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, 854 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
new file mode 100644
index 000000000..4dcf2eb7a
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -0,0 +1,854 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/**************************************************************************
+ *
+ * Copyright © 2011-2018 VMware, Inc., Palo Alto, CA., USA
+ * 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, sub license, 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 NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS 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/ttm/ttm_placement.h>
+
+#include "vmwgfx_drv.h"
+#include "ttm_object.h"
+
+
+/**
+ * vmw_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the
+ * TTM buffer object.
+ */
+static struct vmw_buffer_object *
+vmw_buffer_object(struct ttm_buffer_object *bo)
+{
+	return container_of(bo, struct vmw_buffer_object, base);
+}
+
+/**
+ * bo_is_vmw - check if the buffer object is a &vmw_buffer_object
+ * @bo: ttm buffer object to be checked
+ *
+ * Uses destroy function associated with the object to determine if this is
+ * a &vmw_buffer_object.
+ *
+ * Returns:
+ * true if the object is of &vmw_buffer_object type, false if not.
+ */
+static bool bo_is_vmw(struct ttm_buffer_object *bo)
+{
+	return bo->destroy == &vmw_bo_bo_free ||
+	       bo->destroy == &vmw_gem_destroy;
+}
+
+/**
+ * vmw_bo_pin_in_placement - Validate a buffer to placement.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @placement:  The placement to pin it.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_placement(struct vmw_private *dev_priv,
+			    struct vmw_buffer_object *buf,
+			    struct ttm_placement *placement,
+			    bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->base.pin_count > 0)
+		ret = ttm_resource_compat(bo->resource, placement)
+			? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, placement, &ctx);
+
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err:
+	return ret;
+}
+
+
+/**
+ * vmw_bo_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->base.pin_count > 0) {
+		ret = ttm_resource_compat(bo->resource, &vmw_vram_gmr_placement)
+			? 0 : -EINVAL;
+		goto out_unreserve;
+	}
+
+	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
+	if (likely(ret == 0) || ret == -ERESTARTSYS)
+		goto out_unreserve;
+
+	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
+
+out_unreserve:
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err:
+	return ret;
+}
+
+
+/**
+ * vmw_bo_pin_in_vram - Move a buffer to vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *buf,
+		       bool interruptible)
+{
+	return vmw_bo_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
+				       interruptible);
+}
+
+
+/**
+ * vmw_bo_pin_in_start_of_vram - Move a buffer to start of vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to pin.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *buf,
+				bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	struct ttm_placement placement;
+	struct ttm_place place;
+	int ret = 0;
+
+	place = vmw_vram_placement.placement[0];
+	place.lpfn = PFN_UP(bo->resource->size);
+	placement.num_placement = 1;
+	placement.placement = &place;
+	placement.num_busy_placement = 1;
+	placement.busy_placement = &place;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err_unlock;
+
+	/*
+	 * Is this buffer already in vram but not at the start of it?
+	 * In that case, evict it first because TTM isn't good at handling
+	 * that situation.
+	 */
+	if (bo->resource->mem_type == TTM_PL_VRAM &&
+	    bo->resource->start < PFN_UP(bo->resource->size) &&
+	    bo->resource->start > 0 &&
+	    buf->base.pin_count == 0) {
+		ctx.interruptible = false;
+		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
+	}
+
+	if (buf->base.pin_count > 0)
+		ret = ttm_resource_compat(bo->resource, &placement)
+			? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	/* For some reason we didn't end up at the start of vram */
+	WARN_ON(ret == 0 && bo->resource->start != 0);
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err_unlock:
+
+	return ret;
+}
+
+
+/**
+ * vmw_bo_unpin - Unpin the buffer given buffer, does not move the buffer.
+ *
+ * This function takes the reservation_sem in write mode.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to unpin.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_unpin(struct vmw_private *dev_priv,
+		 struct vmw_buffer_object *buf,
+		 bool interruptible)
+{
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	vmw_bo_pin_reserved(buf, false);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	return ret;
+}
+
+/**
+ * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
+ * of a buffer.
+ *
+ * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
+ * @ptr: SVGAGuestPtr returning the result.
