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, 679 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
new file mode 100644
index 000000000..4e3938e62
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -0,0 +1,679 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/**************************************************************************
+ *
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
+ *
+ * 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 "vmwgfx_drv.h"
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_placement.h>
+
+static const struct ttm_place vram_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = TTM_PL_VRAM,
+	.flags = 0
+};
+
+static const struct ttm_place sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = TTM_PL_SYSTEM,
+	.flags = 0
+};
+
+static const struct ttm_place gmr_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = VMW_PL_GMR,
+	.flags = 0
+};
+
+static const struct ttm_place mob_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = VMW_PL_MOB,
+	.flags = 0
+};
+
+struct ttm_placement vmw_vram_placement = {
+	.num_placement = 1,
+	.placement = &vram_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &vram_placement_flags
+};
+
+static const struct ttm_place vram_gmr_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = TTM_PL_VRAM,
+		.flags = 0
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = VMW_PL_GMR,
+		.flags = 0
+	}
+};
+
+static const struct ttm_place gmr_vram_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = VMW_PL_GMR,
+		.flags = 0
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = TTM_PL_VRAM,
+		.flags = 0
+	}
+};
+
+static const struct ttm_place vmw_sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = VMW_PL_SYSTEM,
+	.flags = 0
+};
+
+struct ttm_placement vmw_vram_gmr_placement = {
+	.num_placement = 2,
+	.placement = vram_gmr_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &gmr_placement_flags
+};
+
+struct ttm_placement vmw_vram_sys_placement = {
+	.num_placement = 1,
+	.placement = &vram_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+struct ttm_placement vmw_sys_placement = {
+	.num_placement = 1,
+	.placement = &sys_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+struct ttm_placement vmw_pt_sys_placement = {
+	.num_placement = 1,
+	.placement = &vmw_sys_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &vmw_sys_placement_flags
+};
+
+static const struct ttm_place nonfixed_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = TTM_PL_SYSTEM,
+		.flags = 0
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = VMW_PL_GMR,
+		.flags = 0
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.mem_type = VMW_PL_MOB,
+		.flags = 0
+	}
+};
+
+struct ttm_placement vmw_srf_placement = {
+	.num_placement = 1,
+	.num_busy_placement = 2,
+	.placement = &gmr_placement_flags,
+	.busy_placement = gmr_vram_placement_flags
+};
+
+struct ttm_placement vmw_mob_placement = {
+	.num_placement = 1,
+	.num_busy_placement = 1,
+	.placement = &mob_placement_flags,
+	.busy_placement = &mob_placement_flags
+};
+
+struct ttm_placement vmw_nonfixed_placement = {
+	.num_placement = 3,
+	.placement = nonfixed_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+const size_t vmw_tt_size = sizeof(struct vmw_ttm_tt);
+
+/**
+ * __vmw_piter_non_sg_next: Helper functions to advance
+ * a struct vmw_piter iterator.
+ *
+ * @viter: Pointer to the iterator.
+ *
+ * These functions return false if past the end of the list,
+ * true otherwise. Functions are selected depending on the current
+ * DMA mapping mode.
+ */
+static bool __vmw_piter_non_sg_next(struct vmw_piter *viter)
+{
+	return ++(viter->i) < viter->num_pages;
+}
+
+static bool __vmw_piter_sg_next(struct vmw_piter *viter)
+{
+	bool ret = __vmw_piter_non_sg_next(viter);
+
+	return __sg_page_iter_dma_next(&viter->iter) && ret;
+}
+
+
+static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
+{
+	return viter->addrs[viter->i];
+}
+
+static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter)
+{
+	return sg_page_iter_dma_address(&viter->iter);
+}
+
+
+/**
+ * vmw_piter_start - Initialize a struct vmw_piter.
+ *
+ * @viter: Pointer to the iterator to initialize
+ * @vsgt: Pointer to a struct vmw_sg_table to initialize from
+ * @p_offset: Pointer offset used to update current array position
+ *
+ * Note that we're following the convention of __sg_page_iter_start, so that
+ * the iterator doesn't point to a valid page after initialization; it has
+ * to be advanced one step first.
