
+
+static void gvt_balance_timeslice(struct gvt_sched_data *sched_data)
+{
+	struct vgpu_sched_data *vgpu_data;
+	struct list_head *pos;
+	static u64 stage_check;
+	int stage = stage_check++ % GVT_TS_BALANCE_STAGE_NUM;
+
+	/* The timeslice accumulation reset at stage 0, which is
+	 * allocated again without adding previous debt.
+	 */
+	if (stage == 0) {
+		int total_weight = 0;
+		ktime_t fair_timeslice;
+
+		list_for_each(pos, &sched_data->lru_runq_head) {
+			vgpu_data = container_of(pos, struct vgpu_sched_data, lru_list);
+			total_weight += vgpu_data->sched_ctl.weight;
+		}
+
+		list_for_each(pos, &sched_data->lru_runq_head) {
+			vgpu_data = container_of(pos, struct vgpu_sched_data, lru_list);
+			fair_timeslice = ktime_divns(ms_to_ktime(GVT_TS_BALANCE_PERIOD_MS),
+						     total_weight) * vgpu_data->sched_ctl.weight;
+
+			vgpu_data->allocated_ts = fair_timeslice;
+			vgpu_data->left_ts = vgpu_data->allocated_ts;
+		}
+	} else {
+		list_for_each(pos, &sched_data->lru_runq_head) {
+			vgpu_data = container_of(pos, struct vgpu_sched_data, lru_list);
+
+			/* timeslice for next 100ms should add the left/debt
+			 * slice of previous stages.
+			 */
+			vgpu_data->left_ts += vgpu_data->allocated_ts;
+		}
+	}
+}
+
+static void try_to_schedule_next_vgpu(struct intel_gvt *gvt)
+{
+	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
+	enum intel_engine_id i;
+	struct intel_engine_cs *engine;
+	struct vgpu_sched_data *vgpu_data;
+	ktime_t cur_time;
+
+	/* no need to schedule if next_vgpu is the same with current_vgpu,
+	 * let scheduler chose next_vgpu again by setting it to NULL.
+	 */
+	if (scheduler->next_vgpu == scheduler->current_vgpu) {
+		scheduler->next_vgpu = NULL;
+		return;
+	}
+
+	/*
+	 * after the flag is set, workload dispatch thread will
+	 * stop dispatching workload for current vgpu
+	 */
+	scheduler->need_reschedule = true;
+
+	/* still have uncompleted workload? */
+	for_each_engine(engine, gvt->gt, i) {
+		if (scheduler->current_workload[engine->id])
+			return;
+	}
+
+	cur_time = ktime_get();
+	vgpu_update_timeslice(scheduler->current_vgpu, cur_time);
+	vgpu_data = scheduler->next_vgpu->sched_data;
+	vgpu_data->sched_in_time = cur_time;
+
+	/* switch current vgpu */
+	scheduler->current_vgpu = scheduler->next_vgpu;
+	scheduler->next_vgpu = NULL;
+
+	scheduler->need_reschedule = false;
+
+	/* wake up workload dispatch thread */
+	for_each_engine(engine, gvt->gt, i)
+		wake_up(&scheduler->waitq[engine->id]);
+}
+
+static struct intel_vgpu *find_busy_vgpu(struct gvt_sched_data *sched_data)
+{
+	struct vgpu_sched_data *vgpu_data;
+	struct intel_vgpu *vgpu = NULL;
+	struct list_head *head = &sched_data->lru_runq_head;
+	struct list_head *pos;
+
+	/* search a vgpu with pending workload */
+	list_for_each(pos, head) {
+
+		vgpu_data = container_of(pos, struct vgpu_sched_data, lru_list);
+		if (!vgpu_has_pending_workload(vgpu_data->vgpu))
+			continue;
+
+		if (vgpu_data->pri_sched) {
+			if (ktime_before(ktime_get(), vgpu_data->pri_time)) {
+				vgpu = vgpu_data->vgpu;
+				break;
+			} else
+				vgpu_data->pri_sched = false;
+		}
+
+		/* Return the vGPU only if it has time slice left */
+		if (vgpu_data->left_ts > 0) {
+			vgpu = vgpu_data->vgpu;
+			break;
+		}
+	}
+
+	return vgpu;
+}
+
+/* in nanosecond */
+#define GVT_DEFAULT_TIME_SLICE 1000000
+
+static void tbs_sched_func(struct gvt_sched_data *sched_data)
+{
+	struct intel_gvt *gvt = sched_data->gvt;
