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, 590 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
new file mode 100644
index 000000000..ffe41e9be
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -0,0 +1,590 @@
+/*
+ * Copyright 2017 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>
+ *
+ * Contributors:
+ *    Xiaoguang Chen
+ *    Tina Zhang <tina.zhang@intel.com>
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/mdev.h>
+
+#include <drm/drm_fourcc.h>
+#include <drm/drm_plane.h>
+
+#include "gem/i915_gem_dmabuf.h"
+
+#include "i915_drv.h"
+#include "i915_reg.h"
+#include "gvt.h"
+
+#define GEN8_DECODE_PTE(pte) (pte & GENMASK_ULL(63, 12))
+
+static int vgpu_gem_get_pages(
+		struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct intel_vgpu *vgpu;
+	struct sg_table *st;
+	struct scatterlist *sg;
+	int i, j, ret;
+	gen8_pte_t __iomem *gtt_entries;
+	struct intel_vgpu_fb_info *fb_info;
+	u32 page_num;
+
+	fb_info = (struct intel_vgpu_fb_info *)obj->gvt_info;
+	if (drm_WARN_ON(&dev_priv->drm, !fb_info))
+		return -ENODEV;
+
+	vgpu = fb_info->obj->vgpu;
+	if (drm_WARN_ON(&dev_priv->drm, !vgpu))
+		return -ENODEV;
+
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (unlikely(!st))
+		return -ENOMEM;
+
+	page_num = obj->base.size >> PAGE_SHIFT;
+	ret = sg_alloc_table(st, page_num, GFP_KERNEL);
+	if (ret) {
+		kfree(st);
+		return ret;
+	}
+	gtt_entries = (gen8_pte_t __iomem *)to_gt(dev_priv)->ggtt->gsm +
+		(fb_info->start >> PAGE_SHIFT);
+	for_each_sg(st->sgl, sg, page_num, i) {
+		dma_addr_t dma_addr =
+			GEN8_DECODE_PTE(readq(&gtt_entries[i]));
+		if (intel_gvt_dma_pin_guest_page(vgpu, dma_addr)) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		sg->offset = 0;
+		sg->length = PAGE_SIZE;
+		sg_dma_len(sg) = PAGE_SIZE;
+		sg_dma_address(sg) = dma_addr;
+	}
+
+	__i915_gem_object_set_pages(obj, st);
+out:
+	if (ret) {
+		dma_addr_t dma_addr;
+
+		for_each_sg(st->sgl, sg, i, j) {
+			dma_addr = sg_dma_address(sg);
+			if (dma_addr)
+				intel_gvt_dma_unmap_guest_page(vgpu, dma_addr);
+		}
+		sg_free_table(st);
+		kfree(st);
+	}
+
+	return ret;
+
+}
+
+static void vgpu_gem_put_pages(struct drm_i915_gem_object *obj,
+		struct sg_table *pages)
+{
+	struct scatterlist *sg;
+
+	if (obj->base.dma_buf) {
+		struct intel_vgpu_fb_info *fb_info = obj->gvt_info;
+		struct intel_vgpu_dmabuf_obj *obj = fb_info->obj;
+		struct intel_vgpu *vgpu = obj->vgpu;
+		int i;
+
+		for_each_sg(pages->sgl, sg, fb_info->size, i)
+			intel_gvt_dma_unmap_guest_page(vgpu,
+					       sg_dma_address(sg));
+	}
+
+	sg_free_table(pages);
+	kfree(pages);
+}
+
+static void dmabuf_gem_object_free(struct kref *kref)
+{
+	struct intel_vgpu_dmabuf_obj *obj =
+		container_of(kref, struct intel_vgpu_dmabuf_obj, kref);
+	struct intel_vgpu *vgpu = obj->vgpu;
