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, 509 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
new file mode 100644
index 000000000..c52c7bf14
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/**************************************************************************
+ *
+ * Copyright 2017 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 "vmwgfx_drv.h"
+#include <linux/highmem.h>
+
+/*
+ * Template that implements find_first_diff() for a generic
+ * unsigned integer type. @size and return value are in bytes.
+ */
+#define VMW_FIND_FIRST_DIFF(_type)			 \
+static size_t vmw_find_first_diff_ ## _type		 \
+	(const _type * dst, const _type * src, size_t size)\
+{							 \
+	size_t i;					 \
+							 \
+	for (i = 0; i < size; i += sizeof(_type)) {	 \
+		if (*dst++ != *src++)			 \
+			break;				 \
+	}						 \
+							 \
+	return i;					 \
+}
+
+
+/*
+ * Template that implements find_last_diff() for a generic
+ * unsigned integer type. Pointers point to the item following the
+ * *end* of the area to be examined. @size and return value are in
+ * bytes.
+ */
+#define VMW_FIND_LAST_DIFF(_type)					\
+static ssize_t vmw_find_last_diff_ ## _type(				\
+	const _type * dst, const _type * src, size_t size)		\
+{									\
+	while (size) {							\
+		if (*--dst != *--src)					\
+			break;						\
+									\
+		size -= sizeof(_type);					\
+	}								\
+	return size;							\
+}
+
+
+/*
+ * Instantiate find diff functions for relevant unsigned integer sizes,
+ * assuming that wider integers are faster (including aligning) up to the
+ * architecture native width, which is assumed to be 32 bit unless
+ * CONFIG_64BIT is defined.
+ */
+VMW_FIND_FIRST_DIFF(u8);
+VMW_FIND_LAST_DIFF(u8);
+
+VMW_FIND_FIRST_DIFF(u16);
+VMW_FIND_LAST_DIFF(u16);
+
+VMW_FIND_FIRST_DIFF(u32);
+VMW_FIND_LAST_DIFF(u32);
+
+#ifdef CONFIG_64BIT
+VMW_FIND_FIRST_DIFF(u64);
+VMW_FIND_LAST_DIFF(u64);
+#endif
+
+
+/* We use size aligned copies. This computes (addr - align(addr)) */
+#define SPILL(_var, _type) ((unsigned long) _var & (sizeof(_type) - 1))
+
+
+/*
+ * Template to compute find_first_diff() for a certain integer type
+ * including a head copy for alignment, and adjustment of parameters
+ * for tail find or increased resolution find using an unsigned integer find
+ * of smaller width. If finding is complete, and resolution is sufficient,
+ * the macro executes a return statement. Otherwise it falls through.
+ */
+#define VMW_TRY_FIND_FIRST_DIFF(_type)					\
+do {									\
+	unsigned int spill = SPILL(dst, _type);				\
+	size_t diff_offs;						\
+									\
+	if (spill && spill == SPILL(src, _type) &&			\
+	    sizeof(_type) - spill <= size) {				\
+		spill = sizeof(_type) - spill;				\
+		diff_offs = vmw_find_first_diff_u8(dst, src, spill);	\
+		if (diff_offs < spill)					\
+			return round_down(offset + diff_offs, granularity); \
+									\
+		dst += spill;						\
+		src += spill;						\
+		size -= spill;						\
+		offset += spill;					\
+		spill = 0;						\
+	}								\
+	if (!spill && !SPILL(src, _type)) {				\
+		size_t to_copy = size &	 ~(sizeof(_type) - 1);		\
+									\
+		diff_offs = vmw_find_first_diff_ ## _type		\
+			((_type *) dst, (_type *) src, to_copy);	\
+		if (diff_offs >= size || granularity == sizeof(_type))	\
+			return (offset + diff_offs);			\
+									\
+		dst += diff_offs;					\
+		src += diff_offs;					\
+		size -= diff_offs;					\
+		offset += diff_offs;					\
+	}								\
+} while (0)								\
+
+
+/**
+ * vmw_find_first_diff - find the first difference between dst and src
+ *
+ * @dst: The destination address
+ * @src: The source address
+ * @size: Number of bytes to compare
+ * @granularity: The granularity needed for the return value in bytes.
+ * return: The offset from find start where the first difference was
+ * encountered in bytes. If no difference was found, the function returns
+ * a value >= @size.
+ */
+static size_t vmw_find_first_diff(const u8 *dst, const u8 *src, size_t size,
+				  size_t granularity)
+{
+	size_t offset = 0;
+
+	/*
+	 * Try finding with large integers if alignment allows, or we can
+	 * fix it. Fall through if we need better resolution or alignment
+	 * was bad.