+ */
+void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
+		     unsigned long p_offset)
+{
+	viter->i = p_offset - 1;
+	viter->num_pages = vsgt->num_pages;
+	viter->pages = vsgt->pages;
+	switch (vsgt->mode) {
+	case vmw_dma_alloc_coherent:
+		viter->next = &__vmw_piter_non_sg_next;
+		viter->dma_address = &__vmw_piter_dma_addr;
+		viter->addrs = vsgt->addrs;
+		break;
+	case vmw_dma_map_populate:
+	case vmw_dma_map_bind:
+		viter->next = &__vmw_piter_sg_next;
+		viter->dma_address = &__vmw_piter_sg_addr;
+		__sg_page_iter_start(&viter->iter.base, vsgt->sgt->sgl,
+				     vsgt->sgt->orig_nents, p_offset);
+		break;
+	default:
+		BUG();
+	}
+}
+
+/**
+ * vmw_ttm_unmap_from_dma - unmap  device addresses previsouly mapped for
+ * TTM pages
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_backend
+ *
+ * Used to free dma mappings previously mapped by vmw_ttm_map_for_dma.
+ */
+static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct device *dev = vmw_tt->dev_priv->drm.dev;
+
+	dma_unmap_sgtable(dev, &vmw_tt->sgt, DMA_BIDIRECTIONAL, 0);
+	vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents;
+}
+
+/**
+ * vmw_ttm_map_for_dma - map TTM pages to get device addresses
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_backend
+ *
+ * This function is used to get device addresses from the kernel DMA layer.
+ * However, it's violating the DMA API in that when this operation has been
+ * performed, it's illegal for the CPU to write to the pages without first
+ * unmapping the DMA mappings, or calling dma_sync_sg_for_cpu(). It is
+ * therefore only legal to call this function if we know that the function
+ * dma_sync_sg_for_cpu() is a NOP, and dma_sync_sg_for_device() is at most
+ * a CPU write buffer flush.
+ */
+static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct device *dev = vmw_tt->dev_priv->drm.dev;
+
+	return dma_map_sgtable(dev, &vmw_tt->sgt, DMA_BIDIRECTIONAL, 0);
+}
+
+/**
+ * vmw_ttm_map_dma - Make sure TTM pages are visible to the device
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_tt
+ *
+ * Select the correct function for and make sure the TTM pages are
+ * visible to the device. Allocate storage for the device mappings.
+ * If a mapping has already been performed, indicated by the storage
+ * pointer being non NULL, the function returns success.
+ */
+static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct vmw_private *dev_priv = vmw_tt->dev_priv;
+	struct vmw_sg_table *vsgt = &vmw_tt->vsgt;
+	int ret = 0;
+
+	if (vmw_tt->mapped)
+		return 0;
+
+	vsgt->mode = dev_priv->map_mode;
+	vsgt->pages = vmw_tt->dma_ttm.pages;
+	vsgt->num_pages = vmw_tt->dma_ttm.num_pages;
+	vsgt->addrs = vmw_tt->dma_ttm.dma_address;
+	vsgt->sgt = NULL;
+
+	switch (dev_priv->map_mode) {
+	case vmw_dma_map_bind:
+	case vmw_dma_map_populate:
+		vsgt->sgt = &vmw_tt->sgt;
+		ret = sg_alloc_table_from_pages_segment(
+			&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
+			(unsigned long)vsgt->num_pages << PAGE_SHIFT,
+			dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL);
+		if (ret)
+			goto out_sg_alloc_fail;
+
+		ret = vmw_ttm_map_for_dma(vmw_tt);
+		if (unlikely(ret != 0))
+			goto out_map_fail;
+
+		break;
+	default:
+		break;
+	}
+
+	vmw_tt->mapped = true;
+	return 0;
+
+out_map_fail:
+	sg_free_table(vmw_tt->vsgt.sgt);
+	vmw_tt->vsgt.sgt = NULL;
+out_sg_alloc_fail:
+	return ret;
+}
+
+/**
+ * vmw_ttm_unmap_dma - Tear down any TTM page device mappings
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_tt
+ *
+ * Tear down any previously set up device DMA mappings and free
+ * any storage space allocated for them. If there are no mappings set up,
+ * this function is a NOP.
+ */
+static void vmw_ttm_unmap_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct vmw_private *dev_priv = vmw_tt->dev_priv;
+
+	if (!vmw_tt->vsgt.sgt)
+		return;
+
+	switch (dev_priv->map_mode) {
+	case vmw_dma_map_bind:
+	case vmw_dma_map_populate:
+		vmw_ttm_unmap_from_dma(vmw_tt);
+		sg_free_table(vmw_tt->vsgt.sgt);
+		vmw_tt->vsgt.sgt = NULL;
+		break;
+	default:
+		break;
+	}
+	vmw_tt->mapped = false;
+}
+
+/**
+ * vmw_bo_sg_table - Return a struct vmw_sg_table object for a
+ * TTM buffer object
+ *
+ * @bo: Pointer to a struct ttm_buffer_object
+ *
+ * Returns a pointer to a struct vmw_sg_table object. The object should
+ * not be freed after use.