+	struct list_head *pos;
+	struct intel_vgpu_dmabuf_obj *dmabuf_obj;
+
+	if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) &&
+	    !list_empty(&vgpu->dmabuf_obj_list_head)) {
+		list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
+			dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
+			if (dmabuf_obj == obj) {
+				list_del(pos);
+				idr_remove(&vgpu->object_idr,
+					   dmabuf_obj->dmabuf_id);
+				kfree(dmabuf_obj->info);
+				kfree(dmabuf_obj);
+				break;
+			}
+		}
+	} else {
+		/* Free the orphan dmabuf_objs here */
+		kfree(obj->info);
+		kfree(obj);
+	}
+}
+
+
+static inline void dmabuf_obj_get(struct intel_vgpu_dmabuf_obj *obj)
+{
+	kref_get(&obj->kref);
+}
+
+static inline void dmabuf_obj_put(struct intel_vgpu_dmabuf_obj *obj)
+{
+	kref_put(&obj->kref, dmabuf_gem_object_free);
+}
+
+static void vgpu_gem_release(struct drm_i915_gem_object *gem_obj)
+{
+
+	struct intel_vgpu_fb_info *fb_info = gem_obj->gvt_info;
+	struct intel_vgpu_dmabuf_obj *obj = fb_info->obj;
+	struct intel_vgpu *vgpu = obj->vgpu;
+
+	if (vgpu) {
+		mutex_lock(&vgpu->dmabuf_lock);
+		gem_obj->base.dma_buf = NULL;
+		dmabuf_obj_put(obj);
+		mutex_unlock(&vgpu->dmabuf_lock);
+	} else {
+		/* vgpu is NULL, as it has been removed already */
+		gem_obj->base.dma_buf = NULL;
+		dmabuf_obj_put(obj);
+	}
+}
+
+static const struct drm_i915_gem_object_ops intel_vgpu_gem_ops = {
+	.name = "i915_gem_object_vgpu",
+	.flags = I915_GEM_OBJECT_IS_PROXY,
+	.get_pages = vgpu_gem_get_pages,
+	.put_pages = vgpu_gem_put_pages,
+	.release = vgpu_gem_release,
+};
+
+static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
+		struct intel_vgpu_fb_info *info)
+{
+	static struct lock_class_key lock_class;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_gem_object *obj;
+
+	obj = i915_gem_object_alloc();
+	if (obj == NULL)
+		return NULL;
+
+	drm_gem_private_object_init(dev, &obj->base,
+		roundup(info->size, PAGE_SIZE));
+	i915_gem_object_init(obj, &intel_vgpu_gem_ops, &lock_class, 0);
+	i915_gem_object_set_readonly(obj);
+
+	obj->read_domains = I915_GEM_DOMAIN_GTT;
+	obj->write_domain = 0;
+	if (GRAPHICS_VER(dev_priv) >= 9) {
+		unsigned int tiling_mode = 0;
+		unsigned int stride = 0;
+
+		switch (info->drm_format_mod) {
+		case DRM_FORMAT_MOD_LINEAR:
+			tiling_mode = I915_TILING_NONE;
+			break;
+		case I915_FORMAT_MOD_X_TILED:
+			tiling_mode = I915_TILING_X;
+			stride = info->stride;
+			break;
+		case I915_FORMAT_MOD_Y_TILED:
+		case I915_FORMAT_MOD_Yf_TILED:
+			tiling_mode = I915_TILING_Y;
+			stride = info->stride;
+			break;
+		default:
+			gvt_dbg_core("invalid drm_format_mod %llx for tiling\n",
+				     info->drm_format_mod);
+		}
+		obj->tiling_and_stride = tiling_mode | stride;
+	} else {
+		obj->tiling_and_stride = info->drm_format_mod ?
