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, 558 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
new file mode 100644
index 000000000..274c6ef42
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -0,0 +1,558 @@
+/*
+ * 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:
+ *    Zhiyuan Lv <zhiyuan.lv@intel.com>
+ *    Zhi Wang <zhi.a.wang@intel.com>
+ *
+ * Contributors:
+ *    Min He <min.he@intel.com>
+ *    Bing Niu <bing.niu@intel.com>
+ *    Ping Gao <ping.a.gao@intel.com>
+ *    Tina Zhang <tina.zhang@intel.com>
+ *
+ */
+
+#include "i915_drv.h"
+#include "gvt.h"
+
+#define _EL_OFFSET_STATUS       0x234
+#define _EL_OFFSET_STATUS_BUF   0x370
+#define _EL_OFFSET_STATUS_PTR   0x3A0
+
+#define execlist_ring_mmio(e, offset) ((e)->mmio_base + (offset))
+
+#define valid_context(ctx) ((ctx)->valid)
+#define same_context(a, b) (((a)->context_id == (b)->context_id) && \
+		((a)->lrca == (b)->lrca))
+
+static int context_switch_events[] = {
+	[RCS0]  = RCS_AS_CONTEXT_SWITCH,
+	[BCS0]  = BCS_AS_CONTEXT_SWITCH,
+	[VCS0]  = VCS_AS_CONTEXT_SWITCH,
+	[VCS1]  = VCS2_AS_CONTEXT_SWITCH,
+	[VECS0] = VECS_AS_CONTEXT_SWITCH,
+};
+
+static int to_context_switch_event(const struct intel_engine_cs *engine)
+{
+	if (WARN_ON(engine->id >= ARRAY_SIZE(context_switch_events)))
+		return -EINVAL;
+
+	return context_switch_events[engine->id];
+}
+
+static void switch_virtual_execlist_slot(struct intel_vgpu_execlist *execlist)
+{
+	gvt_dbg_el("[before] running slot %d/context %x pending slot %d\n",
+			execlist->running_slot ?
+			execlist->running_slot->index : -1,
+			execlist->running_context ?
+			execlist->running_context->context_id : 0,
+			execlist->pending_slot ?
+			execlist->pending_slot->index : -1);
+
+	execlist->running_slot = execlist->pending_slot;
+	execlist->pending_slot = NULL;
+	execlist->running_context = execlist->running_context ?
+		&execlist->running_slot->ctx[0] : NULL;
+
+	gvt_dbg_el("[after] running slot %d/context %x pending slot %d\n",
+			execlist->running_slot ?
+			execlist->running_slot->index : -1,
+			execlist->running_context ?
+			execlist->running_context->context_id : 0,
+			execlist->pending_slot ?
+			execlist->pending_slot->index : -1);
+}
+
+static void emulate_execlist_status(struct intel_vgpu_execlist *execlist)
+{
+	struct intel_vgpu_execlist_slot *running = execlist->running_slot;
+	struct intel_vgpu_execlist_slot *pending = execlist->pending_slot;
+	struct execlist_ctx_descriptor_format *desc = execlist->running_context;
+	struct intel_vgpu *vgpu = execlist->vgpu;
+	struct execlist_status_format status;
+	u32 status_reg =
+		execlist_ring_mmio(execlist->engine, _EL_OFFSET_STATUS);
+
+	status.ldw = vgpu_vreg(vgpu, status_reg);
+	status.udw = vgpu_vreg(vgpu, status_reg + 4);
+
+	if (running) {
+		status.current_execlist_pointer = !!running->index;
+		status.execlist_write_pointer = !!!running->index;
+		status.execlist_0_active = status.execlist_0_valid =
+			!!!(running->index);
+		status.execlist_1_active = status.execlist_1_valid =
+			!!(running->index);
+	} else {
+		status.context_id = 0;
+		status.execlist_0_active = status.execlist_0_valid = 0;
+		status.execlist_1_active = status.execlist_1_valid = 0;
+	}
+
