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, 394 insertions, 0 deletions

diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
new file mode 100644
index 000000000..4c09e313b
--- /dev/null
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -0,0 +1,394 @@
+/*
+ * Copyright (C) 2015 Red Hat, Inc.
+ * 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 <drm/drm_atomic_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_fourcc.h>
+
+#include "virtgpu_drv.h"
+
+static const uint32_t virtio_gpu_formats[] = {
+	DRM_FORMAT_HOST_XRGB8888,
+};
+
+static const uint32_t virtio_gpu_cursor_formats[] = {
+	DRM_FORMAT_HOST_ARGB8888,
+};
+
+uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc)
+{
+	uint32_t format;
+
+	switch (drm_fourcc) {
+	case DRM_FORMAT_XRGB8888:
+		format = VIRTIO_GPU_FORMAT_B8G8R8X8_UNORM;
+		break;
+	case DRM_FORMAT_ARGB8888:
+		format = VIRTIO_GPU_FORMAT_B8G8R8A8_UNORM;
+		break;
+	case DRM_FORMAT_BGRX8888:
+		format = VIRTIO_GPU_FORMAT_X8R8G8B8_UNORM;
+		break;
+	case DRM_FORMAT_BGRA8888:
+		format = VIRTIO_GPU_FORMAT_A8R8G8B8_UNORM;
+		break;
+	default:
+		/*
+		 * This should not happen, we handle everything listed
+		 * in virtio_gpu_formats[].
+		 */
+		format = 0;
+		break;
+	}
+	WARN_ON(format == 0);
+	return format;
+}
+
+static const struct drm_plane_funcs virtio_gpu_plane_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+static int virtio_gpu_plane_atomic_check(struct drm_plane *plane,
+					 struct drm_atomic_state *state)
+{
+	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
+										 plane);
+	bool is_cursor = plane->type == DRM_PLANE_TYPE_CURSOR;
+	struct drm_crtc_state *crtc_state;
+	int ret;
+
+	if (!new_plane_state->fb || WARN_ON(!new_plane_state->crtc))
+		return 0;
+
+	crtc_state = drm_atomic_get_crtc_state(state,
+					       new_plane_state->crtc);
+	if (IS_ERR(crtc_state))
+                return PTR_ERR(crtc_state);
+
+	ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state,
+						  DRM_PLANE_NO_SCALING,
+						  DRM_PLANE_NO_SCALING,
+						  is_cursor, true);
+	return ret;
+}
+
+static void virtio_gpu_update_dumb_bo(struct virtio_gpu_device *vgdev,
+				      struct drm_plane_state *state,
+				      struct drm_rect *rect)
+{
+	struct virtio_gpu_object *bo =
+		gem_to_virtio_gpu_obj(state->fb->obj[0]);
+	struct virtio_gpu_object_array *objs;
+	uint32_t w = rect->x2 - rect->x1;
+	uint32_t h = rect->y2 - rect->y1;
+	uint32_t x = rect->x1;
+	uint32_t y = rect->y1;
+	uint32_t off = x * state->fb->format->cpp[0] +
+		y * state->fb->pitches[0];
+
+	objs = virtio_gpu_array_alloc(1);
+	if (!objs)
+		return;
+	virtio_gpu_array_add_obj(objs, &bo->base.base);
+
+	virtio_gpu_cmd_transfer_to_host_2d(vgdev, off, w, h, x, y,
+					   objs, NULL);
+}
+
+static void virtio_gpu_resource_flush(struct drm_plane *plane,
+				      uint32_t x, uint32_t y,
+				      uint32_t width, uint32_t height)
+{
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_object *bo;
+
+	vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
+	if (vgfb->fence) {
+		struct virtio_gpu_object_array *objs;
+
+		objs = virtio_gpu_array_alloc(1);
+		if (!objs)
+			return;
+		virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]);
+		virtio_gpu_array_lock_resv(objs);
+		virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y,
+					      width, height, objs, vgfb->fence);
+		virtio_gpu_notify(vgdev);
+
+		dma_fence_wait_timeout(&vgfb->fence->f, true,
+				       msecs_to_jiffies(50));
+		dma_fence_put(&vgfb->fence->f);
