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, 892 insertions, 0 deletions

diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
new file mode 100644
index 000000000..da45215a9
--- /dev/null
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -0,0 +1,892 @@
+/*
+ * Copyright (C) 2015 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * Authors:
+ *    Dave Airlie
+ *    Alon Levy
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <linux/file.h>
+#include <linux/sync_file.h>
+#include <linux/uaccess.h>
+
+#include <drm/drm_file.h>
+#include <drm/virtgpu_drm.h>
+
+#include "virtgpu_drv.h"
+
+#define VIRTGPU_BLOB_FLAG_USE_MASK (VIRTGPU_BLOB_FLAG_USE_MAPPABLE | \
+				    VIRTGPU_BLOB_FLAG_USE_SHAREABLE | \
+				    VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE)
+
+static int virtio_gpu_fence_event_create(struct drm_device *dev,
+					 struct drm_file *file,
+					 struct virtio_gpu_fence *fence,
+					 uint32_t ring_idx)
+{
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+	struct virtio_gpu_fence_event *e = NULL;
+	int ret;
+
+	if (!(vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
+		return 0;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED;
+	e->event.length = sizeof(e->event);
+
+	ret = drm_event_reserve_init(dev, file, &e->base, &e->event);
+	if (ret)
+		goto free;
+
+	fence->e = e;
+	return 0;
+free:
+	kfree(e);
+	return ret;
+}
+
+/* Must be called with &virtio_gpu_fpriv.struct_mutex held. */
+static void virtio_gpu_create_context_locked(struct virtio_gpu_device *vgdev,
+					     struct virtio_gpu_fpriv *vfpriv)
+{
+	char dbgname[TASK_COMM_LEN];
+
+	get_task_comm(dbgname, current);
+	virtio_gpu_cmd_context_create(vgdev, vfpriv->ctx_id,
+				      vfpriv->context_init, strlen(dbgname),
+				      dbgname);
+
+	vfpriv->context_created = true;
+}
+
+void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+
+	mutex_lock(&vfpriv->context_lock);
+	if (vfpriv->context_created)
+		goto out_unlock;
+
+	virtio_gpu_create_context_locked(vgdev, vfpriv);
+
+out_unlock:
+	mutex_unlock(&vfpriv->context_lock);
+}
+
+static int virtio_gpu_map_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct drm_virtgpu_map *virtio_gpu_map = data;
+
+	return virtio_gpu_mode_dumb_mmap(file, vgdev->ddev,
+					 virtio_gpu_map->handle,
+					 &virtio_gpu_map->offset);
+}
+
+/*
+ * Usage of execbuffer:
+ * Relocations need to take into account the full VIRTIO_GPUDrawable size.
+ * However, the command as passed from user space must *not* contain the initial
+ * VIRTIO_GPUReleaseInfo struct (first XXX bytes)
+ */
+static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file)
+{
+	struct drm_virtgpu_execbuffer *exbuf = data;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+	struct virtio_gpu_fence *out_fence;
+	int ret;
+	uint32_t *bo_handles = NULL;
+	void __user *user_bo_handles = NULL;
+	struct virtio_gpu_object_array *buflist = NULL;
+	struct sync_file *sync_file;
+	int out_fence_fd = -1;
+	void *buf;
+	uint64_t fence_ctx;
+	uint32_t ring_idx;
+
+	fence_ctx = vgdev->fence_drv.context;
+	ring_idx = 0;
+
+	if (vgdev->has_virgl_3d == false)
+		return -ENOSYS;
+
+	if ((exbuf->flags & ~VIRTGPU_EXECBUF_FLAGS))
+		return -EINVAL;
+
+	if ((exbuf->flags & VIRTGPU_EXECBUF_RING_IDX)) {
+		if (exbuf->ring_idx >= vfpriv->num_rings)
+			return -EINVAL;
+
+		if (!vfpriv->base_fence_ctx)
+			return -EINVAL;
+
+		fence_ctx = vfpriv->base_fence_ctx;
+		ring_idx = exbuf->ring_idx;
+	}
+
+	virtio_gpu_create_context(dev, file);
+	if (exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_IN) {
+		struct dma_fence *in_fence;
+
+		in_fence = sync_file_get_fence(exbuf->fence_fd);
+
+		if (!in_fence)
+			return -EINVAL;
+
+		/*
+		 * Wait if the fence is from a foreign context, or if the fence
+		 * array contains any fence from a foreign context.
