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, 471 insertions, 0 deletions

diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
new file mode 100644
index 000000000..bd515ad4f
--- /dev/null
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -0,0 +1,471 @@
+/*
+ * Copyright 2010 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "radeon_trace.h"
+#include "ni.h"
+#include "nid.h"
+
+/*
+ * DMA
+ * Starting with R600, the GPU has an asynchronous
+ * DMA engine.  The programming model is very similar
+ * to the 3D engine (ring buffer, IBs, etc.), but the
+ * DMA controller has it's own packet format that is
+ * different form the PM4 format used by the 3D engine.
+ * It supports copying data, writing embedded data,
+ * solid fills, and a number of other things.  It also
+ * has support for tiling/detiling of buffers.
+ * Cayman and newer support two asynchronous DMA engines.
+ */
+
+/**
+ * cayman_dma_get_rptr - get the current read pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Get the current rptr from the hardware (cayman+).
+ */
+uint32_t cayman_dma_get_rptr(struct radeon_device *rdev,
+			     struct radeon_ring *ring)
+{
+	u32 rptr, reg;
+
+	if (rdev->wb.enabled) {
+		rptr = rdev->wb.wb[ring->rptr_offs/4];
+	} else {
+		if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+			reg = DMA_RB_RPTR + DMA0_REGISTER_OFFSET;
+		else
+			reg = DMA_RB_RPTR + DMA1_REGISTER_OFFSET;
+
+		rptr = RREG32(reg);
+	}
+
+	return (rptr & 0x3fffc) >> 2;
+}
+
+/**
+ * cayman_dma_get_wptr - get the current write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Get the current wptr from the hardware (cayman+).
+ */
+uint32_t cayman_dma_get_wptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	u32 reg;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		reg = DMA_RB_WPTR + DMA0_REGISTER_OFFSET;
+	else
+		reg = DMA_RB_WPTR + DMA1_REGISTER_OFFSET;
+
+	return (RREG32(reg) & 0x3fffc) >> 2;
+}
+
+/**
+ * cayman_dma_set_wptr - commit the write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Write the wptr back to the hardware (cayman+).
+ */
+void cayman_dma_set_wptr(struct radeon_device *rdev,
+			 struct radeon_ring *ring)
+{
+	u32 reg;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		reg = DMA_RB_WPTR + DMA0_REGISTER_OFFSET;
+	else
+		reg = DMA_RB_WPTR + DMA1_REGISTER_OFFSET;
+
+	WREG32(reg, (ring->wptr << 2) & 0x3fffc);
+}
+
+/**
+ * cayman_dma_ring_ib_execute - Schedule an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ib: IB object to schedule
+ *
+ * Schedule an IB in the DMA ring (cayman-SI).
+ */
+void cayman_dma_ring_ib_execute(struct radeon_device *rdev,
+				struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	unsigned vm_id = ib->vm ? ib->vm->ids[ib->ring].id : 0;
+
+	if (rdev->wb.enabled) {
+		u32 next_rptr = ring->wptr + 4;
+		while ((next_rptr & 7) != 5)
+			next_rptr++;
+		next_rptr += 3;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
+		radeon_ring_write(ring, next_rptr);
+	}
+
+	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
+	 * Pad as necessary with NOPs.
+	 */
+	while ((ring->wptr & 7) != 5)
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+	radeon_ring_write(ring, DMA_IB_PACKET(DMA_PACKET_INDIRECT_BUFFER, vm_id, 0));
+	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
+	radeon_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
+
+}
+
+/**
+ * cayman_dma_stop - stop the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engines (cayman-SI).
+ */
+void cayman_dma_stop(struct radeon_device *rdev)
+{
+	u32 rb_cntl;
+
+	if ((rdev->asic->copy.copy_ring_index == R600_RING_TYPE_DMA_INDEX) ||
+	    (rdev->asic->copy.copy_ring_index == CAYMAN_RING_TYPE_DMA1_INDEX))
+		radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
+	/* dma0 */
+	rb_cntl = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
+	rb_cntl &= ~DMA_RB_ENABLE;
+	WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, rb_cntl);
+
+	/* dma1 */
+	rb_cntl = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
+	rb_cntl &= ~DMA_RB_ENABLE;
+	WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, rb_cntl);
+
+	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
+}
+
+/**
+ * cayman_dma_resume - setup and start the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the DMA ring buffers and enable them. (cayman-SI).
+ * Returns 0 for success, error for failure.