+					I915_TILING_X : 0;
+	}
+
+	return obj;
+}
+
+static bool validate_hotspot(struct intel_vgpu_cursor_plane_format *c)
+{
+	if (c && c->x_hot <= c->width && c->y_hot <= c->height)
+		return true;
+	else
+		return false;
+}
+
+static int vgpu_get_plane_info(struct drm_device *dev,
+		struct intel_vgpu *vgpu,
+		struct intel_vgpu_fb_info *info,
+		int plane_id)
+{
+	struct intel_vgpu_primary_plane_format p;
+	struct intel_vgpu_cursor_plane_format c;
+	int ret, tile_height = 1;
+
+	memset(info, 0, sizeof(*info));
+
+	if (plane_id == DRM_PLANE_TYPE_PRIMARY) {
+		ret = intel_vgpu_decode_primary_plane(vgpu, &p);
+		if (ret)
+			return ret;
+		info->start = p.base;
+		info->start_gpa = p.base_gpa;
+		info->width = p.width;
+		info->height = p.height;
+		info->stride = p.stride;
+		info->drm_format = p.drm_format;
+
+		switch (p.tiled) {
+		case PLANE_CTL_TILED_LINEAR:
+			info->drm_format_mod = DRM_FORMAT_MOD_LINEAR;
+			break;
+		case PLANE_CTL_TILED_X:
+			info->drm_format_mod = I915_FORMAT_MOD_X_TILED;
+			tile_height = 8;
+			break;
+		case PLANE_CTL_TILED_Y:
+			info->drm_format_mod = I915_FORMAT_MOD_Y_TILED;
+			tile_height = 32;
+			break;
+		case PLANE_CTL_TILED_YF:
+			info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED;
+			tile_height = 32;
+			break;
+		default:
+			gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled);
+		}
+	} else if (plane_id == DRM_PLANE_TYPE_CURSOR) {
+		ret = intel_vgpu_decode_cursor_plane(vgpu, &c);
+		if (ret)
+			return ret;
+		info->start = c.base;
+		info->start_gpa = c.base_gpa;
+		info->width = c.width;
+		info->height = c.height;
+		info->stride = c.width * (c.bpp / 8);
+		info->drm_format = c.drm_format;
+		info->drm_format_mod = 0;
+		info->x_pos = c.x_pos;
+		info->y_pos = c.y_pos;
+
+		if (validate_hotspot(&c)) {
+			info->x_hot = c.x_hot;
+			info->y_hot = c.y_hot;
+		} else {
+			info->x_hot = UINT_MAX;
+			info->y_hot = UINT_MAX;
+		}
+	} else {
+		gvt_vgpu_err("invalid plane id:%d\n", plane_id);
+		return -EINVAL;
+	}
+
+	info->size = info->stride * roundup(info->height, tile_height);
+	if (info->size == 0) {
+		gvt_vgpu_err("fb size is zero\n");
+		return -EINVAL;
+	}
+
+	if (info->start & (PAGE_SIZE - 1)) {
+		gvt_vgpu_err("Not aligned fb address:0x%llx\n", info->start);
+		return -EFAULT;
+	}
+
+	if (!intel_gvt_ggtt_validate_range(vgpu, info->start, info->size)) {
+		gvt_vgpu_err("invalid gma addr\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static struct intel_vgpu_dmabuf_obj *
+pick_dmabuf_by_info(struct intel_vgpu *vgpu,
+		    struct intel_vgpu_fb_info *latest_info)
+{
+	struct list_head *pos;
+	struct intel_vgpu_fb_info *fb_info;
+	struct intel_vgpu_dmabuf_obj *dmabuf_obj = NULL;
+	struct intel_vgpu_dmabuf_obj *ret = NULL;
+
+	list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
+		dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
+		if (!dmabuf_obj->info)
+			continue;
+
+		fb_info = (struct intel_vgpu_fb_info *)dmabuf_obj->info;
+		if ((fb_info->start == latest_info->start) &&
+		    (fb_info->start_gpa == latest_info->start_gpa) &&
+		    (fb_info->size == latest_info->size) &&
+		    (fb_info->drm_format_mod == latest_info->drm_format_mod) &&