+		 */
+		ret = 0;
+		if (!dma_fence_match_context(in_fence, fence_ctx + ring_idx))
+			ret = dma_fence_wait(in_fence, true);
+
+		dma_fence_put(in_fence);
+		if (ret)
+			return ret;
+	}
+
+	if (exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) {
+		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
+		if (out_fence_fd < 0)
+			return out_fence_fd;
+	}
+
+	if (exbuf->num_bo_handles) {
+		bo_handles = kvmalloc_array(exbuf->num_bo_handles,
+					    sizeof(uint32_t), GFP_KERNEL);
+		if (!bo_handles) {
+			ret = -ENOMEM;
+			goto out_unused_fd;
+		}
+
+		user_bo_handles = u64_to_user_ptr(exbuf->bo_handles);
+		if (copy_from_user(bo_handles, user_bo_handles,
+				   exbuf->num_bo_handles * sizeof(uint32_t))) {
+			ret = -EFAULT;
+			goto out_unused_fd;
+		}
+
+		buflist = virtio_gpu_array_from_handles(file, bo_handles,
+							exbuf->num_bo_handles);
+		if (!buflist) {
+			ret = -ENOENT;
+			goto out_unused_fd;
+		}
+		kvfree(bo_handles);
+		bo_handles = NULL;
+	}
+
+	buf = vmemdup_user(u64_to_user_ptr(exbuf->command), exbuf->size);
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto out_unused_fd;
+	}
+
+	if (buflist) {
+		ret = virtio_gpu_array_lock_resv(buflist);
+		if (ret)
+			goto out_memdup;
+	}
+
+	out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
+	if(!out_fence) {
+		ret = -ENOMEM;
+		goto out_unresv;
+	}
+
+	ret = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
+	if (ret)
+		goto out_unresv;
+
+	if (out_fence_fd >= 0) {
+		sync_file = sync_file_create(&out_fence->f);
+		if (!sync_file) {
+			dma_fence_put(&out_fence->f);
+			ret = -ENOMEM;
+			goto out_unresv;
+		}
+
+		exbuf->fence_fd = out_fence_fd;
+		fd_install(out_fence_fd, sync_file->file);
+	}
+
+	virtio_gpu_cmd_submit(vgdev, buf, exbuf->size,
+			      vfpriv->ctx_id, buflist, out_fence);
+	dma_fence_put(&out_fence->f);
+	virtio_gpu_notify(vgdev);
+	return 0;
+
+out_unresv:
+	if (buflist)
+		virtio_gpu_array_unlock_resv(buflist);
+out_memdup:
+	kvfree(buf);
+out_unused_fd:
+	kvfree(bo_handles);
+	if (buflist)
+		virtio_gpu_array_put_free(buflist);
+
+	if (out_fence_fd >= 0)
+		put_unused_fd(out_fence_fd);
+
+	return ret;
+}
+
+static int virtio_gpu_getparam_ioctl(struct drm_device *dev, void *data,
+				     struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct drm_virtgpu_getparam *param = data;
+	int value;
+
+	switch (param->param) {
+	case VIRTGPU_PARAM_3D_FEATURES:
+		value = vgdev->has_virgl_3d ? 1 : 0;
+		break;
+	case VIRTGPU_PARAM_CAPSET_QUERY_FIX:
+		value = 1;
+		break;
+	case VIRTGPU_PARAM_RESOURCE_BLOB:
+		value = vgdev->has_resource_blob ? 1 : 0;
+		break;
+	case VIRTGPU_PARAM_HOST_VISIBLE:
+		value = vgdev->has_host_visible ? 1 : 0;
+		break;
+	case VIRTGPU_PARAM_CROSS_DEVICE:
+		value = vgdev->has_resource_assign_uuid ? 1 : 0;
+		break;
+	case VIRTGPU_PARAM_CONTEXT_INIT:
+		value = vgdev->has_context_init ? 1 : 0;
+		break;
+	case VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs:
+		value = vgdev->capset_id_mask;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (copy_to_user(u64_to_user_ptr(param->value), &value, sizeof(int)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data,
+					    struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct drm_virtgpu_resource_create *rc = data;
+	struct virtio_gpu_fence *fence;
+	int ret;
+	struct virtio_gpu_object *qobj;
+	struct drm_gem_object *obj;
+	uint32_t handle = 0;
+	struct virtio_gpu_object_params params = { 0 };
+
+	if (vgdev->has_virgl_3d) {
+		virtio_gpu_create_context(dev, file);