+	status.context_id = desc ? desc->context_id : 0;
+	status.execlist_queue_full = !!(pending);
+
+	vgpu_vreg(vgpu, status_reg) = status.ldw;
+	vgpu_vreg(vgpu, status_reg + 4) = status.udw;
+
+	gvt_dbg_el("vgpu%d: status reg offset %x ldw %x udw %x\n",
+		vgpu->id, status_reg, status.ldw, status.udw);
+}
+
+static void emulate_csb_update(struct intel_vgpu_execlist *execlist,
+			       struct execlist_context_status_format *status,
+			       bool trigger_interrupt_later)
+{
+	struct intel_vgpu *vgpu = execlist->vgpu;
+	struct execlist_context_status_pointer_format ctx_status_ptr;
+	u32 write_pointer;
+	u32 ctx_status_ptr_reg, ctx_status_buf_reg, offset;
+	unsigned long hwsp_gpa;
+
+	ctx_status_ptr_reg =
+		execlist_ring_mmio(execlist->engine, _EL_OFFSET_STATUS_PTR);
+	ctx_status_buf_reg =
+		execlist_ring_mmio(execlist->engine, _EL_OFFSET_STATUS_BUF);
+
+	ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
+
+	write_pointer = ctx_status_ptr.write_ptr;
+
+	if (write_pointer == 0x7)
+		write_pointer = 0;
+	else {
+		++write_pointer;
+		write_pointer %= 0x6;
+	}
+
+	offset = ctx_status_buf_reg + write_pointer * 8;
+
+	vgpu_vreg(vgpu, offset) = status->ldw;
+	vgpu_vreg(vgpu, offset + 4) = status->udw;
+
+	ctx_status_ptr.write_ptr = write_pointer;
+	vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
+
+	/* Update the CSB and CSB write pointer in HWSP */
+	hwsp_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm,
+					 vgpu->hws_pga[execlist->engine->id]);
+	if (hwsp_gpa != INTEL_GVT_INVALID_ADDR) {
+		intel_gvt_write_gpa(vgpu,
+			hwsp_gpa + I915_HWS_CSB_BUF0_INDEX * 4 + write_pointer * 8,
+			status, 8);
+		intel_gvt_write_gpa(vgpu,
+			hwsp_gpa + INTEL_HWS_CSB_WRITE_INDEX(execlist->engine->i915) * 4,
+			&write_pointer, 4);
+	}
+
+	gvt_dbg_el("vgpu%d: w pointer %u reg %x csb l %x csb h %x\n",
+		   vgpu->id, write_pointer, offset, status->ldw, status->udw);
+
+	if (trigger_interrupt_later)
+		return;
+
+	intel_vgpu_trigger_virtual_event(vgpu,
+					 to_context_switch_event(execlist->engine));
+}
+
+static int emulate_execlist_ctx_schedule_out(
+		struct intel_vgpu_execlist *execlist,
+		struct execlist_ctx_descriptor_format *ctx)
+{
+	struct intel_vgpu *vgpu = execlist->vgpu;
+	struct intel_vgpu_execlist_slot *running = execlist->running_slot;
+	struct intel_vgpu_execlist_slot *pending = execlist->pending_slot;
+	struct execlist_ctx_descriptor_format *ctx0 = &running->ctx[0];
+	struct execlist_ctx_descriptor_format *ctx1 = &running->ctx[1];
+	struct execlist_context_status_format status;
+
+	memset(&status, 0, sizeof(status));
+
+	gvt_dbg_el("schedule out context id %x\n", ctx->context_id);
+
+	if (WARN_ON(!same_context(ctx, execlist->running_context))) {
+		gvt_vgpu_err("schedule out context is not running context,"
+				"ctx id %x running ctx id %x\n",
+				ctx->context_id,
+				execlist->running_context->context_id);
+		return -EINVAL;
+	}
+
+	/* ctx1 is valid, ctx0/ctx is scheduled-out -> element switch */
+	if (valid_context(ctx1) && same_context(ctx0, ctx)) {
+		gvt_dbg_el("ctx 1 valid, ctx/ctx 0 is scheduled-out\n");
+
+		execlist->running_context = ctx1;
+
+		emulate_execlist_status(execlist);
+
+		status.context_complete = status.element_switch = 1;
+		status.context_id = ctx->context_id;