+ * Note that for the device addresses to be valid, the buffer object must
+ * either be reserved or pinned.
+ */
+const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo)
+{
+	struct vmw_ttm_tt *vmw_tt =
+		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm);
+
+	return &vmw_tt->vsgt;
+}
+
+
+static int vmw_ttm_bind(struct ttm_device *bdev,
+			struct ttm_tt *ttm, struct ttm_resource *bo_mem)
+{
+	struct vmw_ttm_tt *vmw_be =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm);
+	int ret = 0;
+
+	if (!bo_mem)
+		return -EINVAL;
+
+	if (vmw_be->bound)
+		return 0;
+
+	ret = vmw_ttm_map_dma(vmw_be);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_be->gmr_id = bo_mem->start;
+	vmw_be->mem_type = bo_mem->mem_type;
+
+	switch (bo_mem->mem_type) {
+	case VMW_PL_GMR:
+		ret = vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt,
+				    ttm->num_pages, vmw_be->gmr_id);
+		break;
+	case VMW_PL_MOB:
+		if (unlikely(vmw_be->mob == NULL)) {
+			vmw_be->mob =
+				vmw_mob_create(ttm->num_pages);
+			if (unlikely(vmw_be->mob == NULL))
+				return -ENOMEM;
+		}
+
+		ret = vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob,
+				    &vmw_be->vsgt, ttm->num_pages,
+				    vmw_be->gmr_id);
+		break;
+	case VMW_PL_SYSTEM:
+		/* Nothing to be done for a system bind */
+		break;
+	default:
+		BUG();
+	}
+	vmw_be->bound = true;
+	return ret;
+}
+
+static void vmw_ttm_unbind(struct ttm_device *bdev,
+			   struct ttm_tt *ttm)
+{
+	struct vmw_ttm_tt *vmw_be =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm);
+
+	if (!vmw_be->bound)
+		return;
+
+	switch (vmw_be->mem_type) {
+	case VMW_PL_GMR:
+		vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id);
+		break;
+	case VMW_PL_MOB:
+		vmw_mob_unbind(vmw_be->dev_priv, vmw_be->mob);
+		break;
+	case VMW_PL_SYSTEM:
+		break;
+	default:
+		BUG();
+	}
+
+	if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind)
+		vmw_ttm_unmap_dma(vmw_be);
+	vmw_be->bound = false;
+}
+
+
+static void vmw_ttm_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
+{
+	struct vmw_ttm_tt *vmw_be =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm);
+
+	vmw_ttm_unmap_dma(vmw_be);
+	ttm_tt_fini(ttm);
+	if (vmw_be->mob)
+		vmw_mob_destroy(vmw_be->mob);
+
+	kfree(vmw_be);
+}
+
+
+static int vmw_ttm_populate(struct ttm_device *bdev,
+			    struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+{
+	int ret;
+
+	/* TODO: maybe completely drop this ? */
+	if (ttm_tt_is_populated(ttm))
+		return 0;
+
+	ret = ttm_pool_alloc(&bdev->pool, ttm, ctx);
+
+	return ret;
+}
+
+static void vmw_ttm_unpopulate(struct ttm_device *bdev,
+			       struct ttm_tt *ttm)
+{
+	struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
+						 dma_ttm);
+
+	vmw_ttm_unbind(bdev, ttm);
+
+	if (vmw_tt->mob) {
+		vmw_mob_destroy(vmw_tt->mob);
+		vmw_tt->mob = NULL;
+	}
+
+	vmw_ttm_unmap_dma(vmw_tt);
+
+	ttm_pool_free(&bdev->pool, ttm);
+}
+
+static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
+					uint32_t page_flags)
+{
+	struct vmw_ttm_tt *vmw_be;
+	int ret;
+
+	vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL);
+	if (!vmw_be)
+		return NULL;
+
+	vmw_be->dev_priv = container_of(bo->bdev, struct vmw_private, bdev);
+	vmw_be->mob = NULL;
+
+	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
+		ret = ttm_sg_tt_init(&vmw_be->dma_ttm, bo, page_flags,
+				     ttm_cached);
+	else
+		ret = ttm_tt_init(&vmw_be->dma_ttm, bo, page_flags,
+				  ttm_cached, 0);
+	if (unlikely(ret != 0))
+		goto out_no_init;
+
+	return &vmw_be->dma_ttm;
+out_no_init:
+	kfree(vmw_be);
+	return NULL;
+}
+
+static void vmw_evict_flags(struct ttm_buffer_object *bo,
+		     struct ttm_placement *placement)
+{
+	*placement = vmw_sys_placement;
+}
+
+static int vmw_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem)
+{
+	struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev);
+
+	switch (mem->mem_type) {
+	case TTM_PL_SYSTEM:
+	case VMW_PL_SYSTEM:
+	case VMW_PL_GMR:
+	case VMW_PL_MOB:
+		return 0;
+	case TTM_PL_VRAM:
+		mem->bus.offset = (mem->start << PAGE_SHIFT) +
+			dev_priv->vram_start;
+		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_cached;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * vmw_move_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to move.
