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, 539 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
new file mode 100644
index 000000000..b0d87c5f5
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
@@ -0,0 +1,539 @@
+/**********************************************************
+ * Copyright 2021 VMware, Inc.
+ * SPDX-License-Identifier: GPL-2.0 OR MIT
+ *
+ * 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 AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ **********************************************************/
+
+#ifndef VMW_SURFACE_CACHE_H
+#define VMW_SURFACE_CACHE_H
+
+#include "device_include/svga3d_surfacedefs.h"
+
+#include <drm/vmwgfx_drm.h>
+
+static inline u32 clamped_umul32(u32 a, u32 b)
+{
+	uint64_t tmp = (uint64_t) a*b;
+	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
+}
+
+/**
+ * vmw_surface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the
+ * given format.
+ */
+static inline const SVGA3dSurfaceDesc *
+vmw_surface_get_desc(SVGA3dSurfaceFormat format)
+{
+	if (format < ARRAY_SIZE(g_SVGA3dSurfaceDescs))
+		return &g_SVGA3dSurfaceDescs[format];
+
+	return &g_SVGA3dSurfaceDescs[SVGA3D_FORMAT_INVALID];
+}
+
+/**
+ * vmw_surface_get_mip_size -  Given a base level size and the mip level,
+ * compute the size of the mip level.
+ */
+static inline struct drm_vmw_size
+vmw_surface_get_mip_size(struct drm_vmw_size base_level, u32 mip_level)
+{
+	struct drm_vmw_size size = {
+		.width = max_t(u32, base_level.width >> mip_level, 1),
+		.height = max_t(u32, base_level.height >> mip_level, 1),
+		.depth = max_t(u32, base_level.depth >> mip_level, 1)
+	};
+
+	return size;
+}
+
+static inline void
+vmw_surface_get_size_in_blocks(const SVGA3dSurfaceDesc *desc,
+				 const struct drm_vmw_size *pixel_size,
+				 SVGA3dSize *block_size)
+{
+	block_size->width = __KERNEL_DIV_ROUND_UP(pixel_size->width,
+						  desc->blockSize.width);
+	block_size->height = __KERNEL_DIV_ROUND_UP(pixel_size->height,
+						   desc->blockSize.height);
+	block_size->depth = __KERNEL_DIV_ROUND_UP(pixel_size->depth,
+						  desc->blockSize.depth);
+}
+
+static inline bool
+vmw_surface_is_planar_surface(const SVGA3dSurfaceDesc *desc)
+{
+	return (desc->blockDesc & SVGA3DBLOCKDESC_PLANAR_YUV) != 0;
+}
+
+static inline u32
+vmw_surface_calculate_pitch(const SVGA3dSurfaceDesc *desc,
+			      const struct drm_vmw_size *size)
+{
+	u32 pitch;
+	SVGA3dSize blocks;
+
+	vmw_surface_get_size_in_blocks(desc, size, &blocks);
+
+	pitch = blocks.width * desc->pitchBytesPerBlock;
+
+	return pitch;
+}
+
+/**
+ * vmw_surface_get_image_buffer_size - Calculates image buffer size.
+ *
+ * Return the number of bytes of buffer space required to store one image of a
+ * surface, optionally using the specified pitch.
+ *
+ * If pitch is zero, it is assumed that rows are tightly packed.
+ *
+ * This function is overflow-safe. If the result would have overflowed, instead
+ * we return MAX_UINT32.
+ */
+static inline u32
+vmw_surface_get_image_buffer_size(const SVGA3dSurfaceDesc *desc,
+				    const struct drm_vmw_size *size,
+				    u32 pitch)
+{
+	SVGA3dSize image_blocks;
+	u32 slice_size, total_size;
+
+	vmw_surface_get_size_in_blocks(desc, size, &image_blocks);
+
+	if (vmw_surface_is_planar_surface(desc)) {
+		total_size = clamped_umul32(image_blocks.width,
+					    image_blocks.height);
+		total_size = clamped_umul32(total_size, image_blocks.depth);
+		total_size = clamped_umul32(total_size, desc->bytesPerBlock);
+		return total_size;
+	}
+
+	if (pitch == 0)
+		pitch = vmw_surface_calculate_pitch(desc, size);
+
+	slice_size = clamped_umul32(image_blocks.height, pitch);
+	total_size = clamped_umul32(slice_size, image_blocks.depth);
+
+	return total_size;
+}
+
+/**
+ * vmw_surface_get_serialized_size - Get the serialized size for the image.