+ */
+void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
+			  SVGAGuestPtr *ptr)
+{
+	if (bo->resource->mem_type == TTM_PL_VRAM) {
+		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
+		ptr->offset = bo->resource->start << PAGE_SHIFT;
+	} else {
+		ptr->gmrId = bo->resource->start;
+		ptr->offset = 0;
+	}
+}
+
+
+/**
+ * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
+ *
+ * @vbo: The buffer object. Must be reserved.
+ * @pin: Whether to pin or unpin.
+ *
+ */
+void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin)
+{
+	struct ttm_operation_ctx ctx = { false, true };
+	struct ttm_place pl;
+	struct ttm_placement placement;
+	struct ttm_buffer_object *bo = &vbo->base;
+	uint32_t old_mem_type = bo->resource->mem_type;
+	int ret;
+
+	dma_resv_assert_held(bo->base.resv);
+
+	if (pin == !!bo->pin_count)
+		return;
+
+	pl.fpfn = 0;
+	pl.lpfn = 0;
+	pl.mem_type = bo->resource->mem_type;
+	pl.flags = bo->resource->placement;
+
+	memset(&placement, 0, sizeof(placement));
+	placement.num_placement = 1;
+	placement.placement = &pl;
+
+	ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	BUG_ON(ret != 0 || bo->resource->mem_type != old_mem_type);
+
+	if (pin)
+		ttm_bo_pin(bo);
+	else
+		ttm_bo_unpin(bo);
+}
+
+/**
+ * vmw_bo_map_and_cache - Map a buffer object and cache the map
+ *
+ * @vbo: The buffer object to map
+ * Return: A kernel virtual address or NULL if mapping failed.
+ *
+ * This function maps a buffer object into the kernel address space, or
+ * returns the virtual kernel address of an already existing map. The virtual
+ * address remains valid as long as the buffer object is pinned or reserved.
+ * The cached map is torn down on either
+ * 1) Buffer object move
+ * 2) Buffer object swapout
+ * 3) Buffer object destruction
+ *
+ */
+void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo)
+{
+	struct ttm_buffer_object *bo = &vbo->base;
+	bool not_used;
+	void *virtual;
+	int ret;
+
+	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
+	if (virtual)
+		return virtual;
+
+	ret = ttm_bo_kmap(bo, 0, PFN_UP(bo->base.size), &vbo->map);
+	if (ret)
+		DRM_ERROR("Buffer object map failed: %d.\n", ret);
+
+	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
+}
+
+
+/**
+ * vmw_bo_unmap - Tear down a cached buffer object map.
+ *
+ * @vbo: The buffer object whose map we are tearing down.
+ *
+ * This function tears down a cached map set up using
+ * vmw_buffer_object_map_and_cache().
+ */
+void vmw_bo_unmap(struct vmw_buffer_object *vbo)
+{
+	if (vbo->map.bo == NULL)
+		return;
+
+	ttm_bo_kunmap(&vbo->map);
+}
+
+
+/**
+ * vmw_bo_bo_free - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+void vmw_bo_bo_free(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	WARN_ON(vmw_bo->dirty);
+	WARN_ON(!RB_EMPTY_ROOT(&vmw_bo->res_tree));
+	vmw_bo_unmap(vmw_bo);
+	drm_gem_object_release(&bo->base);
+	kfree(vmw_bo);
+}
+
+/* default destructor */
+static void vmw_bo_default_destroy(struct ttm_buffer_object *bo)
+{
+	kfree(bo);
+}
+
+/**
+ * vmw_bo_create_kernel - Create a pinned BO for internal kernel use.
+ *
+ * @dev_priv: Pointer to the device private struct
+ * @size: size of the BO we need
+ * @placement: where to put it
+ * @p_bo: resulting BO
+ *
+ * Creates and pin a simple BO for in kernel use.