+
+		emulate_csb_update(execlist, &status, false);
+		/*
+		 * ctx1 is not valid, ctx == ctx0
+		 * ctx1 is valid, ctx1 == ctx
+		 *	--> last element is finished
+		 * emulate:
+		 *	active-to-idle if there is *no* pending execlist
+		 *	context-complete if there *is* pending execlist
+		 */
+	} else if ((!valid_context(ctx1) && same_context(ctx0, ctx))
+			|| (valid_context(ctx1) && same_context(ctx1, ctx))) {
+		gvt_dbg_el("need to switch virtual execlist slot\n");
+
+		switch_virtual_execlist_slot(execlist);
+
+		emulate_execlist_status(execlist);
+
+		status.context_complete = status.active_to_idle = 1;
+		status.context_id = ctx->context_id;
+
+		if (!pending) {
+			emulate_csb_update(execlist, &status, false);
+		} else {
+			emulate_csb_update(execlist, &status, true);
+
+			memset(&status, 0, sizeof(status));
+
+			status.idle_to_active = 1;
+			status.context_id = 0;
+
+			emulate_csb_update(execlist, &status, false);
+		}
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct intel_vgpu_execlist_slot *get_next_execlist_slot(
+		struct intel_vgpu_execlist *execlist)
+{
+	struct intel_vgpu *vgpu = execlist->vgpu;
+	u32 status_reg =
+		execlist_ring_mmio(execlist->engine, _EL_OFFSET_STATUS);
+	struct execlist_status_format status;
+
+	status.ldw = vgpu_vreg(vgpu, status_reg);
+	status.udw = vgpu_vreg(vgpu, status_reg + 4);
+
+	if (status.execlist_queue_full) {
+		gvt_vgpu_err("virtual execlist slots are full\n");
+		return NULL;
+	}
+
+	return &execlist->slot[status.execlist_write_pointer];
+}
+
+static int emulate_execlist_schedule_in(struct intel_vgpu_execlist *execlist,
+		struct execlist_ctx_descriptor_format ctx[2])
+{
+	struct intel_vgpu_execlist_slot *running = execlist->running_slot;
+	struct intel_vgpu_execlist_slot *slot =
+		get_next_execlist_slot(execlist);
+
+	struct execlist_ctx_descriptor_format *ctx0, *ctx1;
+	struct execlist_context_status_format status;
+	struct intel_vgpu *vgpu = execlist->vgpu;
+
+	gvt_dbg_el("emulate schedule-in\n");
+
+	if (!slot) {
+		gvt_vgpu_err("no available execlist slot\n");
+		return -EINVAL;
+	}
+
+	memset(&status, 0, sizeof(status));
+	memset(slot->ctx, 0, sizeof(slot->ctx));
+
+	slot->ctx[0] = ctx[0];
+	slot->ctx[1] = ctx[1];
+
+	gvt_dbg_el("alloc slot index %d ctx 0 %x ctx 1 %x\n",
+			slot->index, ctx[0].context_id,
+			ctx[1].context_id);
+
+	/*
+	 * no running execlist, make this write bundle as running execlist
+	 * -> idle-to-active
+	 */
+	if (!running) {
+		gvt_dbg_el("no current running execlist\n");
+
+		execlist->running_slot = slot;
+		execlist->pending_slot = NULL;
+		execlist->running_context = &slot->ctx[0];
+
+		gvt_dbg_el("running slot index %d running context %x\n",
+				execlist->running_slot->index,
+				execlist->running_context->context_id);
+
+		emulate_execlist_status(execlist);
+
+		status.idle_to_active = 1;
+		status.context_id = 0;
+
+		emulate_csb_update(execlist, &status, false);
+		return 0;
+	}
+
+	ctx0 = &running->ctx[0];
+	ctx1 = &running->ctx[1];
+
+	gvt_dbg_el("current running slot index %d ctx 0 %x ctx 1 %x\n",
+		running->index, ctx0->context_id, ctx1->context_id);
+
+	/*
+	 * already has an running execlist
+	 *	a. running ctx1 is valid,
+	 *	   ctx0 is finished, and running ctx1 == new execlist ctx[0]