+ */
+static inline u32
+vmw_surface_get_serialized_size(SVGA3dSurfaceFormat format,
+				  struct drm_vmw_size base_level_size,
+				  u32 num_mip_levels,
+				  u32 num_layers)
+{
+	const SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
+	u32 total_size = 0;
+	u32 mip;
+
+	for (mip = 0; mip < num_mip_levels; mip++) {
+		struct drm_vmw_size size =
+			vmw_surface_get_mip_size(base_level_size, mip);
+		total_size += vmw_surface_get_image_buffer_size(desc,
+								  &size, 0);
+	}
+
+	return total_size * num_layers;
+}
+
+/**
+ * vmw_surface_get_serialized_size_extended - Returns the number of bytes
+ * required for a surface with given parameters. Support for sample count.
+ */
+static inline u32
+vmw_surface_get_serialized_size_extended(SVGA3dSurfaceFormat format,
+					   struct drm_vmw_size base_level_size,
+					   u32 num_mip_levels,
+					   u32 num_layers,
+					   u32 num_samples)
+{
+	uint64_t total_size =
+		vmw_surface_get_serialized_size(format,
+						  base_level_size,
+						  num_mip_levels,
+						  num_layers);
+	total_size *= max_t(u32, 1, num_samples);
+
+	return min_t(uint64_t, total_size, (uint64_t)U32_MAX);
+}
+
+/**
+ * vmw_surface_get_pixel_offset - Compute the offset (in bytes) to a pixel
+ * in an image (or volume).
+ *
+ * @width: The image width in pixels.
+ * @height: The image height in pixels
+ */
+static inline u32
+vmw_surface_get_pixel_offset(SVGA3dSurfaceFormat format,
+			       u32 width, u32 height,
+			       u32 x, u32 y, u32 z)
+{
+	const SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
+	const u32 bw = desc->blockSize.width, bh = desc->blockSize.height;
+	const u32 bd = desc->blockSize.depth;
+	const u32 rowstride = __KERNEL_DIV_ROUND_UP(width, bw) *
+			      desc->bytesPerBlock;
+	const u32 imgstride = __KERNEL_DIV_ROUND_UP(height, bh) * rowstride;
+	const u32 offset = (z / bd * imgstride +
+			    y / bh * rowstride +
+			    x / bw * desc->bytesPerBlock);
+	return offset;
+}
+
+static inline u32
+vmw_surface_get_image_offset(SVGA3dSurfaceFormat format,
+			       struct drm_vmw_size baseLevelSize,
+			       u32 numMipLevels,
+			       u32 face,
+			       u32 mip)
+
+{
+	u32 offset;
+	u32 mipChainBytes;
+	u32 mipChainBytesToLevel;
+	u32 i;
+	const SVGA3dSurfaceDesc *desc;
+	struct drm_vmw_size mipSize;
+	u32 bytes;
+
+	desc = vmw_surface_get_desc(format);
+
+	mipChainBytes = 0;
+	mipChainBytesToLevel = 0;
+	for (i = 0; i < numMipLevels; i++) {
+		mipSize = vmw_surface_get_mip_size(baseLevelSize, i);
+		bytes = vmw_surface_get_image_buffer_size(desc, &mipSize, 0);
+		mipChainBytes += bytes;
+		if (i < mip)
+			mipChainBytesToLevel += bytes;
+	}
+
+	offset = mipChainBytes * face + mipChainBytesToLevel;
+
+	return offset;
+}
+
+
+/**
+ * vmw_surface_is_gb_screen_target_format - Is the specified format usable as
+ *                                            a ScreenTarget?
+ *                                            (with just the GBObjects cap-bit
+ *                                             set)
+ * @format: format to queried
+ *
+ * RETURNS:
+ * true if queried format is valid for screen targets
+ */
+static inline bool
+vmw_surface_is_gb_screen_target_format(SVGA3dSurfaceFormat format)
+{
+	return (format == SVGA3D_X8R8G8B8 ||
+		format == SVGA3D_A8R8G8B8 ||
+		format == SVGA3D_R5G6B5   ||
+		format == SVGA3D_X1R5G5B5 ||
+		format == SVGA3D_A1R5G5B5 ||
+		format == SVGA3D_P8);
+}
+
+
+/**
+ * vmw_surface_is_dx_screen_target_format - Is the specified format usable as
+ *                                            a ScreenTarget?
+ *                                            (with DX10 enabled)
+ *
+ * @format: format to queried
+ *
+ * Results:
+ * true if queried format is valid for screen targets
+ */
+static inline bool
+vmw_surface_is_dx_screen_target_format(SVGA3dSurfaceFormat format)
+{
+	return (format == SVGA3D_R8G8B8A8_UNORM ||
+		format == SVGA3D_B8G8R8A8_UNORM ||
+		format == SVGA3D_B8G8R8X8_UNORM);
+}
+
+
+/**
+ * vmw_surface_is_screen_target_format - Is the specified format usable as a
+ *                                         ScreenTarget?