+		params.virgl = true;
+		params.target = rc->target;
+		params.bind = rc->bind;
+		params.depth = rc->depth;
+		params.array_size = rc->array_size;
+		params.last_level = rc->last_level;
+		params.nr_samples = rc->nr_samples;
+		params.flags = rc->flags;
+	} else {
+		if (rc->depth > 1)
+			return -EINVAL;
+		if (rc->nr_samples > 1)
+			return -EINVAL;
+		if (rc->last_level > 1)
+			return -EINVAL;
+		if (rc->target != 2)
+			return -EINVAL;
+		if (rc->array_size > 1)
+			return -EINVAL;
+	}
+
+	params.format = rc->format;
+	params.width = rc->width;
+	params.height = rc->height;
+	params.size = rc->size;
+	/* allocate a single page size object */
+	if (params.size == 0)
+		params.size = PAGE_SIZE;
+
+	fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context, 0);
+	if (!fence)
+		return -ENOMEM;
+	ret = virtio_gpu_object_create(vgdev, &params, &qobj, fence);
+	dma_fence_put(&fence->f);
+	if (ret < 0)
+		return ret;
+	obj = &qobj->base.base;
+
+	ret = drm_gem_handle_create(file, obj, &handle);
+	if (ret) {
+		drm_gem_object_release(obj);
+		return ret;
+	}
+
+	rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */
+	rc->bo_handle = handle;
+
+	/*
+	 * The handle owns the reference now.  But we must drop our
+	 * remaining reference *after* we no longer need to dereference
+	 * the obj.  Otherwise userspace could guess the handle and
+	 * race closing it from another thread.
+	 */
+	drm_gem_object_put(obj);
+
+	return 0;
+}
+
+static int virtio_gpu_resource_info_ioctl(struct drm_device *dev, void *data,
+					  struct drm_file *file)
+{
+	struct drm_virtgpu_resource_info *ri = data;
+	struct drm_gem_object *gobj = NULL;
+	struct virtio_gpu_object *qobj = NULL;
+
+	gobj = drm_gem_object_lookup(file, ri->bo_handle);
+	if (gobj == NULL)
+		return -ENOENT;
+
+	qobj = gem_to_virtio_gpu_obj(gobj);
+
+	ri->size = qobj->base.base.size;
+	ri->res_handle = qobj->hw_res_handle;
+	if (qobj->host3d_blob || qobj->guest_blob)
+		ri->blob_mem = qobj->blob_mem;
+
+	drm_gem_object_put(gobj);
+	return 0;
+}
+
+static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev,
+					       void *data,
+					       struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+	struct drm_virtgpu_3d_transfer_from_host *args = data;
+	struct virtio_gpu_object *bo;
+	struct virtio_gpu_object_array *objs;
+	struct virtio_gpu_fence *fence;
+	int ret;
+	u32 offset = args->offset;
+
+	if (vgdev->has_virgl_3d == false)
+		return -ENOSYS;
+
+	virtio_gpu_create_context(dev, file);
+	objs = virtio_gpu_array_from_handles(file, &args->bo_handle, 1);
+	if (objs == NULL)
+		return -ENOENT;
+
+	bo = gem_to_virtio_gpu_obj(objs->objs[0]);
+	if (bo->guest_blob && !bo->host3d_blob) {
+		ret = -EINVAL;
+		goto err_put_free;
+	}
+
+	if (!bo->host3d_blob && (args->stride || args->layer_stride)) {
+		ret = -EINVAL;
+		goto err_put_free;
+	}
+
+	ret = virtio_gpu_array_lock_resv(objs);
+	if (ret != 0)
+		goto err_put_free;
+
+	fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context, 0);
+	if (!fence) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	virtio_gpu_cmd_transfer_from_host_3d
+		(vgdev, vfpriv->ctx_id, offset, args->level, args->stride,
+		 args->layer_stride, &args->box, objs, fence);
+	dma_fence_put(&fence->f);
+	virtio_gpu_notify(vgdev);
+	return 0;
+
+err_unlock:
+	virtio_gpu_array_unlock_resv(objs);
+err_put_free:
+	virtio_gpu_array_put_free(objs);
+	return ret;
+}
+
+static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data,