+ * @old_mem: The old memory where we move from
+ * @new_mem: The struct ttm_resource indicating to what memory
+ *       region the move is taking place.
+ *
+ * Calls move_notify for all subsystems needing it.
+ * (currently only resources).
+ */
+static void vmw_move_notify(struct ttm_buffer_object *bo,
+			    struct ttm_resource *old_mem,
+			    struct ttm_resource *new_mem)
+{
+	vmw_bo_move_notify(bo, new_mem);
+	vmw_query_move_notify(bo, old_mem, new_mem);
+}
+
+
+/**
+ * vmw_swap_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to be swapped out.
+ */
+static void vmw_swap_notify(struct ttm_buffer_object *bo)
+{
+	vmw_bo_swap_notify(bo);
+	(void) ttm_bo_wait(bo, false, false);
+}
+
+static bool vmw_memtype_is_system(uint32_t mem_type)
+{
+	return mem_type == TTM_PL_SYSTEM || mem_type == VMW_PL_SYSTEM;
+}
+
+static int vmw_move(struct ttm_buffer_object *bo,
+		    bool evict,
+		    struct ttm_operation_ctx *ctx,
+		    struct ttm_resource *new_mem,
+		    struct ttm_place *hop)
+{
+	struct ttm_resource_manager *old_man = ttm_manager_type(bo->bdev, bo->resource->mem_type);
+	struct ttm_resource_manager *new_man = ttm_manager_type(bo->bdev, new_mem->mem_type);
+	int ret;
+
+	if (new_man->use_tt && !vmw_memtype_is_system(new_mem->mem_type)) {
+		ret = vmw_ttm_bind(bo->bdev, bo->ttm, new_mem);
+		if (ret)
+			return ret;
+	}
+
+	vmw_move_notify(bo, bo->resource, new_mem);
+
+	if (old_man->use_tt && new_man->use_tt) {
+		if (vmw_memtype_is_system(bo->resource->mem_type)) {
+			ttm_bo_move_null(bo, new_mem);
+			return 0;
+		}
+		ret = ttm_bo_wait_ctx(bo, ctx);
+		if (ret)
+			goto fail;
+
+		vmw_ttm_unbind(bo->bdev, bo->ttm);
+		ttm_resource_free(bo, &bo->resource);
+		ttm_bo_assign_mem(bo, new_mem);
+		return 0;
+	} else {
+		ret = ttm_bo_move_memcpy(bo, ctx, new_mem);
+		if (ret)
+			goto fail;
+	}
+	return 0;
+fail:
+	vmw_move_notify(bo, new_mem, bo->resource);
+	return ret;
+}
+
+struct ttm_device_funcs vmw_bo_driver = {
+	.ttm_tt_create = &vmw_ttm_tt_create,
+	.ttm_tt_populate = &vmw_ttm_populate,
+	.ttm_tt_unpopulate = &vmw_ttm_unpopulate,
+	.ttm_tt_destroy = &vmw_ttm_destroy,
+	.eviction_valuable = ttm_bo_eviction_valuable,
+	.evict_flags = vmw_evict_flags,
+	.move = vmw_move,
+	.swap_notify = vmw_swap_notify,
+	.io_mem_reserve = &vmw_ttm_io_mem_reserve,
+};
+
+int vmw_bo_create_and_populate(struct vmw_private *dev_priv,
+			       unsigned long bo_size,
+			       struct ttm_buffer_object **bo_p)
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = false,
+		.no_wait_gpu = false
+	};
+	struct ttm_buffer_object *bo;
+	int ret;
+
+	ret = vmw_bo_create_kernel(dev_priv, bo_size,
+				   &vmw_pt_sys_placement,
+				   &bo);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_bo_reserve(bo, false, true, NULL);
+	BUG_ON(ret != 0);
+	ret = vmw_ttm_populate(bo->bdev, bo->ttm, &ctx);
+	if (likely(ret == 0)) {
+		struct vmw_ttm_tt *vmw_tt =
+			container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm);
+		ret = vmw_ttm_map_dma(vmw_tt);
+	}
+
+	ttm_bo_unreserve(bo);
+
+	if (likely(ret == 0))
+		*bo_p = bo;
+	return ret;
+}