+ *                                         (for some combination of caps)
+ *
+ * @format: format to queried
+ *
+ * Results:
+ * true if queried format is valid for screen targets
+ */
+static inline bool
+vmw_surface_is_screen_target_format(SVGA3dSurfaceFormat format)
+{
+	if (vmw_surface_is_gb_screen_target_format(format)) {
+		return true;
+	}
+	return vmw_surface_is_dx_screen_target_format(format);
+}
+
+/**
+ * struct vmw_surface_mip - Mimpmap level information
+ * @bytes: Bytes required in the backing store of this mipmap level.
+ * @img_stride: Byte stride per image.
+ * @row_stride: Byte stride per block row.
+ * @size: The size of the mipmap.
+ */
+struct vmw_surface_mip {
+	size_t bytes;
+	size_t img_stride;
+	size_t row_stride;
+	struct drm_vmw_size size;
+
+};
+
+/**
+ * struct vmw_surface_cache - Cached surface information
+ * @desc: Pointer to the surface descriptor
+ * @mip: Array of mipmap level information. Valid size is @num_mip_levels.
+ * @mip_chain_bytes: Bytes required in the backing store for the whole chain
+ * of mip levels.
+ * @sheet_bytes: Bytes required in the backing store for a sheet
+ * representing a single sample.
+ * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in
+ * a chain.
+ * @num_layers: Number of slices in an array texture or number of faces in
+ * a cubemap texture.
+ */
+struct vmw_surface_cache {
+	const SVGA3dSurfaceDesc *desc;
+	struct vmw_surface_mip mip[DRM_VMW_MAX_MIP_LEVELS];
+	size_t mip_chain_bytes;
+	size_t sheet_bytes;
+	u32 num_mip_levels;
+	u32 num_layers;
+};
+
+/**
+ * struct vmw_surface_loc - Surface location
+ * @sheet: The multisample sheet.
+ * @sub_resource: Surface subresource. Defined as layer * num_mip_levels +
+ * mip_level.
+ * @x: X coordinate.
+ * @y: Y coordinate.
+ * @z: Z coordinate.
+ */
+struct vmw_surface_loc {
+	u32 sheet;
+	u32 sub_resource;
+	u32 x, y, z;
+};
+
+/**
+ * vmw_surface_subres - Compute the subresource from layer and mipmap.
+ * @cache: Surface layout data.
+ * @mip_level: The mipmap level.
+ * @layer: The surface layer (face or array slice).
+ *
+ * Return: The subresource.
+ */
+static inline u32 vmw_surface_subres(const struct vmw_surface_cache *cache,
+				       u32 mip_level, u32 layer)
+{
+	return cache->num_mip_levels * layer + mip_level;
+}
+
+/**
+ * vmw_surface_setup_cache - Build a surface cache entry
+ * @size: The surface base level dimensions.
+ * @format: The surface format.
+ * @num_mip_levels: Number of mipmap levels.
+ * @num_layers: Number of layers.
+ * @cache: Pointer to a struct vmw_surface_cach object to be filled in.
+ *
+ * Return: Zero on success, -EINVAL on invalid surface layout.
+ */
+static inline int vmw_surface_setup_cache(const struct drm_vmw_size *size,
+					    SVGA3dSurfaceFormat format,
+					    u32 num_mip_levels,
+					    u32 num_layers,
+					    u32 num_samples,
+					    struct vmw_surface_cache *cache)
+{
+	const SVGA3dSurfaceDesc *desc;
+	u32 i;
+
+	memset(cache, 0, sizeof(*cache));
+	cache->desc = desc = vmw_surface_get_desc(format);
+	cache->num_mip_levels = num_mip_levels;
+	cache->num_layers = num_layers;
+	for (i = 0; i < cache->num_mip_levels; i++) {
+		struct vmw_surface_mip *mip = &cache->mip[i];
+
+		mip->size = vmw_surface_get_mip_size(*size, i);
+		mip->bytes = vmw_surface_get_image_buffer_size
+			(desc, &mip->size, 0);
+		mip->row_stride =
+			__KERNEL_DIV_ROUND_UP(mip->size.width,
+					      desc->blockSize.width) *
+			desc->bytesPerBlock * num_samples;
+		if (!mip->row_stride)
+			goto invalid_dim;
+
+		mip->img_stride =
+			__KERNEL_DIV_ROUND_UP(mip->size.height,
+					      desc->blockSize.height) *
+			mip->row_stride;
+		if (!mip->img_stride)
+			goto invalid_dim;
+
+		cache->mip_chain_bytes += mip->bytes;
+	}
+	cache->sheet_bytes = cache->mip_chain_bytes * num_layers;
+	if (!cache->sheet_bytes)
+		goto invalid_dim;
+
+	return 0;
+
+invalid_dim:
+	VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n");
+	return -EINVAL;
+}
+
+/**
+ * vmw_surface_get_loc - Get a surface location from an offset into the
+ * backing store
+ * @cache: Surface layout data.