+					     struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+	struct drm_virtgpu_3d_transfer_to_host *args = data;
+	struct virtio_gpu_object *bo;
+	struct virtio_gpu_object_array *objs;
+	struct virtio_gpu_fence *fence;
+	int ret;
+	u32 offset = args->offset;
+
+	objs = virtio_gpu_array_from_handles(file, &args->bo_handle, 1);
+	if (objs == NULL)
+		return -ENOENT;
+
+	bo = gem_to_virtio_gpu_obj(objs->objs[0]);
+	if (bo->guest_blob && !bo->host3d_blob) {
+		ret = -EINVAL;
+		goto err_put_free;
+	}
+
+	if (!vgdev->has_virgl_3d) {
+		virtio_gpu_cmd_transfer_to_host_2d
+			(vgdev, offset,
+			 args->box.w, args->box.h, args->box.x, args->box.y,
+			 objs, NULL);
+	} else {
+		virtio_gpu_create_context(dev, file);
+
+		if (!bo->host3d_blob && (args->stride || args->layer_stride)) {
+			ret = -EINVAL;
+			goto err_put_free;
+		}
+
+		ret = virtio_gpu_array_lock_resv(objs);
+		if (ret != 0)
+			goto err_put_free;
+
+		ret = -ENOMEM;
+		fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context,
+					       0);
+		if (!fence)
+			goto err_unlock;
+
+		virtio_gpu_cmd_transfer_to_host_3d
+			(vgdev,
+			 vfpriv ? vfpriv->ctx_id : 0, offset, args->level,
+			 args->stride, args->layer_stride, &args->box, objs,
+			 fence);
+		dma_fence_put(&fence->f);
+	}
+	virtio_gpu_notify(vgdev);
+	return 0;
+
+err_unlock:
+	virtio_gpu_array_unlock_resv(objs);
+err_put_free:
+	virtio_gpu_array_put_free(objs);
+	return ret;
+}
+
+static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file)
+{
+	struct drm_virtgpu_3d_wait *args = data;
+	struct drm_gem_object *obj;
+	long timeout = 15 * HZ;
+	int ret;
+
+	obj = drm_gem_object_lookup(file, args->handle);
+	if (obj == NULL)
+		return -ENOENT;
+
+	if (args->flags & VIRTGPU_WAIT_NOWAIT) {
+		ret = dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ);
+	} else {
+		ret = dma_resv_wait_timeout(obj->resv, DMA_RESV_USAGE_READ,
+					    true, timeout);
+	}
+	if (ret == 0)
+		ret = -EBUSY;
+	else if (ret > 0)
+		ret = 0;
+
+	drm_gem_object_put(obj);
+	return ret;
+}
+
+static int virtio_gpu_get_caps_ioctl(struct drm_device *dev,
+				void *data, struct drm_file *file)
+{
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct drm_virtgpu_get_caps *args = data;
+	unsigned size, host_caps_size;
+	int i;
+	int found_valid = -1;
+	int ret;
+	struct virtio_gpu_drv_cap_cache *cache_ent;
+	void *ptr;
+
+	if (vgdev->num_capsets == 0)
+		return -ENOSYS;
+
+	/* don't allow userspace to pass 0 */
+	if (args->size == 0)
+		return -EINVAL;
+
+	spin_lock(&vgdev->display_info_lock);
+	for (i = 0; i < vgdev->num_capsets; i++) {
+		if (vgdev->capsets[i].id == args->cap_set_id) {
+			if (vgdev->capsets[i].max_version >= args->cap_set_ver) {
+				found_valid = i;
+				break;
+			}
+		}
+	}
+
+	if (found_valid == -1) {
+		spin_unlock(&vgdev->display_info_lock);
+		return -EINVAL;
+	}
+
+	host_caps_size = vgdev->capsets[found_valid].max_size;
+	/* only copy to user the minimum of the host caps size or the guest caps size */
+	size = min(args->size, host_caps_size);
+
+	list_for_each_entry(cache_ent, &vgdev->cap_cache, head) {
+		if (cache_ent->id == args->cap_set_id &&
+		    cache_ent->version == args->cap_set_ver) {
+			spin_unlock(&vgdev->display_info_lock);
+			goto copy_exit;
+		}
+	}
+	spin_unlock(&vgdev->display_info_lock);
+
+	/* not in cache - need to talk to hw */
+	ret = virtio_gpu_cmd_get_capset(vgdev, found_valid, args->cap_set_ver,
+					&cache_ent);
+	if (ret)
+		return ret;
+	virtio_gpu_notify(vgdev);
+
+copy_exit:
+	ret = wait_event_timeout(vgdev->resp_wq,
+				 atomic_read(&cache_ent->is_valid), 5 * HZ);