+		vgfb->fence = NULL;
+	} else {
+		virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y,
+					      width, height, NULL, NULL);
+		virtio_gpu_notify(vgdev);
+	}
+}
+
+static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
+					    struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state,
+									   plane);
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_output *output = NULL;
+	struct virtio_gpu_object *bo;
+	struct drm_rect rect;
+
+	if (plane->state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(plane->state->crtc);
+	if (old_state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(old_state->crtc);
+	if (WARN_ON(!output))
+		return;
+
+	if (!plane->state->fb || !output->crtc.state->active) {
+		DRM_DEBUG("nofb\n");
+		virtio_gpu_cmd_set_scanout(vgdev, output->index, 0,
+					   plane->state->src_w >> 16,
+					   plane->state->src_h >> 16,
+					   0, 0);
+		virtio_gpu_notify(vgdev);
+		return;
+	}
+
+	if (!drm_atomic_helper_damage_merged(old_state, plane->state, &rect))
+		return;
+
+	bo = gem_to_virtio_gpu_obj(plane->state->fb->obj[0]);
+	if (bo->dumb)
+		virtio_gpu_update_dumb_bo(vgdev, plane->state, &rect);
+
+	if (plane->state->fb != old_state->fb ||
+	    plane->state->src_w != old_state->src_w ||
+	    plane->state->src_h != old_state->src_h ||
+	    plane->state->src_x != old_state->src_x ||
+	    plane->state->src_y != old_state->src_y ||
+	    output->needs_modeset) {
+		output->needs_modeset = false;
+		DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n",
+			  bo->hw_res_handle,
+			  plane->state->crtc_w, plane->state->crtc_h,
+			  plane->state->crtc_x, plane->state->crtc_y,
+			  plane->state->src_w >> 16,
+			  plane->state->src_h >> 16,
+			  plane->state->src_x >> 16,
+			  plane->state->src_y >> 16);
+
+		if (bo->host3d_blob || bo->guest_blob) {
+			virtio_gpu_cmd_set_scanout_blob
+						(vgdev, output->index, bo,
+						 plane->state->fb,
+						 plane->state->src_w >> 16,
+						 plane->state->src_h >> 16,
+						 plane->state->src_x >> 16,
+						 plane->state->src_y >> 16);
+		} else {
+			virtio_gpu_cmd_set_scanout(vgdev, output->index,
+						   bo->hw_res_handle,
+						   plane->state->src_w >> 16,
+						   plane->state->src_h >> 16,
+						   plane->state->src_x >> 16,
+						   plane->state->src_y >> 16);
+		}
+	}
+
+	virtio_gpu_resource_flush(plane,
+				  rect.x1,
+				  rect.y1,
+				  rect.x2 - rect.x1,
+				  rect.y2 - rect.y1);
+}
+
+static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane,
+				       struct drm_plane_state *new_state)
+{
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_object *bo;
+
+	if (!new_state->fb)
+		return 0;
+
+	vgfb = to_virtio_gpu_framebuffer(new_state->fb);
+	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
+	if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob))
+		return 0;
+
+	if (bo->dumb && (plane->state->fb != new_state->fb)) {
+		vgfb->fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context,
+						     0);
+		if (!vgfb->fence)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane,
+					struct drm_plane_state *state)
+{
+	struct virtio_gpu_framebuffer *vgfb;
+
+	if (!state->fb)
+		return;
+
+	vgfb = to_virtio_gpu_framebuffer(state->fb);
+	if (vgfb->fence) {
+		dma_fence_put(&vgfb->fence->f);
+		vgfb->fence = NULL;
+	}
+}
+
+static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
+					   struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state,
+									   plane);