+ */
+int cayman_dma_resume(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring;
+	u32 rb_cntl, dma_cntl, ib_cntl;
+	u32 rb_bufsz;
+	u32 reg_offset, wb_offset;
+	int i, r;
+
+	for (i = 0; i < 2; i++) {
+		if (i == 0) {
+			ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
+			reg_offset = DMA0_REGISTER_OFFSET;
+			wb_offset = R600_WB_DMA_RPTR_OFFSET;
+		} else {
+			ring = &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX];
+			reg_offset = DMA1_REGISTER_OFFSET;
+			wb_offset = CAYMAN_WB_DMA1_RPTR_OFFSET;
+		}
+
+		WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL + reg_offset, 0);
+		WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL + reg_offset, 0);
+
+		/* Set ring buffer size in dwords */
+		rb_bufsz = order_base_2(ring->ring_size / 4);
+		rb_cntl = rb_bufsz << 1;
+#ifdef __BIG_ENDIAN
+		rb_cntl |= DMA_RB_SWAP_ENABLE | DMA_RPTR_WRITEBACK_SWAP_ENABLE;
+#endif
+		WREG32(DMA_RB_CNTL + reg_offset, rb_cntl);
+
+		/* Initialize the ring buffer's read and write pointers */
+		WREG32(DMA_RB_RPTR + reg_offset, 0);
+		WREG32(DMA_RB_WPTR + reg_offset, 0);
+
+		/* set the wb address whether it's enabled or not */
+		WREG32(DMA_RB_RPTR_ADDR_HI + reg_offset,
+		       upper_32_bits(rdev->wb.gpu_addr + wb_offset) & 0xFF);
+		WREG32(DMA_RB_RPTR_ADDR_LO + reg_offset,
+		       ((rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC));
+
+		if (rdev->wb.enabled)
+			rb_cntl |= DMA_RPTR_WRITEBACK_ENABLE;
+
+		WREG32(DMA_RB_BASE + reg_offset, ring->gpu_addr >> 8);
+
+		/* enable DMA IBs */
+		ib_cntl = DMA_IB_ENABLE | CMD_VMID_FORCE;
+#ifdef __BIG_ENDIAN
+		ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+		WREG32(DMA_IB_CNTL + reg_offset, ib_cntl);
+
+		dma_cntl = RREG32(DMA_CNTL + reg_offset);
+		dma_cntl &= ~CTXEMPTY_INT_ENABLE;
+		WREG32(DMA_CNTL + reg_offset, dma_cntl);
+
+		ring->wptr = 0;
+		WREG32(DMA_RB_WPTR + reg_offset, ring->wptr << 2);
+
+		WREG32(DMA_RB_CNTL + reg_offset, rb_cntl | DMA_RB_ENABLE);
+
+		ring->ready = true;
+
+		r = radeon_ring_test(rdev, ring->idx, ring);
+		if (r) {
+			ring->ready = false;
+			return r;
+		}
+	}
+
+	if ((rdev->asic->copy.copy_ring_index == R600_RING_TYPE_DMA_INDEX) ||
+	    (rdev->asic->copy.copy_ring_index == CAYMAN_RING_TYPE_DMA1_INDEX))
+		radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
+
+	return 0;
+}
+
+/**
+ * cayman_dma_fini - tear down the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engines and free the rings (cayman-SI).
+ */
+void cayman_dma_fini(struct radeon_device *rdev)
+{
+	cayman_dma_stop(rdev);
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
+	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
+}
+
+/**
+ * cayman_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = cayman_gpu_check_soft_reset(rdev);
+	u32 mask;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		mask = RADEON_RESET_DMA;
+	else
+		mask = RADEON_RESET_DMA1;
+
+	if (!(reset_mask & mask)) {
+		radeon_ring_lockup_update(rdev, ring);
+		return false;
+	}
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+/**
+ * cayman_dma_vm_copy_pages - update PTEs by copying them from the GART
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @src: src addr where to copy from
+ * @count: number of page entries to update
+ *
+ * Update PTEs by copying them from the GART using the DMA (cayman/TN).