+	if (!ret)
+		return -EBUSY;
+
+	/* is_valid check must proceed before copy of the cache entry. */
+	smp_rmb();
+
+	ptr = cache_ent->caps_cache;
+
+	if (copy_to_user(u64_to_user_ptr(args->addr), ptr, size))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int verify_blob(struct virtio_gpu_device *vgdev,
+		       struct virtio_gpu_fpriv *vfpriv,
+		       struct virtio_gpu_object_params *params,
+		       struct drm_virtgpu_resource_create_blob *rc_blob,
+		       bool *guest_blob, bool *host3d_blob)
+{
+	if (!vgdev->has_resource_blob)
+		return -EINVAL;
+
+	if (rc_blob->blob_flags & ~VIRTGPU_BLOB_FLAG_USE_MASK)
+		return -EINVAL;
+
+	if (rc_blob->blob_flags & VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE) {
+		if (!vgdev->has_resource_assign_uuid)
+			return -EINVAL;
+	}
+
+	switch (rc_blob->blob_mem) {
+	case VIRTGPU_BLOB_MEM_GUEST:
+		*guest_blob = true;
+		break;
+	case VIRTGPU_BLOB_MEM_HOST3D_GUEST:
+		*guest_blob = true;
+		fallthrough;
+	case VIRTGPU_BLOB_MEM_HOST3D:
+		*host3d_blob = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (*host3d_blob) {
+		if (!vgdev->has_virgl_3d)
+			return -EINVAL;
+
+		/* Must be dword aligned. */
+		if (rc_blob->cmd_size % 4 != 0)
+			return -EINVAL;
+
+		params->ctx_id = vfpriv->ctx_id;
+		params->blob_id = rc_blob->blob_id;
+	} else {
+		if (rc_blob->blob_id != 0)
+			return -EINVAL;
+
+		if (rc_blob->cmd_size != 0)
+			return -EINVAL;
+	}
+
+	params->blob_mem = rc_blob->blob_mem;
+	params->size = rc_blob->size;
+	params->blob = true;
+	params->blob_flags = rc_blob->blob_flags;
+	return 0;
+}
+
+static int virtio_gpu_resource_create_blob_ioctl(struct drm_device *dev,
+						 void *data,
+						 struct drm_file *file)
+{
+	int ret = 0;
+	uint32_t handle = 0;
+	bool guest_blob = false;
+	bool host3d_blob = false;
+	struct drm_gem_object *obj;
+	struct virtio_gpu_object *bo;
+	struct virtio_gpu_object_params params = { 0 };
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+	struct drm_virtgpu_resource_create_blob *rc_blob = data;
+
+	if (verify_blob(vgdev, vfpriv, &params, rc_blob,
+			&guest_blob, &host3d_blob))
+		return -EINVAL;
+
+	if (vgdev->has_virgl_3d)
+		virtio_gpu_create_context(dev, file);
+
+	if (rc_blob->cmd_size) {
+		void *buf;
+
+		buf = memdup_user(u64_to_user_ptr(rc_blob->cmd),
+				  rc_blob->cmd_size);
+
+		if (IS_ERR(buf))
+			return PTR_ERR(buf);
+
+		virtio_gpu_cmd_submit(vgdev, buf, rc_blob->cmd_size,
+				      vfpriv->ctx_id, NULL, NULL);
+	}
+
+	if (guest_blob)
+		ret = virtio_gpu_object_create(vgdev, &params, &bo, NULL);
+	else if (!guest_blob && host3d_blob)
+		ret = virtio_gpu_vram_create(vgdev, &params, &bo);
+	else
+		return -EINVAL;
+
+	if (ret < 0)
+		return ret;
+
+	bo->guest_blob = guest_blob;
+	bo->host3d_blob = host3d_blob;
+	bo->blob_mem = rc_blob->blob_mem;
+	bo->blob_flags = rc_blob->blob_flags;
+
+	obj = &bo->base.base;
+	if (params.blob_flags & VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE) {
+		ret = virtio_gpu_resource_assign_uuid(vgdev, bo);
+		if (ret) {
+			drm_gem_object_release(obj);
+			return ret;
+		}
+	}
+
+	ret = drm_gem_handle_create(file, obj, &handle);
+	if (ret) {
+		drm_gem_object_release(obj);
+		return ret;
+	}
+
+	rc_blob->res_handle = bo->hw_res_handle;
+	rc_blob->bo_handle = handle;
+
+	/*
+	 * The handle owns the reference now.  But we must drop our
+	 * remaining reference *after* we no longer need to dereference
+	 * the obj.  Otherwise userspace could guess the handle and
+	 * race closing it from another thread.