+	 */
+#ifdef CONFIG_64BIT
+	VMW_TRY_FIND_FIRST_DIFF(u64);
+#endif
+	VMW_TRY_FIND_FIRST_DIFF(u32);
+	VMW_TRY_FIND_FIRST_DIFF(u16);
+
+	return round_down(offset + vmw_find_first_diff_u8(dst, src, size),
+			  granularity);
+}
+
+
+/*
+ * Template to compute find_last_diff() for a certain integer type
+ * including a tail copy for alignment, and adjustment of parameters
+ * for head find or increased resolution find using an unsigned integer find
+ * of smaller width. If finding is complete, and resolution is sufficient,
+ * the macro executes a return statement. Otherwise it falls through.
+ */
+#define VMW_TRY_FIND_LAST_DIFF(_type)					\
+do {									\
+	unsigned int spill = SPILL(dst, _type);				\
+	ssize_t location;						\
+	ssize_t diff_offs;						\
+									\
+	if (spill && spill <= size && spill == SPILL(src, _type)) {	\
+		diff_offs = vmw_find_last_diff_u8(dst, src, spill);	\
+		if (diff_offs) {					\
+			location = size - spill + diff_offs - 1;	\
+			return round_down(location, granularity);	\
+		}							\
+									\
+		dst -= spill;						\
+		src -= spill;						\
+		size -= spill;						\
+		spill = 0;						\
+	}								\
+	if (!spill && !SPILL(src, _type)) {				\
+		size_t to_copy = round_down(size, sizeof(_type));	\
+									\
+		diff_offs = vmw_find_last_diff_ ## _type		\
+			((_type *) dst, (_type *) src, to_copy);	\
+		location = size - to_copy + diff_offs - sizeof(_type);	\
+		if (location < 0 || granularity == sizeof(_type))	\
+			return location;				\
+									\
+		dst -= to_copy - diff_offs;				\
+		src -= to_copy - diff_offs;				\
+		size -= to_copy - diff_offs;				\
+	}								\
+} while (0)
+
+
+/**
+ * vmw_find_last_diff - find the last difference between dst and src
+ *
+ * @dst: The destination address
+ * @src: The source address
+ * @size: Number of bytes to compare
+ * @granularity: The granularity needed for the return value in bytes.
+ * return: The offset from find start where the last difference was
+ * encountered in bytes, or a negative value if no difference was found.
+ */
+static ssize_t vmw_find_last_diff(const u8 *dst, const u8 *src, size_t size,
+				  size_t granularity)
+{
+	dst += size;
+	src += size;
+
+#ifdef CONFIG_64BIT
+	VMW_TRY_FIND_LAST_DIFF(u64);
+#endif
+	VMW_TRY_FIND_LAST_DIFF(u32);
+	VMW_TRY_FIND_LAST_DIFF(u16);
+
+	return round_down(vmw_find_last_diff_u8(dst, src, size) - 1,
+			  granularity);
+}
+
+
+/**
+ * vmw_memcpy - A wrapper around kernel memcpy with allowing to plug it into a
+ * struct vmw_diff_cpy.
+ *
+ * @diff: The struct vmw_diff_cpy closure argument (unused).
+ * @dest: The copy destination.
+ * @src: The copy source.
+ * @n: Number of bytes to copy.
+ */
+void vmw_memcpy(struct vmw_diff_cpy *diff, u8 *dest, const u8 *src, size_t n)
+{
+	memcpy(dest, src, n);
+}
+
+
+/**
+ * vmw_adjust_rect - Adjust rectangle coordinates for newly found difference
+ *
+ * @diff: The struct vmw_diff_cpy used to track the modified bounding box.
+ * @diff_offs: The offset from @diff->line_offset where the difference was
+ * found.
+ */
+static void vmw_adjust_rect(struct vmw_diff_cpy *diff, size_t diff_offs)
+{
+	size_t offs = (diff_offs + diff->line_offset) / diff->cpp;
+	struct drm_rect *rect = &diff->rect;
+
+	rect->x1 = min_t(int, rect->x1, offs);
+	rect->x2 = max_t(int, rect->x2, offs + 1);
+	rect->y1 = min_t(int, rect->y1, diff->line);
+	rect->y2 = max_t(int, rect->y2, diff->line + 1);
+}
+
+/**
+ * vmw_diff_memcpy - memcpy that creates a bounding box of modified content.