+		    (fb_info->drm_format == latest_info->drm_format) &&
+		    (fb_info->width == latest_info->width) &&
+		    (fb_info->height == latest_info->height)) {
+			ret = dmabuf_obj;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static struct intel_vgpu_dmabuf_obj *
+pick_dmabuf_by_num(struct intel_vgpu *vgpu, u32 id)
+{
+	struct list_head *pos;
+	struct intel_vgpu_dmabuf_obj *dmabuf_obj = NULL;
+	struct intel_vgpu_dmabuf_obj *ret = NULL;
+
+	list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
+		dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
+		if (dmabuf_obj->dmabuf_id == id) {
+			ret = dmabuf_obj;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void update_fb_info(struct vfio_device_gfx_plane_info *gvt_dmabuf,
+		      struct intel_vgpu_fb_info *fb_info)
+{
+	gvt_dmabuf->drm_format = fb_info->drm_format;
+	gvt_dmabuf->drm_format_mod = fb_info->drm_format_mod;
+	gvt_dmabuf->width = fb_info->width;
+	gvt_dmabuf->height = fb_info->height;
+	gvt_dmabuf->stride = fb_info->stride;
+	gvt_dmabuf->size = fb_info->size;
+	gvt_dmabuf->x_pos = fb_info->x_pos;
+	gvt_dmabuf->y_pos = fb_info->y_pos;
+	gvt_dmabuf->x_hot = fb_info->x_hot;
+	gvt_dmabuf->y_hot = fb_info->y_hot;
+}
+
+int intel_vgpu_query_plane(struct intel_vgpu *vgpu, void *args)
+{
+	struct drm_device *dev = &vgpu->gvt->gt->i915->drm;
+	struct vfio_device_gfx_plane_info *gfx_plane_info = args;
+	struct intel_vgpu_dmabuf_obj *dmabuf_obj;
+	struct intel_vgpu_fb_info fb_info;
+	int ret = 0;
+
+	if (gfx_plane_info->flags == (VFIO_GFX_PLANE_TYPE_DMABUF |
+				       VFIO_GFX_PLANE_TYPE_PROBE))
+		return ret;
+	else if ((gfx_plane_info->flags & ~VFIO_GFX_PLANE_TYPE_DMABUF) ||
+			(!gfx_plane_info->flags))
+		return -EINVAL;
+
+	ret = vgpu_get_plane_info(dev, vgpu, &fb_info,
+					gfx_plane_info->drm_plane_type);
+	if (ret != 0)
+		goto out;
+
+	mutex_lock(&vgpu->dmabuf_lock);
+	/* If exists, pick up the exposed dmabuf_obj */
+	dmabuf_obj = pick_dmabuf_by_info(vgpu, &fb_info);
+	if (dmabuf_obj) {
+		update_fb_info(gfx_plane_info, &fb_info);
+		gfx_plane_info->dmabuf_id = dmabuf_obj->dmabuf_id;
+
+		/* This buffer may be released between query_plane ioctl and
+		 * get_dmabuf ioctl. Add the refcount to make sure it won't
+		 * be released between the two ioctls.
+		 */
+		if (!dmabuf_obj->initref) {
+			dmabuf_obj->initref = true;
+			dmabuf_obj_get(dmabuf_obj);
+		}
+		ret = 0;
+		gvt_dbg_dpy("vgpu%d: re-use dmabuf_obj ref %d, id %d\n",
+			    vgpu->id, kref_read(&dmabuf_obj->kref),
+			    gfx_plane_info->dmabuf_id);
+		mutex_unlock(&vgpu->dmabuf_lock);
+		goto out;
+	}
+
+	mutex_unlock(&vgpu->dmabuf_lock);
+
+	/* Need to allocate a new one*/
+	dmabuf_obj = kmalloc(sizeof(struct intel_vgpu_dmabuf_obj), GFP_KERNEL);
+	if (unlikely(!dmabuf_obj)) {
+		gvt_vgpu_err("alloc dmabuf_obj failed\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	dmabuf_obj->info = kmalloc(sizeof(struct intel_vgpu_fb_info),
+				   GFP_KERNEL);
+	if (unlikely(!dmabuf_obj->info)) {
+		gvt_vgpu_err("allocate intel vgpu fb info failed\n");
+		ret = -ENOMEM;
+		goto out_free_dmabuf;
+	}
+	memcpy(dmabuf_obj->info, &fb_info, sizeof(struct intel_vgpu_fb_info));
+
+	((struct intel_vgpu_fb_info *)dmabuf_obj->info)->obj = dmabuf_obj;