+	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
+	struct vgpu_sched_data *vgpu_data;
+	struct intel_vgpu *vgpu = NULL;
+
+	/* no active vgpu or has already had a target */
+	if (list_empty(&sched_data->lru_runq_head) || scheduler->next_vgpu)
+		goto out;
+
+	vgpu = find_busy_vgpu(sched_data);
+	if (vgpu) {
+		scheduler->next_vgpu = vgpu;
+		vgpu_data = vgpu->sched_data;
+		if (!vgpu_data->pri_sched) {
+			/* Move the last used vGPU to the tail of lru_list */
+			list_del_init(&vgpu_data->lru_list);
+			list_add_tail(&vgpu_data->lru_list,
+				      &sched_data->lru_runq_head);
+		}
+	} else {
+		scheduler->next_vgpu = gvt->idle_vgpu;
+	}
+out:
+	if (scheduler->next_vgpu)
+		try_to_schedule_next_vgpu(gvt);
+}
+
+void intel_gvt_schedule(struct intel_gvt *gvt)
+{
+	struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
+	ktime_t cur_time;
+
+	mutex_lock(&gvt->sched_lock);
+	cur_time = ktime_get();
+
+	if (test_and_clear_bit(INTEL_GVT_REQUEST_SCHED,
+				(void *)&gvt->service_request)) {
+		if (cur_time >= sched_data->expire_time) {
+			gvt_balance_timeslice(sched_data);
+			sched_data->expire_time = ktime_add_ms(
+				cur_time, GVT_TS_BALANCE_PERIOD_MS);
+		}
+	}
+	clear_bit(INTEL_GVT_REQUEST_EVENT_SCHED, (void *)&gvt->service_request);
+
+	vgpu_update_timeslice(gvt->scheduler.current_vgpu, cur_time);
+	tbs_sched_func(sched_data);
+
+	mutex_unlock(&gvt->sched_lock);
+}
+
+static enum hrtimer_restart tbs_timer_fn(struct hrtimer *timer_data)
+{
+	struct gvt_sched_data *data;
+
+	data = container_of(timer_data, struct gvt_sched_data, timer);
+
+	intel_gvt_request_service(data->gvt, INTEL_GVT_REQUEST_SCHED);
+
+	hrtimer_add_expires_ns(&data->timer, data->period);
+
+	return HRTIMER_RESTART;
+}
+
+static int tbs_sched_init(struct intel_gvt *gvt)
+{
+	struct intel_gvt_workload_scheduler *scheduler =
+		&gvt->scheduler;
+
+	struct gvt_sched_data *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&data->lru_runq_head);
+	hrtimer_init(&data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	data->timer.function = tbs_timer_fn;
+	data->period = GVT_DEFAULT_TIME_SLICE;
+	data->gvt = gvt;
+
+	scheduler->sched_data = data;
+
+	return 0;
+}
+
+static void tbs_sched_clean(struct intel_gvt *gvt)
+{
+	struct intel_gvt_workload_scheduler *scheduler =
+		&gvt->scheduler;
+	struct gvt_sched_data *data = scheduler->sched_data;
+
+	hrtimer_cancel(&data->timer);
+
+	kfree(data);
+	scheduler->sched_data = NULL;
+}
+
+static int tbs_sched_init_vgpu(struct intel_vgpu *vgpu)
+{
+	struct vgpu_sched_data *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->sched_ctl.weight = vgpu->sched_ctl.weight;
+	data->vgpu = vgpu;
+	INIT_LIST_HEAD(&data->lru_list);
+
+	vgpu->sched_data = data;
+
+	return 0;
+}
+
+static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
+
+	kfree(vgpu->sched_data);
+	vgpu->sched_data = NULL;
+
+	/* this vgpu id has been removed */
+	if (idr_is_empty(&gvt->vgpu_idr))
+		hrtimer_cancel(&sched_data->timer);
+}
+
+static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
+{
+	struct gvt_sched_data *sched_data = vgpu->gvt->scheduler.sched_data;
+	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+	ktime_t now;
+
+	if (!list_empty(&vgpu_data->lru_list))
+		return;
+
+	now = ktime_get();
+	vgpu_data->pri_time = ktime_add(now,
+					ktime_set(GVT_SCHED_VGPU_PRI_TIME, 0));
+	vgpu_data->pri_sched = true;
+
+	list_add(&vgpu_data->lru_list, &sched_data->lru_runq_head);
+