+	 *	b. running ctx1 is not valid,
+	 *	   ctx0 == new execlist ctx[0]
+	 * ----> lite-restore + preempted
+	 */
+	if ((valid_context(ctx1) && same_context(ctx1, &slot->ctx[0]) &&
+		/* condition a */
+		(!same_context(ctx0, execlist->running_context))) ||
+			(!valid_context(ctx1) &&
+			 same_context(ctx0, &slot->ctx[0]))) { /* condition b */
+		gvt_dbg_el("need to switch virtual execlist slot\n");
+
+		execlist->pending_slot = slot;
+		switch_virtual_execlist_slot(execlist);
+
+		emulate_execlist_status(execlist);
+
+		status.lite_restore = status.preempted = 1;
+		status.context_id = ctx[0].context_id;
+
+		emulate_csb_update(execlist, &status, false);
+	} else {
+		gvt_dbg_el("emulate as pending slot\n");
+		/*
+		 * otherwise
+		 * --> emulate pending execlist exist + but no preemption case
+		 */
+		execlist->pending_slot = slot;
+		emulate_execlist_status(execlist);
+	}
+	return 0;
+}
+
+#define get_desc_from_elsp_dwords(ed, i) \
+	((struct execlist_ctx_descriptor_format *)&((ed)->data[i * 2]))
+
+static int prepare_execlist_workload(struct intel_vgpu_workload *workload)
+{
+	struct intel_vgpu *vgpu = workload->vgpu;
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct execlist_ctx_descriptor_format ctx[2];
+	int ret;
+
+	if (!workload->emulate_schedule_in)
+		return 0;
+
+	ctx[0] = *get_desc_from_elsp_dwords(&workload->elsp_dwords, 0);
+	ctx[1] = *get_desc_from_elsp_dwords(&workload->elsp_dwords, 1);
+
+	ret = emulate_execlist_schedule_in(&s->execlist[workload->engine->id],
+					   ctx);
+	if (ret) {
+		gvt_vgpu_err("fail to emulate execlist schedule in\n");
+		return ret;
+	}
+	return 0;
+}
+
+static int complete_execlist_workload(struct intel_vgpu_workload *workload)
+{
+	struct intel_vgpu *vgpu = workload->vgpu;
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_vgpu_execlist *execlist =
+		&s->execlist[workload->engine->id];
+	struct intel_vgpu_workload *next_workload;
+	struct list_head *next = workload_q_head(vgpu, workload->engine)->next;
+	bool lite_restore = false;
+	int ret = 0;
+
+	gvt_dbg_el("complete workload %p status %d\n",
+		   workload, workload->status);
+
+	if (workload->status || vgpu->resetting_eng & workload->engine->mask)
+		goto out;
+
+	if (!list_empty(workload_q_head(vgpu, workload->engine))) {
+		struct execlist_ctx_descriptor_format *this_desc, *next_desc;
+
+		next_workload = container_of(next,
+				struct intel_vgpu_workload, list);
+		this_desc = &workload->ctx_desc;
+		next_desc = &next_workload->ctx_desc;
+
+		lite_restore = same_context(this_desc, next_desc);
+	}
+
+	if (lite_restore) {
+		gvt_dbg_el("next context == current - no schedule-out\n");
+		goto out;
+	}
+
+	ret = emulate_execlist_ctx_schedule_out(execlist, &workload->ctx_desc);
+out:
+	return ret;
+}
+
+static int submit_context(struct intel_vgpu *vgpu,
+			  const struct intel_engine_cs *engine,
+			  struct execlist_ctx_descriptor_format *desc,
+			  bool emulate_schedule_in)
+{
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_vgpu_workload *workload = NULL;
+
+	workload = intel_vgpu_create_workload(vgpu, engine, desc);
+	if (IS_ERR(workload))
+		return PTR_ERR(workload);
+
+	workload->prepare = prepare_execlist_workload;