+ */
+void cayman_dma_vm_copy_pages(struct radeon_device *rdev,
+			      struct radeon_ib *ib,
+			      uint64_t pe, uint64_t src,
+			      unsigned count)
+{
+	unsigned ndw;
+
+	while (count) {
+		ndw = count * 2;
+		if (ndw > 0xFFFFE)
+			ndw = 0xFFFFE;
+
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_COPY,
+						      0, 0, ndw);
+		ib->ptr[ib->length_dw++] = lower_32_bits(pe);
+		ib->ptr[ib->length_dw++] = lower_32_bits(src);
+		ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+		ib->ptr[ib->length_dw++] = upper_32_bits(src) & 0xff;
+
+		pe += ndw * 4;
+		src += ndw * 4;
+		count -= ndw / 2;
+	}
+}
+
+/**
+ * cayman_dma_vm_write_pages - update PTEs by writing them manually
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @addr: dst addr to write into pe
+ * @count: number of page entries to update
+ * @incr: increase next addr by incr bytes
+ * @flags: hw access flags
+ *
+ * Update PTEs by writing them manually using the DMA (cayman/TN).
+ */
+void cayman_dma_vm_write_pages(struct radeon_device *rdev,
+			       struct radeon_ib *ib,
+			       uint64_t pe,
+			       uint64_t addr, unsigned count,
+			       uint32_t incr, uint32_t flags)
+{
+	uint64_t value;
+	unsigned ndw;
+
+	while (count) {
+		ndw = count * 2;
+		if (ndw > 0xFFFFE)
+			ndw = 0xFFFFE;
+
+		/* for non-physically contiguous pages (system) */
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE,
+						      0, 0, ndw);
+		ib->ptr[ib->length_dw++] = pe;
+		ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+		for (; ndw > 0; ndw -= 2, --count, pe += 8) {
+			if (flags & R600_PTE_SYSTEM) {
+				value = radeon_vm_map_gart(rdev, addr);
+			} else if (flags & R600_PTE_VALID) {
+				value = addr;
+			} else {
+				value = 0;
+			}
+			addr += incr;
+			value |= flags;
+			ib->ptr[ib->length_dw++] = value;
+			ib->ptr[ib->length_dw++] = upper_32_bits(value);
+		}
+	}
+}
+
+/**
+ * cayman_dma_vm_set_pages - update the page tables using the DMA
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @addr: dst addr to write into pe
+ * @count: number of page entries to update
+ * @incr: increase next addr by incr bytes
+ * @flags: hw access flags
+ *
+ * Update the page tables using the DMA (cayman/TN).
+ */
+void cayman_dma_vm_set_pages(struct radeon_device *rdev,
+			     struct radeon_ib *ib,
+			     uint64_t pe,
+			     uint64_t addr, unsigned count,
+			     uint32_t incr, uint32_t flags)
+{
+	uint64_t value;
+	unsigned ndw;
+
+	while (count) {
+		ndw = count * 2;
+		if (ndw > 0xFFFFE)
+			ndw = 0xFFFFE;
+
+		if (flags & R600_PTE_VALID)
+			value = addr;
+		else
+			value = 0;
+
+		/* for physically contiguous pages (vram) */
+		ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
+		ib->ptr[ib->length_dw++] = pe; /* dst addr */
+		ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+		ib->ptr[ib->length_dw++] = flags; /* mask */
+		ib->ptr[ib->length_dw++] = 0;
+		ib->ptr[ib->length_dw++] = value; /* value */
+		ib->ptr[ib->length_dw++] = upper_32_bits(value);
+		ib->ptr[ib->length_dw++] = incr; /* increment size */
+		ib->ptr[ib->length_dw++] = 0;
+
+		pe += ndw * 4;
+		addr += (ndw / 2) * incr;
+		count -= ndw / 2;
+	}
+}
+
+/**
+ * cayman_dma_vm_pad_ib - pad the IB to the required number of dw
+ *
+ * @ib: indirect buffer to fill with padding
+ *
+ */
+void cayman_dma_vm_pad_ib(struct radeon_ib *ib)
+{
+	while (ib->length_dw & 0x7)
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
+}
+
+void cayman_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+			 unsigned vm_id, uint64_t pd_addr)
+{
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2)) >> 2));
+	radeon_ring_write(ring, pd_addr >> 12);
+
+	/* flush hdp cache */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
+	radeon_ring_write(ring, 1);
+
+	/* bits 0-7 are the VM contexts0-7 */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
+	radeon_ring_write(ring, 1 << vm_id);
+
+	/* wait for invalidate to complete */
+	radeon_ring_write(ring, DMA_SRBM_READ_PACKET);
+	radeon_ring_write(ring, (0xff << 20) | (VM_INVALIDATE_REQUEST >> 2));
+	radeon_ring_write(ring, 0); /* mask */
+	radeon_ring_write(ring, 0); /* value */
+}
+