+ */
+int vmw_bo_create_kernel(struct vmw_private *dev_priv, unsigned long size,
+			 struct ttm_placement *placement,
+			 struct ttm_buffer_object **p_bo)
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = false,
+		.no_wait_gpu = false
+	};
+	struct ttm_buffer_object *bo;
+	struct drm_device *vdev = &dev_priv->drm;
+	int ret;
+
+	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
+	if (unlikely(!bo))
+		return -ENOMEM;
+
+	size = ALIGN(size, PAGE_SIZE);
+
+	drm_gem_private_object_init(vdev, &bo->base, size);
+
+	ret = ttm_bo_init_reserved(&dev_priv->bdev, bo, ttm_bo_type_kernel,
+				   placement, 0, &ctx, NULL, NULL,
+				   vmw_bo_default_destroy);
+	if (unlikely(ret))
+		goto error_free;
+
+	ttm_bo_pin(bo);
+	ttm_bo_unreserve(bo);
+	*p_bo = bo;
+
+	return 0;
+
+error_free:
+	kfree(bo);
+	return ret;
+}
+
+int vmw_bo_create(struct vmw_private *vmw,
+		  size_t size, struct ttm_placement *placement,
+		  bool interruptible, bool pin,
+		  void (*bo_free)(struct ttm_buffer_object *bo),
+		  struct vmw_buffer_object **p_bo)
+{
+	int ret;
+
+	BUG_ON(!bo_free);
+
+	*p_bo = kmalloc(sizeof(**p_bo), GFP_KERNEL);
+	if (unlikely(!*p_bo)) {
+		DRM_ERROR("Failed to allocate a buffer.\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * vmw_bo_init will delete the *p_bo object if it fails
+	 */
+	ret = vmw_bo_init(vmw, *p_bo, size,
+			  placement, interruptible, pin,
+			  bo_free);
+	if (unlikely(ret != 0))
+		goto out_error;
+
+	return ret;
+out_error:
+	*p_bo = NULL;
+	return ret;
+}
+
+/**
+ * vmw_bo_init - Initialize a vmw buffer object
+ *
+ * @dev_priv: Pointer to the device private struct
+ * @vmw_bo: Pointer to the struct vmw_buffer_object to initialize.
+ * @size: Buffer object size in bytes.
+ * @placement: Initial placement.
+ * @interruptible: Whether waits should be performed interruptible.
+ * @pin: If the BO should be created pinned at a fixed location.
+ * @bo_free: The buffer object destructor.
+ * Returns: Zero on success, negative error code on error.
+ *
+ * Note that on error, the code will free the buffer object.
+ */
+int vmw_bo_init(struct vmw_private *dev_priv,
+		struct vmw_buffer_object *vmw_bo,
+		size_t size, struct ttm_placement *placement,
+		bool interruptible, bool pin,
+		void (*bo_free)(struct ttm_buffer_object *bo))
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = interruptible,
+		.no_wait_gpu = false
+	};
+	struct ttm_device *bdev = &dev_priv->bdev;
+	struct drm_device *vdev = &dev_priv->drm;
+	int ret;
+
+	WARN_ON_ONCE(!bo_free);
+	memset(vmw_bo, 0, sizeof(*vmw_bo));
+	BUILD_BUG_ON(TTM_MAX_BO_PRIORITY <= 3);
+	vmw_bo->base.priority = 3;
+	vmw_bo->res_tree = RB_ROOT;
+
+	size = ALIGN(size, PAGE_SIZE);
+	drm_gem_private_object_init(vdev, &vmw_bo->base.base, size);
+
+	ret = ttm_bo_init_reserved(bdev, &vmw_bo->base, ttm_bo_type_device,
+				   placement, 0, &ctx, NULL, NULL, bo_free);
+	if (unlikely(ret)) {
+		return ret;
+	}
+
+	if (pin)
+		ttm_bo_pin(&vmw_bo->base);
+	ttm_bo_unreserve(&vmw_bo->base);
+
+	return 0;
+}
+
+/**
+ * vmw_user_bo_synccpu_grab - Grab a struct vmw_buffer_object for cpu
+ * access, idling previous GPU operations on the buffer and optionally
+ * blocking it for further command submissions.
+ *
+ * @vmw_bo: Pointer to the buffer object being grabbed for CPU access
+ * @flags: Flags indicating how the grab should be performed.
+ * Return: Zero on success, Negative error code on error. In particular,
+ * -EBUSY will be returned if a dontblock operation is requested and the
+ * buffer object is busy, and -ERESTARTSYS will be returned if a wait is
+ * interrupted by a signal.
+ *
+ * A blocking grab will be automatically released when @tfile is closed.
