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, 495 insertions, 0 deletions

diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
new file mode 100644
index 000000000..89ca2738c
--- /dev/null
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -0,0 +1,495 @@
+/*
+ * Copyright 2013 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 "r600.h"
+#include "r600d.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.
+ */
+
+/**
+ * r600_dma_get_rptr - get the current read pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Get the current rptr from the hardware (r6xx+).
+ */
+uint32_t r600_dma_get_rptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	u32 rptr;
+
+	if (rdev->wb.enabled)
+		rptr = rdev->wb.wb[ring->rptr_offs/4];
+	else
+		rptr = RREG32(DMA_RB_RPTR);
+
+	return (rptr & 0x3fffc) >> 2;
+}
+
+/**
+ * r600_dma_get_wptr - get the current write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Get the current wptr from the hardware (r6xx+).
+ */
+uint32_t r600_dma_get_wptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	return (RREG32(DMA_RB_WPTR) & 0x3fffc) >> 2;
+}
+
+/**
+ * r600_dma_set_wptr - commit the write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Write the wptr back to the hardware (r6xx+).
+ */
+void r600_dma_set_wptr(struct radeon_device *rdev,
+		       struct radeon_ring *ring)
+{
+	WREG32(DMA_RB_WPTR, (ring->wptr << 2) & 0x3fffc);
+}
+
+/**
+ * r600_dma_stop - stop the async dma engine
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engine (r6xx-evergreen).
+ */
+void r600_dma_stop(struct radeon_device *rdev)
+{
+	u32 rb_cntl = RREG32(DMA_RB_CNTL);
+
+	if (rdev->asic->copy.copy_ring_index == R600_RING_TYPE_DMA_INDEX)
+		radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
+	rb_cntl &= ~DMA_RB_ENABLE;
+	WREG32(DMA_RB_CNTL, rb_cntl);
+
+	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+}
+
+/**
+ * r600_dma_resume - setup and start the async dma engine
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the DMA ring buffer and enable it. (r6xx-evergreen).
+ * Returns 0 for success, error for failure.
+ */
+int r600_dma_resume(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
+	u32 rb_cntl, dma_cntl, ib_cntl;
+	u32 rb_bufsz;
+	int r;
+
+	WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0);
+	WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 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, rb_cntl);
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32(DMA_RB_RPTR, 0);
+	WREG32(DMA_RB_WPTR, 0);
+
+	/* set the wb address whether it's enabled or not */
+	WREG32(DMA_RB_RPTR_ADDR_HI,
+	       upper_32_bits(rdev->wb.gpu_addr + R600_WB_DMA_RPTR_OFFSET) & 0xFF);
+	WREG32(DMA_RB_RPTR_ADDR_LO,
+	       ((rdev->wb.gpu_addr + R600_WB_DMA_RPTR_OFFSET) & 0xFFFFFFFC));
+
+	if (rdev->wb.enabled)
+		rb_cntl |= DMA_RPTR_WRITEBACK_ENABLE;
+
+	WREG32(DMA_RB_BASE, ring->gpu_addr >> 8);
+
+	/* enable DMA IBs */
+	ib_cntl = DMA_IB_ENABLE;
+#ifdef __BIG_ENDIAN
+	ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+	WREG32(DMA_IB_CNTL, ib_cntl);
+
+	dma_cntl = RREG32(DMA_CNTL);
+	dma_cntl &= ~CTXEMPTY_INT_ENABLE;
+	WREG32(DMA_CNTL, dma_cntl);
+
+	if (rdev->family >= CHIP_RV770)
+		WREG32(DMA_MODE, 1);
+
+	ring->wptr = 0;
+	WREG32(DMA_RB_WPTR, ring->wptr << 2);
+
+	WREG32(DMA_RB_CNTL, rb_cntl | DMA_RB_ENABLE);
+
+	ring->ready = true;
+
+	r = radeon_ring_test(rdev, R600_RING_TYPE_DMA_INDEX, ring);
+	if (r) {
+		ring->ready = false;
+		return r;
+	}
+
+	if (rdev->asic->copy.copy_ring_index == R600_RING_TYPE_DMA_INDEX)
+		radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
+
+	return 0;
+}
+
+/**
+ * r600_dma_fini - tear down the async dma engine
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engine and free the ring (r6xx-evergreen).
+ */
+void r600_dma_fini(struct radeon_device *rdev)
+{
+	r600_dma_stop(rdev);
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
+}
+
+/**
+ * r600_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 r600_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = r600_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & RADEON_RESET_DMA)) {
+		radeon_ring_lockup_update(rdev, ring);
+		return false;
+	}
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+
+/**
+ * r600_dma_ring_test - simple async dma engine test
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Test the DMA engine by writing using it to write an
+ * value to memory. (r6xx-SI).
+ * Returns 0 for success, error for failure.