+	 */
+	drm_gem_object_put(obj);
+
+	return 0;
+}
+
+static int virtio_gpu_context_init_ioctl(struct drm_device *dev,
+					 void *data, struct drm_file *file)
+{
+	int ret = 0;
+	uint32_t num_params, i, param, value;
+	uint64_t valid_ring_mask;
+	size_t len;
+	struct drm_virtgpu_context_set_param *ctx_set_params = NULL;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+	struct drm_virtgpu_context_init *args = data;
+
+	num_params = args->num_params;
+	len = num_params * sizeof(struct drm_virtgpu_context_set_param);
+
+	if (!vgdev->has_context_init || !vgdev->has_virgl_3d)
+		return -EINVAL;
+
+	/* Number of unique parameters supported at this time. */
+	if (num_params > 3)
+		return -EINVAL;
+
+	ctx_set_params = memdup_user(u64_to_user_ptr(args->ctx_set_params),
+				     len);
+
+	if (IS_ERR(ctx_set_params))
+		return PTR_ERR(ctx_set_params);
+
+	mutex_lock(&vfpriv->context_lock);
+	if (vfpriv->context_created) {
+		ret = -EEXIST;
+		goto out_unlock;
+	}
+
+	for (i = 0; i < num_params; i++) {
+		param = ctx_set_params[i].param;
+		value = ctx_set_params[i].value;
+
+		switch (param) {
+		case VIRTGPU_CONTEXT_PARAM_CAPSET_ID:
+			if (value > MAX_CAPSET_ID) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			if ((vgdev->capset_id_mask & (1ULL << value)) == 0) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			/* Context capset ID already set */
+			if (vfpriv->context_init &
+			    VIRTIO_GPU_CONTEXT_INIT_CAPSET_ID_MASK) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			vfpriv->context_init |= value;
+			break;
+		case VIRTGPU_CONTEXT_PARAM_NUM_RINGS:
+			if (vfpriv->base_fence_ctx) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			if (value > MAX_RINGS) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			vfpriv->base_fence_ctx = dma_fence_context_alloc(value);
+			vfpriv->num_rings = value;
+			break;
+		case VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK:
+			if (vfpriv->ring_idx_mask) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			vfpriv->ring_idx_mask = value;
+			break;
+		default:
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+	}
+
+	if (vfpriv->ring_idx_mask) {
+		valid_ring_mask = 0;
+		for (i = 0; i < vfpriv->num_rings; i++)
+			valid_ring_mask |= 1ULL << i;
+
+		if (~valid_ring_mask & vfpriv->ring_idx_mask) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+	}
+
+	virtio_gpu_create_context_locked(vgdev, vfpriv);
+	virtio_gpu_notify(vgdev);
+
+out_unlock:
+	mutex_unlock(&vfpriv->context_lock);
+	kfree(ctx_set_params);
+	return ret;
+}
+
+struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS] = {
+	DRM_IOCTL_DEF_DRV(VIRTGPU_MAP, virtio_gpu_map_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_EXECBUFFER, virtio_gpu_execbuffer_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_GETPARAM, virtio_gpu_getparam_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_CREATE,
+			  virtio_gpu_resource_create_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_INFO, virtio_gpu_resource_info_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	/* make transfer async to the main ring? - no sure, can we
+	 * thread these in the underlying GL
+	 */
+	DRM_IOCTL_DEF_DRV(VIRTGPU_TRANSFER_FROM_HOST,
+			  virtio_gpu_transfer_from_host_ioctl,
+			  DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VIRTGPU_TRANSFER_TO_HOST,
+			  virtio_gpu_transfer_to_host_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_WAIT, virtio_gpu_wait_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_GET_CAPS, virtio_gpu_get_caps_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_CREATE_BLOB,
+			  virtio_gpu_resource_create_blob_ioctl,
+			  DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF_DRV(VIRTGPU_CONTEXT_INIT, virtio_gpu_context_init_ioctl,
+			  DRM_RENDER_ALLOW),
+};