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_output *output = NULL;
+	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_object *bo = NULL;
+	uint32_t handle;
+
+	if (plane->state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(plane->state->crtc);
+	if (old_state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(old_state->crtc);
+	if (WARN_ON(!output))
+		return;
+
+	if (plane->state->fb) {
+		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
+		handle = bo->hw_res_handle;
+	} else {
+		handle = 0;
+	}
+
+	if (bo && bo->dumb && (plane->state->fb != old_state->fb)) {
+		/* new cursor -- update & wait */
+		struct virtio_gpu_object_array *objs;
+
+		objs = virtio_gpu_array_alloc(1);
+		if (!objs)
+			return;
+		virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]);
+		virtio_gpu_array_lock_resv(objs);
+		virtio_gpu_cmd_transfer_to_host_2d
+			(vgdev, 0,
+			 plane->state->crtc_w,
+			 plane->state->crtc_h,
+			 0, 0, objs, vgfb->fence);
+		virtio_gpu_notify(vgdev);
+		dma_fence_wait(&vgfb->fence->f, true);
+		dma_fence_put(&vgfb->fence->f);
+		vgfb->fence = NULL;
+	}
+
+	if (plane->state->fb != old_state->fb) {
+		DRM_DEBUG("update, handle %d, pos +%d+%d, hot %d,%d\n", handle,
+			  plane->state->crtc_x,
+			  plane->state->crtc_y,
+			  plane->state->fb ? plane->state->fb->hot_x : 0,
+			  plane->state->fb ? plane->state->fb->hot_y : 0);
+		output->cursor.hdr.type =
+			cpu_to_le32(VIRTIO_GPU_CMD_UPDATE_CURSOR);
+		output->cursor.resource_id = cpu_to_le32(handle);
+		if (plane->state->fb) {
+			output->cursor.hot_x =
+				cpu_to_le32(plane->state->fb->hot_x);
+			output->cursor.hot_y =
+				cpu_to_le32(plane->state->fb->hot_y);
+		} else {
+			output->cursor.hot_x = cpu_to_le32(0);
+			output->cursor.hot_y = cpu_to_le32(0);
+		}
+	} else {
+		DRM_DEBUG("move +%d+%d\n",
+			  plane->state->crtc_x,
+			  plane->state->crtc_y);
+		output->cursor.hdr.type =
+			cpu_to_le32(VIRTIO_GPU_CMD_MOVE_CURSOR);
+	}
+	output->cursor.pos.x = cpu_to_le32(plane->state->crtc_x);
+	output->cursor.pos.y = cpu_to_le32(plane->state->crtc_y);
+	virtio_gpu_cursor_ping(vgdev, output);
+}
+
+static const struct drm_plane_helper_funcs virtio_gpu_primary_helper_funcs = {
+	.prepare_fb		= virtio_gpu_plane_prepare_fb,
+	.cleanup_fb		= virtio_gpu_plane_cleanup_fb,
+	.atomic_check		= virtio_gpu_plane_atomic_check,
+	.atomic_update		= virtio_gpu_primary_plane_update,
+};
+
+static const struct drm_plane_helper_funcs virtio_gpu_cursor_helper_funcs = {
+	.prepare_fb		= virtio_gpu_plane_prepare_fb,
+	.cleanup_fb		= virtio_gpu_plane_cleanup_fb,
+	.atomic_check		= virtio_gpu_plane_atomic_check,
+	.atomic_update		= virtio_gpu_cursor_plane_update,
+};
+
+struct drm_plane *virtio_gpu_plane_init(struct virtio_gpu_device *vgdev,
+					enum drm_plane_type type,
+					int index)
+{
+	struct drm_device *dev = vgdev->ddev;
+	const struct drm_plane_helper_funcs *funcs;
+	struct drm_plane *plane;
+	const uint32_t *formats;
+	int nformats;
+
+	if (type == DRM_PLANE_TYPE_CURSOR) {
+		formats = virtio_gpu_cursor_formats;
+		nformats = ARRAY_SIZE(virtio_gpu_cursor_formats);
+		funcs = &virtio_gpu_cursor_helper_funcs;
+	} else {
+		formats = virtio_gpu_formats;
+		nformats = ARRAY_SIZE(virtio_gpu_formats);
+		funcs = &virtio_gpu_primary_helper_funcs;
+	}
+
+	plane = drmm_universal_plane_alloc(dev, struct drm_plane, dev,
+					   1 << index, &virtio_gpu_plane_funcs,
+					   formats, nformats, NULL, type, NULL);
+	if (IS_ERR(plane))
+		return plane;
+
+	drm_plane_helper_add(plane, funcs);
+	return plane;
+}