+
+	dmabuf_obj->vgpu = vgpu;
+
+	ret = idr_alloc(&vgpu->object_idr, dmabuf_obj, 1, 0, GFP_NOWAIT);
+	if (ret < 0)
+		goto out_free_info;
+	gfx_plane_info->dmabuf_id = ret;
+	dmabuf_obj->dmabuf_id = ret;
+
+	dmabuf_obj->initref = true;
+
+	kref_init(&dmabuf_obj->kref);
+
+	update_fb_info(gfx_plane_info, &fb_info);
+
+	INIT_LIST_HEAD(&dmabuf_obj->list);
+	mutex_lock(&vgpu->dmabuf_lock);
+	list_add_tail(&dmabuf_obj->list, &vgpu->dmabuf_obj_list_head);
+	mutex_unlock(&vgpu->dmabuf_lock);
+
+	gvt_dbg_dpy("vgpu%d: %s new dmabuf_obj ref %d, id %d\n", vgpu->id,
+		    __func__, kref_read(&dmabuf_obj->kref), ret);
+
+	return 0;
+
+out_free_info:
+	kfree(dmabuf_obj->info);
+out_free_dmabuf:
+	kfree(dmabuf_obj);
+out:
+	/* ENODEV means plane isn't ready, which might be a normal case. */
+	return (ret == -ENODEV) ? 0 : ret;
+}
+
+/* To associate an exposed dmabuf with the dmabuf_obj */
+int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
+{
+	struct drm_device *dev = &vgpu->gvt->gt->i915->drm;
+	struct intel_vgpu_dmabuf_obj *dmabuf_obj;
+	struct drm_i915_gem_object *obj;
+	struct dma_buf *dmabuf;
+	int dmabuf_fd;
+	int ret = 0;
+
+	mutex_lock(&vgpu->dmabuf_lock);
+
+	dmabuf_obj = pick_dmabuf_by_num(vgpu, dmabuf_id);
+	if (dmabuf_obj == NULL) {
+		gvt_vgpu_err("invalid dmabuf id:%d\n", dmabuf_id);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	obj = vgpu_create_gem(dev, dmabuf_obj->info);
+	if (obj == NULL) {
+		gvt_vgpu_err("create gvt gem obj failed\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	obj->gvt_info = dmabuf_obj->info;
+
+	dmabuf = i915_gem_prime_export(&obj->base, DRM_CLOEXEC | DRM_RDWR);
+	if (IS_ERR(dmabuf)) {
+		gvt_vgpu_err("export dma-buf failed\n");
+		ret = PTR_ERR(dmabuf);
+		goto out_free_gem;
+	}
+
+	ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR);
+	if (ret < 0) {
+		gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret);
+		goto out_free_dmabuf;
+	}
+	dmabuf_fd = ret;
+
+	dmabuf_obj_get(dmabuf_obj);
+
+	if (dmabuf_obj->initref) {
+		dmabuf_obj->initref = false;
+		dmabuf_obj_put(dmabuf_obj);
+	}
+
+	mutex_unlock(&vgpu->dmabuf_lock);
+
+	gvt_dbg_dpy("vgpu%d: dmabuf:%d, dmabuf ref %d, fd:%d\n"
+		    "        file count: %ld, GEM ref: %d\n",
+		    vgpu->id, dmabuf_obj->dmabuf_id,
+		    kref_read(&dmabuf_obj->kref),
+		    dmabuf_fd,
+		    file_count(dmabuf->file),
+		    kref_read(&obj->base.refcount));
+
+	i915_gem_object_put(obj);
+
+	return dmabuf_fd;
+
+out_free_dmabuf:
+	dma_buf_put(dmabuf);
+out_free_gem:
+	i915_gem_object_put(obj);
+out:
+	mutex_unlock(&vgpu->dmabuf_lock);
+	return ret;
+}
+
+void intel_vgpu_dmabuf_cleanup(struct intel_vgpu *vgpu)
+{
+	struct list_head *pos, *n;
+	struct intel_vgpu_dmabuf_obj *dmabuf_obj;
+
+	mutex_lock(&vgpu->dmabuf_lock);
+	list_for_each_safe(pos, n, &vgpu->dmabuf_obj_list_head) {
+		dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
+		dmabuf_obj->vgpu = NULL;
+
+		idr_remove(&vgpu->object_idr, dmabuf_obj->dmabuf_id);
+		list_del(pos);
+
+		/* dmabuf_obj might be freed in dmabuf_obj_put */
+		if (dmabuf_obj->initref) {
+			dmabuf_obj->initref = false;
+			dmabuf_obj_put(dmabuf_obj);
+		}
+
+	}
+	mutex_unlock(&vgpu->dmabuf_lock);
+}