+ * @loc: Pointer to a struct vmw_surface_loc to be filled in.
+ * @offset: Offset into the surface backing store.
+ */
+static inline void
+vmw_surface_get_loc(const struct vmw_surface_cache *cache,
+		      struct vmw_surface_loc *loc,
+		      size_t offset)
+{
+	const struct vmw_surface_mip *mip = &cache->mip[0];
+	const SVGA3dSurfaceDesc *desc = cache->desc;
+	u32 layer;
+	int i;
+
+	loc->sheet = offset / cache->sheet_bytes;
+	offset -= loc->sheet * cache->sheet_bytes;
+
+	layer = offset / cache->mip_chain_bytes;
+	offset -= layer * cache->mip_chain_bytes;
+	for (i = 0; i < cache->num_mip_levels; ++i, ++mip) {
+		if (mip->bytes > offset)
+			break;
+		offset -= mip->bytes;
+	}
+
+	loc->sub_resource = vmw_surface_subres(cache, i, layer);
+	loc->z = offset / mip->img_stride;
+	offset -= loc->z * mip->img_stride;
+	loc->z *= desc->blockSize.depth;
+	loc->y = offset / mip->row_stride;
+	offset -= loc->y * mip->row_stride;
+	loc->y *= desc->blockSize.height;
+	loc->x = offset / desc->bytesPerBlock;
+	loc->x *= desc->blockSize.width;
+}
+
+/**
+ * vmw_surface_inc_loc - Clamp increment a surface location with one block
+ * size
+ * in each dimension.
+ * @loc: Pointer to a struct vmw_surface_loc to be incremented.
+ *
+ * When computing the size of a range as size = end - start, the range does not
+ * include the end element. However a location representing the last byte
+ * of a touched region in the backing store *is* included in the range.
+ * This function modifies such a location to match the end definition
+ * given as start + size which is the one used in a SVGA3dBox.
+ */
+static inline void
+vmw_surface_inc_loc(const struct vmw_surface_cache *cache,
+		      struct vmw_surface_loc *loc)
+{
+	const SVGA3dSurfaceDesc *desc = cache->desc;
+	u32 mip = loc->sub_resource % cache->num_mip_levels;
+	const struct drm_vmw_size *size = &cache->mip[mip].size;
+
+	loc->sub_resource++;
+	loc->x += desc->blockSize.width;
+	if (loc->x > size->width)
+		loc->x = size->width;
+	loc->y += desc->blockSize.height;
+	if (loc->y > size->height)
+		loc->y = size->height;
+	loc->z += desc->blockSize.depth;
+	if (loc->z > size->depth)
+		loc->z = size->depth;
+}
+
+/**
+ * vmw_surface_min_loc - The start location in a subresource
+ * @cache: Surface layout data.
+ * @sub_resource: The subresource.
+ * @loc: Pointer to a struct vmw_surface_loc to be filled in.
+ */
+static inline void
+vmw_surface_min_loc(const struct vmw_surface_cache *cache,
+		      u32 sub_resource,
+		      struct vmw_surface_loc *loc)
+{
+	loc->sheet = 0;
+	loc->sub_resource = sub_resource;
+	loc->x = loc->y = loc->z = 0;
+}
+
+/**
+ * vmw_surface_min_loc - The end location in a subresource
+ * @cache: Surface layout data.
+ * @sub_resource: The subresource.
+ * @loc: Pointer to a struct vmw_surface_loc to be filled in.
+ *
+ * Following the end definition given in vmw_surface_inc_loc(),
+ * Compute the end location of a surface subresource.
+ */
+static inline void
+vmw_surface_max_loc(const struct vmw_surface_cache *cache,
+		      u32 sub_resource,
+		      struct vmw_surface_loc *loc)
+{
+	const struct drm_vmw_size *size;
+	u32 mip;
+
+	loc->sheet = 0;
+	loc->sub_resource = sub_resource + 1;
+	mip = sub_resource % cache->num_mip_levels;
+	size = &cache->mip[mip].size;
+	loc->x = size->width;
+	loc->y = size->height;
+	loc->z = size->depth;
+}
+
+
+#endif /* VMW_SURFACE_CACHE_H */