+ */
+static int vmw_user_bo_synccpu_grab(struct vmw_buffer_object *vmw_bo,
+				    uint32_t flags)
+{
+	bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
+	struct ttm_buffer_object *bo = &vmw_bo->base;
+	int ret;
+
+	if (flags & drm_vmw_synccpu_allow_cs) {
+		long lret;
+
+		lret = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_READ,
+					     true, nonblock ? 0 :
+					     MAX_SCHEDULE_TIMEOUT);
+		if (!lret)
+			return -EBUSY;
+		else if (lret < 0)
+			return lret;
+		return 0;
+	}
+
+	ret = ttm_bo_reserve(bo, true, nonblock, NULL);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_bo_wait(bo, true, nonblock);
+	if (likely(ret == 0))
+		atomic_inc(&vmw_bo->cpu_writers);
+
+	ttm_bo_unreserve(bo);
+	if (unlikely(ret != 0))
+		return ret;
+
+	return ret;
+}
+
+/**
+ * vmw_user_bo_synccpu_release - Release a previous grab for CPU access,
+ * and unblock command submission on the buffer if blocked.
+ *
+ * @filp: Identifying the caller.
+ * @handle: Handle identifying the buffer object.
+ * @flags: Flags indicating the type of release.
+ */
+static int vmw_user_bo_synccpu_release(struct drm_file *filp,
+				       uint32_t handle,
+				       uint32_t flags)
+{
+	struct vmw_buffer_object *vmw_bo;
+	int ret = vmw_user_bo_lookup(filp, handle, &vmw_bo);
+
+	if (!ret) {
+		if (!(flags & drm_vmw_synccpu_allow_cs)) {
+			atomic_dec(&vmw_bo->cpu_writers);
+		}
+		ttm_bo_put(&vmw_bo->base);
+	}
+
+	drm_gem_object_put(&vmw_bo->base.base);
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_ioctl - ioctl function implementing the synccpu
+ * functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and calls the
+ * relevant synccpu functions.
+ */
+int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct drm_vmw_synccpu_arg *arg =
+		(struct drm_vmw_synccpu_arg *) data;
+	struct vmw_buffer_object *vbo;
+	int ret;
+
+	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
+	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
+			       drm_vmw_synccpu_dontblock |
+			       drm_vmw_synccpu_allow_cs)) != 0) {
+		DRM_ERROR("Illegal synccpu flags.\n");
+		return -EINVAL;
+	}
+
+	switch (arg->op) {
+	case drm_vmw_synccpu_grab:
+		ret = vmw_user_bo_lookup(file_priv, arg->handle, &vbo);
+		if (unlikely(ret != 0))
+			return ret;
+
+		ret = vmw_user_bo_synccpu_grab(vbo, arg->flags);
+		vmw_bo_unreference(&vbo);
+		drm_gem_object_put(&vbo->base.base);
+		if (unlikely(ret != 0)) {
+			if (ret == -ERESTARTSYS || ret == -EBUSY)
+				return -EBUSY;
+			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	case drm_vmw_synccpu_release:
+		ret = vmw_user_bo_synccpu_release(file_priv,
+						  arg->handle,
+						  arg->flags);
+		if (unlikely(ret != 0)) {
+			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	default:
+		DRM_ERROR("Invalid synccpu operation.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * vmw_bo_unref_ioctl - Generic handle close ioctl.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and closes a
+ * handle to a TTM base object, optionally freeing the object.
+ */
+int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct drm_vmw_unref_dmabuf_arg *arg =
+	    (struct drm_vmw_unref_dmabuf_arg *)data;
+
+	drm_gem_handle_delete(file_priv, arg->handle);
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_lookup - Look up a vmw user buffer object from a handle.
+ *
+ * @filp: The file the handle is registered with.
+ * @handle: The user buffer object handle
+ * @out: Pointer to a where a pointer to the embedded
+ * struct vmw_buffer_object should be placed.
+ * Return: Zero on success, Negative error code on error.
+ *
+ * The vmw buffer object pointer will be refcounted (both ttm and gem)
+ */
+int vmw_user_bo_lookup(struct drm_file *filp,
+		       uint32_t handle,
+		       struct vmw_buffer_object **out)
+{
+	struct drm_gem_object *gobj;
+
+	gobj = drm_gem_object_lookup(filp, handle);
+	if (!gobj) {
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -ESRCH;
+	}
+
+	*out = gem_to_vmw_bo(gobj);
+	ttm_bo_get(&(*out)->base);
+
+	return 0;
+}
+
+/**
+ * vmw_bo_fence_single - Utility function to fence a single TTM buffer
+ *                       object without unreserving it.