+ *
+ * @diff: The struct vmw_diff_cpy used to track the modified bounding box.
+ * @dest: The copy destination.
+ * @src: The copy source.
+ * @n: Number of bytes to copy.
+ *
+ * In order to correctly track the modified content, the field @diff->line must
+ * be pre-loaded with the current line number, the field @diff->line_offset must
+ * be pre-loaded with the line offset in bytes where the copy starts, and
+ * finally the field @diff->cpp need to be preloaded with the number of bytes
+ * per unit in the horizontal direction of the area we're examining.
+ * Typically bytes per pixel.
+ * This is needed to know the needed granularity of the difference computing
+ * operations. A higher cpp generally leads to faster execution at the cost of
+ * bounding box width precision.
+ */
+void vmw_diff_memcpy(struct vmw_diff_cpy *diff, u8 *dest, const u8 *src,
+		     size_t n)
+{
+	ssize_t csize, byte_len;
+
+	if (WARN_ON_ONCE(round_down(n, diff->cpp) != n))
+		return;
+
+	/* TODO: Possibly use a single vmw_find_first_diff per line? */
+	csize = vmw_find_first_diff(dest, src, n, diff->cpp);
+	if (csize < n) {
+		vmw_adjust_rect(diff, csize);
+		byte_len = diff->cpp;
+
+		/*
+		 * Starting from where first difference was found, find
+		 * location of last difference, and then copy.
+		 */
+		diff->line_offset += csize;
+		dest += csize;
+		src += csize;
+		n -= csize;
+		csize = vmw_find_last_diff(dest, src, n, diff->cpp);
+		if (csize >= 0) {
+			byte_len += csize;
+			vmw_adjust_rect(diff, csize);
+		}
+		memcpy(dest, src, byte_len);
+	}
+	diff->line_offset += n;
+}
+
+/**
+ * struct vmw_bo_blit_line_data - Convenience argument to vmw_bo_cpu_blit_line
+ *
+ * @mapped_dst: Already mapped destination page index in @dst_pages.
+ * @dst_addr: Kernel virtual address of mapped destination page.
+ * @dst_pages: Array of destination bo pages.
+ * @dst_num_pages: Number of destination bo pages.
+ * @dst_prot: Destination bo page protection.
+ * @mapped_src: Already mapped source page index in @dst_pages.
+ * @src_addr: Kernel virtual address of mapped source page.
+ * @src_pages: Array of source bo pages.
+ * @src_num_pages: Number of source bo pages.
+ * @src_prot: Source bo page protection.
+ * @diff: Struct vmw_diff_cpy, in the end forwarded to the memcpy routine.
+ */
+struct vmw_bo_blit_line_data {
+	u32 mapped_dst;
+	u8 *dst_addr;
+	struct page **dst_pages;
+	u32 dst_num_pages;
+	pgprot_t dst_prot;
+	u32 mapped_src;
+	u8 *src_addr;
+	struct page **src_pages;
+	u32 src_num_pages;
+	pgprot_t src_prot;
+	struct vmw_diff_cpy *diff;
+};
+
+/**
+ * vmw_bo_cpu_blit_line - Blit part of a line from one bo to another.
+ *
+ * @d: Blit data as described above.
+ * @dst_offset: Destination copy start offset from start of bo.
+ * @src_offset: Source copy start offset from start of bo.
+ * @bytes_to_copy: Number of bytes to copy in this line.