+	workload->complete = complete_execlist_workload;
+	workload->emulate_schedule_in = emulate_schedule_in;
+
+	if (emulate_schedule_in)
+		workload->elsp_dwords = s->execlist[engine->id].elsp_dwords;
+
+	gvt_dbg_el("workload %p emulate schedule_in %d\n", workload,
+		   emulate_schedule_in);
+
+	intel_vgpu_queue_workload(workload);
+	return 0;
+}
+
+int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu,
+			       const struct intel_engine_cs *engine)
+{
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_vgpu_execlist *execlist = &s->execlist[engine->id];
+	struct execlist_ctx_descriptor_format *desc[2];
+	int i, ret;
+
+	desc[0] = get_desc_from_elsp_dwords(&execlist->elsp_dwords, 0);
+	desc[1] = get_desc_from_elsp_dwords(&execlist->elsp_dwords, 1);
+
+	if (!desc[0]->valid) {
+		gvt_vgpu_err("invalid elsp submission, desc0 is invalid\n");
+		goto inv_desc;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(desc); i++) {
+		if (!desc[i]->valid)
+			continue;
+		if (!desc[i]->privilege_access) {
+			gvt_vgpu_err("unexpected GGTT elsp submission\n");
+			goto inv_desc;
+		}
+	}
+
+	/* submit workload */
+	for (i = 0; i < ARRAY_SIZE(desc); i++) {
+		if (!desc[i]->valid)
+			continue;
+		ret = submit_context(vgpu, engine, desc[i], i == 0);
+		if (ret) {
+			gvt_vgpu_err("failed to submit desc %d\n", i);
+			return ret;
+		}
+	}
+
+	return 0;
+
+inv_desc:
+	gvt_vgpu_err("descriptors content: desc0 %08x %08x desc1 %08x %08x\n",
+		     desc[0]->udw, desc[0]->ldw, desc[1]->udw, desc[1]->ldw);
+	return -EINVAL;
+}
+
+static void init_vgpu_execlist(struct intel_vgpu *vgpu,
+			       const struct intel_engine_cs *engine)
+{
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_vgpu_execlist *execlist = &s->execlist[engine->id];
+	struct execlist_context_status_pointer_format ctx_status_ptr;
+	u32 ctx_status_ptr_reg;
+
+	memset(execlist, 0, sizeof(*execlist));
+
+	execlist->vgpu = vgpu;
+	execlist->engine = engine;
+	execlist->slot[0].index = 0;
+	execlist->slot[1].index = 1;
+
+	ctx_status_ptr_reg = execlist_ring_mmio(engine, _EL_OFFSET_STATUS_PTR);
+	ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
+	ctx_status_ptr.read_ptr = 0;
+	ctx_status_ptr.write_ptr = 0x7;
+	vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
+}
+
+static void clean_execlist(struct intel_vgpu *vgpu,
+			   intel_engine_mask_t engine_mask)
+{
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_engine_cs *engine;
+	intel_engine_mask_t tmp;
+
+	for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp) {
+		kfree(s->ring_scan_buffer[engine->id]);
+		s->ring_scan_buffer[engine->id] = NULL;
+		s->ring_scan_buffer_size[engine->id] = 0;
+	}
+}
+
+static void reset_execlist(struct intel_vgpu *vgpu,
+			   intel_engine_mask_t engine_mask)
+{
+	struct intel_engine_cs *engine;
+	intel_engine_mask_t tmp;
+
+	for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp)
+		init_vgpu_execlist(vgpu, engine);
+}
+
+static int init_execlist(struct intel_vgpu *vgpu,
+			 intel_engine_mask_t engine_mask)
+{
+	reset_execlist(vgpu, engine_mask);
+	return 0;
+}
+
+const struct intel_vgpu_submission_ops intel_vgpu_execlist_submission_ops = {
+	.name = "execlist",
+	.init = init_execlist,
+	.reset = reset_execlist,
+	.clean = clean_execlist,
+};