+ */
+int r600_dma_ring_test(struct radeon_device *rdev,
+		       struct radeon_ring *ring)
+{
+	unsigned i;
+	int r;
+	unsigned index;
+	u32 tmp;
+	u64 gpu_addr;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
+
+	tmp = 0xCAFEDEAD;
+	rdev->wb.wb[index/4] = cpu_to_le32(tmp);
+
+	r = radeon_ring_lock(rdev, ring, 4);
+	if (r) {
+		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
+		return r;
+	}
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
+	radeon_ring_write(ring, lower_32_bits(gpu_addr));
+	radeon_ring_write(ring, upper_32_bits(gpu_addr) & 0xff);
+	radeon_ring_write(ring, 0xDEADBEEF);
+	radeon_ring_unlock_commit(rdev, ring, false);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+	} else {
+		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
+			  ring->idx, tmp);
+		r = -EINVAL;
+	}
+	return r;
+}
+
+/**
+ * r600_dma_fence_ring_emit - emit a fence on the DMA ring
+ *
+ * @rdev: radeon_device pointer
+ * @fence: radeon fence object
+ *
+ * Add a DMA fence packet to the ring to write
+ * the fence seq number and DMA trap packet to generate
+ * an interrupt if needed (r6xx-r7xx).
+ */
+void r600_dma_fence_ring_emit(struct radeon_device *rdev,
+			      struct radeon_fence *fence)
+{
+	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+
+	/* write the fence */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0, 0));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff));
+	radeon_ring_write(ring, lower_32_bits(fence->seq));
+	/* generate an interrupt */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0, 0));
+}
+
+/**
+ * r600_dma_semaphore_ring_emit - emit a semaphore on the dma ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ * @semaphore: radeon semaphore object
+ * @emit_wait: wait or signal semaphore
+ *
+ * Add a DMA semaphore packet to the ring wait on or signal
+ * other rings (r6xx-SI).
+ */
+bool r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
+				  struct radeon_ring *ring,
+				  struct radeon_semaphore *semaphore,
+				  bool emit_wait)
+{
+	u64 addr = semaphore->gpu_addr;
+	u32 s = emit_wait ? 0 : 1;
+
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SEMAPHORE, 0, s, 0));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
+
+	return true;
+}
+
+/**
+ * r600_dma_ib_test - test an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Test a simple IB in the DMA ring (r6xx-SI).
+ * Returns 0 on success, error on failure.
+ */
+int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	struct radeon_ib ib;
+	unsigned i;
+	unsigned index;
+	int r;
+	u32 tmp = 0;
+	u64 gpu_addr;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
+
+	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
+	if (r) {
+		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
+		return r;
+	}
+
+	ib.ptr[0] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1);
+	ib.ptr[1] = lower_32_bits(gpu_addr);
+	ib.ptr[2] = upper_32_bits(gpu_addr) & 0xff;
+	ib.ptr[3] = 0xDEADBEEF;
+	ib.length_dw = 4;
+
+	r = radeon_ib_schedule(rdev, &ib, NULL, false);
+	if (r) {
+		radeon_ib_free(rdev, &ib);
+		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
+		return r;
+	}
+	r = radeon_fence_wait_timeout(ib.fence, false, usecs_to_jiffies(
+		RADEON_USEC_IB_TEST_TIMEOUT));
+	if (r < 0) {
+		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+		return r;
+	} else if (r == 0) {
+		DRM_ERROR("radeon: fence wait timed out.\n");
+		return -ETIMEDOUT;
+	}
+	r = 0;
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib.fence->ring, i);
+	} else {
+		DRM_ERROR("radeon: ib test failed (0x%08X)\n", tmp);
+		r = -EINVAL;
+	}
+	radeon_ib_free(rdev, &ib);
+	return r;
+}
+
+/**
+ * r600_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 (r6xx-r7xx).
+ */
+void r600_dma_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+
+	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_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0, 0));
+	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
+	radeon_ring_write(ring, (ib->length_dw << 16) | (upper_32_bits(ib->gpu_addr) & 0xFF));
+
+}
+
+/**
+ * r600_copy_dma - copy pages using the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @resv: reservation object to sync to
+ *
+ * Copy GPU paging using the DMA engine (r6xx).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+struct radeon_fence *r600_copy_dma(struct radeon_device *rdev,
+				   uint64_t src_offset, uint64_t dst_offset,
+				   unsigned num_gpu_pages,
+				   struct dma_resv *resv)
+{
+	struct radeon_fence *fence;
+	struct radeon_sync sync;
+	int ring_index = rdev->asic->copy.dma_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_dw, cur_size_in_dw;
+	int i, num_loops;
+	int r = 0;
+
+	radeon_sync_create(&sync);
+
+	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
+	num_loops = DIV_ROUND_UP(size_in_dw, 0xFFFE);
+	r = radeon_ring_lock(rdev, ring, num_loops * 4 + 8);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_sync_free(rdev, &sync, NULL);
+		return ERR_PTR(r);
+	}
+
+	radeon_sync_resv(rdev, &sync, resv, false);
+	radeon_sync_rings(rdev, &sync, ring->idx);
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_dw = size_in_dw;
+		if (cur_size_in_dw > 0xFFFE)
+			cur_size_in_dw = 0xFFFE;
+		size_in_dw -= cur_size_in_dw;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
+		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, src_offset & 0xfffffffc);
+		radeon_ring_write(ring, (((upper_32_bits(dst_offset) & 0xff) << 16) |
+					 (upper_32_bits(src_offset) & 0xff)));
+		src_offset += cur_size_in_dw * 4;
+		dst_offset += cur_size_in_dw * 4;
+	}
+
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		radeon_sync_free(rdev, &sync, NULL);
+		return ERR_PTR(r);
+	}
+
+	radeon_ring_unlock_commit(rdev, ring, false);
+	radeon_sync_free(rdev, &sync, fence);
+
+	return fence;
+}