+ */
+static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
+				u32 dst_offset,
+				u32 src_offset,
+				u32 bytes_to_copy)
+{
+	struct vmw_diff_cpy *diff = d->diff;
+
+	while (bytes_to_copy) {
+		u32 copy_size = bytes_to_copy;
+		u32 dst_page = dst_offset >> PAGE_SHIFT;
+		u32 src_page = src_offset >> PAGE_SHIFT;
+		u32 dst_page_offset = dst_offset & ~PAGE_MASK;
+		u32 src_page_offset = src_offset & ~PAGE_MASK;
+		bool unmap_dst = d->dst_addr && dst_page != d->mapped_dst;
+		bool unmap_src = d->src_addr && (src_page != d->mapped_src ||
+						 unmap_dst);
+
+		copy_size = min_t(u32, copy_size, PAGE_SIZE - dst_page_offset);
+		copy_size = min_t(u32, copy_size, PAGE_SIZE - src_page_offset);
+
+		if (unmap_src) {
+			kunmap_atomic(d->src_addr);
+			d->src_addr = NULL;
+		}
+
+		if (unmap_dst) {
+			kunmap_atomic(d->dst_addr);
+			d->dst_addr = NULL;
+		}
+
+		if (!d->dst_addr) {
+			if (WARN_ON_ONCE(dst_page >= d->dst_num_pages))
+				return -EINVAL;
+
+			d->dst_addr =
+				kmap_atomic_prot(d->dst_pages[dst_page],
+						 d->dst_prot);
+			if (!d->dst_addr)
+				return -ENOMEM;
+
+			d->mapped_dst = dst_page;
+		}
+
+		if (!d->src_addr) {
+			if (WARN_ON_ONCE(src_page >= d->src_num_pages))
+				return -EINVAL;
+
+			d->src_addr =
+				kmap_atomic_prot(d->src_pages[src_page],
+						 d->src_prot);
+			if (!d->src_addr)
+				return -ENOMEM;
+
+			d->mapped_src = src_page;
+		}
+		diff->do_cpy(diff, d->dst_addr + dst_page_offset,
+			     d->src_addr + src_page_offset, copy_size);
+
+		bytes_to_copy -= copy_size;
+		dst_offset += copy_size;
+		src_offset += copy_size;
+	}
+
+	return 0;
+}
+
+/**
+ * vmw_bo_cpu_blit - in-kernel cpu blit.
+ *
+ * @dst: Destination buffer object.
+ * @dst_offset: Destination offset of blit start in bytes.
+ * @dst_stride: Destination stride in bytes.
+ * @src: Source buffer object.
+ * @src_offset: Source offset of blit start in bytes.
+ * @src_stride: Source stride in bytes.
+ * @w: Width of blit.
+ * @h: Height of blit.
+ * @diff: The struct vmw_diff_cpy used to track the modified bounding box.
+ * return: Zero on success. Negative error value on failure. Will print out
+ * kernel warnings on caller bugs.
+ *
+ * Performs a CPU blit from one buffer object to another avoiding a full
+ * bo vmap which may exhaust- or fragment vmalloc space.
+ * On supported architectures (x86), we're using kmap_atomic which avoids
+ * cross-processor TLB- and cache flushes and may, on non-HIGHMEM systems
+ * reference already set-up mappings.
+ *
+ * Neither of the buffer objects may be placed in PCI memory
+ * (Fixed memory in TTM terminology) when using this function.
+ */
+int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
+		    u32 dst_offset, u32 dst_stride,
+		    struct ttm_buffer_object *src,
+		    u32 src_offset, u32 src_stride,
+		    u32 w, u32 h,
+		    struct vmw_diff_cpy *diff)
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = false,
+		.no_wait_gpu = false
+	};
+	u32 j, initial_line = dst_offset / dst_stride;
+	struct vmw_bo_blit_line_data d;
+	int ret = 0;
+
+	/* Buffer objects need to be either pinned or reserved: */
+	if (!(dst->pin_count))
+		dma_resv_assert_held(dst->base.resv);
+	if (!(src->pin_count))
+		dma_resv_assert_held(src->base.resv);
+
+	if (!ttm_tt_is_populated(dst->ttm)) {
+		ret = dst->bdev->funcs->ttm_tt_populate(dst->bdev, dst->ttm, &ctx);
+		if (ret)
+			return ret;
+	}
+
+	if (!ttm_tt_is_populated(src->ttm)) {
+		ret = src->bdev->funcs->ttm_tt_populate(src->bdev, src->ttm, &ctx);
+		if (ret)
+			return ret;
+	}
+
+	d.mapped_dst = 0;
+	d.mapped_src = 0;
+	d.dst_addr = NULL;
+	d.src_addr = NULL;
+	d.dst_pages = dst->ttm->pages;
+	d.src_pages = src->ttm->pages;
+	d.dst_num_pages = PFN_UP(dst->resource->size);
+	d.src_num_pages = PFN_UP(src->resource->size);
+	d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL);
+	d.src_prot = ttm_io_prot(src, src->resource, PAGE_KERNEL);
+	d.diff = diff;
+
+	for (j = 0; j < h; ++j) {
+		diff->line = j + initial_line;
+		diff->line_offset = dst_offset % dst_stride;
+		ret = vmw_bo_cpu_blit_line(&d, dst_offset, src_offset, w);
+		if (ret)
+			goto out;
+
+		dst_offset += dst_stride;
+		src_offset += src_stride;
+	}
+out:
+	if (d.src_addr)
+		kunmap_atomic(d.src_addr);
+	if (d.dst_addr)
+		kunmap_atomic(d.dst_addr);
+
+	return ret;
+}