+ *
+ * @bo:             Pointer to the struct ttm_buffer_object to fence.
+ * @fence:          Pointer to the fence. If NULL, this function will
+ *                  insert a fence into the command stream..
+ *
+ * Contrary to the ttm_eu version of this function, it takes only
+ * a single buffer object instead of a list, and it also doesn't
+ * unreserve the buffer object, which needs to be done separately.
+ */
+void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+			 struct vmw_fence_obj *fence)
+{
+	struct ttm_device *bdev = bo->bdev;
+	struct vmw_private *dev_priv =
+		container_of(bdev, struct vmw_private, bdev);
+	int ret;
+
+	if (fence == NULL)
+		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
+	else
+		dma_fence_get(&fence->base);
+
+	ret = dma_resv_reserve_fences(bo->base.resv, 1);
+	if (!ret)
+		dma_resv_add_fence(bo->base.resv, &fence->base,
+				   DMA_RESV_USAGE_KERNEL);
+	else
+		/* Last resort fallback when we are OOM */
+		dma_fence_wait(&fence->base, false);
+	dma_fence_put(&fence->base);
+}
+
+
+/**
+ * vmw_dumb_create - Create a dumb kms buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @args: Pointer to a struct drm_mode_create_dumb structure
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm create_dumb functionality.
+ * Note that this is very similar to the vmw_bo_alloc ioctl, except
+ * that the arguments have a different format.
+ */
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_buffer_object *vbo;
+	int cpp = DIV_ROUND_UP(args->bpp, 8);
+	int ret;
+
+	switch (cpp) {
+	case 1: /* DRM_FORMAT_C8 */
+	case 2: /* DRM_FORMAT_RGB565 */
+	case 4: /* DRM_FORMAT_XRGB8888 */
+		break;
+	default:
+		/*
+		 * Dumb buffers don't allow anything else.
+		 * This is tested via IGT's dumb_buffers
+		 */
+		return -EINVAL;
+	}
+
+	args->pitch = args->width * cpp;
+	args->size = ALIGN(args->pitch * args->height, PAGE_SIZE);
+
+	ret = vmw_gem_object_create_with_handle(dev_priv, file_priv,
+						args->size, &args->handle,
+						&vbo);
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_put(&vbo->base.base);
+	return ret;
+}
+
+/**
+ * vmw_bo_swap_notify - swapout notify callback.
+ *
+ * @bo: The buffer object to be swapped out.
+ */
+void vmw_bo_swap_notify(struct ttm_buffer_object *bo)
+{
+	/* Is @bo embedded in a struct vmw_buffer_object? */
+	if (!bo_is_vmw(bo))
+		return;
+
+	/* Kill any cached kernel maps before swapout */
+	vmw_bo_unmap(vmw_buffer_object(bo));
+}
+
+
+/**
+ * vmw_bo_move_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to move.
+ * @mem: The struct ttm_resource indicating to what memory
+ *       region the move is taking place.
+ *
+ * Detaches cached maps and device bindings that require that the
+ * buffer doesn't move.
+ */
+void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			struct ttm_resource *mem)
+{
+	struct vmw_buffer_object *vbo;
+
+	/* Make sure @bo is embedded in a struct vmw_buffer_object? */
+	if (!bo_is_vmw(bo))
+		return;
+
+	vbo = container_of(bo, struct vmw_buffer_object, base);
+
+	/*
+	 * Kill any cached kernel maps before move to or from VRAM.
+	 * With other types of moves, the underlying pages stay the same,
+	 * and the map can be kept.
+	 */
+	if (mem->mem_type == TTM_PL_VRAM || bo->resource->mem_type == TTM_PL_VRAM)
+		vmw_bo_unmap(vbo);
+
+	/*
+	 * If we're moving a backup MOB out of MOB placement, then make sure we
+	 * read back all resource content first, and unbind the MOB from
+	 * the resource.
+	 */
+	if (mem->mem_type != VMW_PL_MOB && bo->resource->mem_type == VMW_PL_MOB)
+		vmw_resource_unbind_list(vbo);
+}