+	if (!hrtimer_active(&sched_data->timer))
+		hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(),
+			sched_data->period), HRTIMER_MODE_ABS);
+	vgpu_data->active = true;
+}
+
+static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu)
+{
+	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+
+	list_del_init(&vgpu_data->lru_list);
+	vgpu_data->active = false;
+}
+
+static const struct intel_gvt_sched_policy_ops tbs_schedule_ops = {
+	.init = tbs_sched_init,
+	.clean = tbs_sched_clean,
+	.init_vgpu = tbs_sched_init_vgpu,
+	.clean_vgpu = tbs_sched_clean_vgpu,
+	.start_schedule = tbs_sched_start_schedule,
+	.stop_schedule = tbs_sched_stop_schedule,
+};
+
+int intel_gvt_init_sched_policy(struct intel_gvt *gvt)
+{
+	int ret;
+
+	mutex_lock(&gvt->sched_lock);
+	gvt->scheduler.sched_ops = &tbs_schedule_ops;
+	ret = gvt->scheduler.sched_ops->init(gvt);
+	mutex_unlock(&gvt->sched_lock);
+
+	return ret;
+}
+
+void intel_gvt_clean_sched_policy(struct intel_gvt *gvt)
+{
+	mutex_lock(&gvt->sched_lock);
+	gvt->scheduler.sched_ops->clean(gvt);
+	mutex_unlock(&gvt->sched_lock);
+}
+
+/* for per-vgpu scheduler policy, there are 2 per-vgpu data:
+ * sched_data, and sched_ctl. We see these 2 data as part of
+ * the global scheduler which are proteced by gvt->sched_lock.
+ * Caller should make their decision if the vgpu_lock should
+ * be hold outside.
+ */
+
+int intel_vgpu_init_sched_policy(struct intel_vgpu *vgpu)
+{
+	int ret;
+
+	mutex_lock(&vgpu->gvt->sched_lock);
+	ret = vgpu->gvt->scheduler.sched_ops->init_vgpu(vgpu);
+	mutex_unlock(&vgpu->gvt->sched_lock);
+
+	return ret;
+}
+
+void intel_vgpu_clean_sched_policy(struct intel_vgpu *vgpu)
+{
+	mutex_lock(&vgpu->gvt->sched_lock);
+	vgpu->gvt->scheduler.sched_ops->clean_vgpu(vgpu);
+	mutex_unlock(&vgpu->gvt->sched_lock);
+}
+
+void intel_vgpu_start_schedule(struct intel_vgpu *vgpu)
+{
+	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+
+	mutex_lock(&vgpu->gvt->sched_lock);
+	if (!vgpu_data->active) {
+		gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
+		vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
+	}
+	mutex_unlock(&vgpu->gvt->sched_lock);
+}
+
+void intel_gvt_kick_schedule(struct intel_gvt *gvt)
+{
+	mutex_lock(&gvt->sched_lock);
+	intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);
+	mutex_unlock(&gvt->sched_lock);
+}
+
+void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
+{
+	struct intel_gvt_workload_scheduler *scheduler =
+		&vgpu->gvt->scheduler;
+	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+	struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	if (!vgpu_data->active)
+		return;
+
+	gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
+
+	mutex_lock(&vgpu->gvt->sched_lock);
+	scheduler->sched_ops->stop_schedule(vgpu);
+
+	if (scheduler->next_vgpu == vgpu)
+		scheduler->next_vgpu = NULL;
+
+	if (scheduler->current_vgpu == vgpu) {
+		/* stop workload dispatching */
+		scheduler->need_reschedule = true;
+		scheduler->current_vgpu = NULL;
+	}
+
+	intel_runtime_pm_get(&dev_priv->runtime_pm);
+	spin_lock_bh(&scheduler->mmio_context_lock);
+	for_each_engine(engine, vgpu->gvt->gt, id) {
+		if (scheduler->engine_owner[engine->id] == vgpu) {
+			intel_gvt_switch_mmio(vgpu, NULL, engine);
+			scheduler->engine_owner[engine->id] = NULL;
+		}
+	}
+	spin_unlock_bh(&scheduler->mmio_context_lock);
+	intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm);
+	mutex_unlock(&vgpu->gvt->sched_lock);
+}