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, 676 insertions, 0 deletions

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
new file mode 100644
index 000000000..230726d7b
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -0,0 +1,676 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and 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.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and 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.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+static void xgbe_unmap_rdata(struct xgbe_prv_data *, struct xgbe_ring_data *);
+
+static void xgbe_free_ring(struct xgbe_prv_data *pdata,
+			   struct xgbe_ring *ring)
+{
+	struct xgbe_ring_data *rdata;
+	unsigned int i;
+
+	if (!ring)
+		return;
+
+	if (ring->rdata) {
+		for (i = 0; i < ring->rdesc_count; i++) {
+			rdata = XGBE_GET_DESC_DATA(ring, i);
+			xgbe_unmap_rdata(pdata, rdata);
+		}
+
+		kfree(ring->rdata);
+		ring->rdata = NULL;
+	}
+
+	if (ring->rx_hdr_pa.pages) {
+		dma_unmap_page(pdata->dev, ring->rx_hdr_pa.pages_dma,
+			       ring->rx_hdr_pa.pages_len, DMA_FROM_DEVICE);
+		put_page(ring->rx_hdr_pa.pages);
+
+		ring->rx_hdr_pa.pages = NULL;
+		ring->rx_hdr_pa.pages_len = 0;
+		ring->rx_hdr_pa.pages_offset = 0;
+		ring->rx_hdr_pa.pages_dma = 0;
+	}
+
+	if (ring->rx_buf_pa.pages) {
+		dma_unmap_page(pdata->dev, ring->rx_buf_pa.pages_dma,
+			       ring->rx_buf_pa.pages_len, DMA_FROM_DEVICE);
+		put_page(ring->rx_buf_pa.pages);
+
+		ring->rx_buf_pa.pages = NULL;
+		ring->rx_buf_pa.pages_len = 0;
+		ring->rx_buf_pa.pages_offset = 0;
+		ring->rx_buf_pa.pages_dma = 0;
+	}
+
+	if (ring->rdesc) {
+		dma_free_coherent(pdata->dev,
+				  (sizeof(struct xgbe_ring_desc) *
+				   ring->rdesc_count),
+				  ring->rdesc, ring->rdesc_dma);
+		ring->rdesc = NULL;
+	}
+}
+
+static void xgbe_free_ring_resources(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	DBGPR("-->xgbe_free_ring_resources\n");
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		channel = pdata->channel[i];
+		xgbe_free_ring(pdata, channel->tx_ring);
+		xgbe_free_ring(pdata, channel->rx_ring);
+	}
+
+	DBGPR("<--xgbe_free_ring_resources\n");
+}
+
+static void *xgbe_alloc_node(size_t size, int node)
+{
+	void *mem;
+
+	mem = kzalloc_node(size, GFP_KERNEL, node);
+	if (!mem)
+		mem = kzalloc(size, GFP_KERNEL);
+
+	return mem;
+}
+
+static void *xgbe_dma_alloc_node(struct device *dev, size_t size,
+				 dma_addr_t *dma, int node)
+{
+	void *mem;
+	int cur_node = dev_to_node(dev);
+
+	set_dev_node(dev, node);
+	mem = dma_alloc_coherent(dev, size, dma, GFP_KERNEL);
+	set_dev_node(dev, cur_node);
+
+	if (!mem)
+		mem = dma_alloc_coherent(dev, size, dma, GFP_KERNEL);
+
+	return mem;
+}
+
+static int xgbe_init_ring(struct xgbe_prv_data *pdata,
+			  struct xgbe_ring *ring, unsigned int rdesc_count)
+{
+	size_t size;
+
+	if (!ring)
+		return 0;
+
+	/* Descriptors */
+	size = rdesc_count * sizeof(struct xgbe_ring_desc);
+
+	ring->rdesc_count = rdesc_count;
+	ring->rdesc = xgbe_dma_alloc_node(pdata->dev, size, &ring->rdesc_dma,
+					  ring->node);
+	if (!ring->rdesc)
+		return -ENOMEM;
+
+	/* Descriptor information */
+	size = rdesc_count * sizeof(struct xgbe_ring_data);
+
+	ring->rdata = xgbe_alloc_node(size, ring->node);
+	if (!ring->rdata)
+		return -ENOMEM;
+
+	netif_dbg(pdata, drv, pdata->netdev,
+		  "rdesc=%p, rdesc_dma=%pad, rdata=%p, node=%d\n",
+		  ring->rdesc, &ring->rdesc_dma, ring->rdata, ring->node);
+
+	return 0;
+}
+
+static int xgbe_alloc_ring_resources(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		channel = pdata->channel[i];
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n",
+			  channel->name);
+
+		ret = xgbe_init_ring(pdata, channel->tx_ring,
+				     pdata->tx_desc_count);
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Tx ring\n");
+			goto err_ring;
+		}
+
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n",
+			  channel->name);
+
+		ret = xgbe_init_ring(pdata, channel->rx_ring,
+				     pdata->rx_desc_count);
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Rx ring\n");
+			goto err_ring;
+		}
+	}
+
+	return 0;
+
+err_ring:
+	xgbe_free_ring_resources(pdata);
+
+	return ret;
+}
+
+static int xgbe_alloc_pages(struct xgbe_prv_data *pdata,
+			    struct xgbe_page_alloc *pa, int alloc_order,
+			    int node)
+{
+	struct page *pages = NULL;
+	dma_addr_t pages_dma;
+	gfp_t gfp;
+	int order;
+
+again:
+	order = alloc_order;
+
+	/* Try to obtain pages, decreasing order if necessary */
+	gfp = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
+	while (order >= 0) {
+		pages = alloc_pages_node(node, gfp, order);
+		if (pages)
+			break;
+
+		order--;
+	}
+
+	/* If we couldn't get local pages, try getting from anywhere */
+	if (!pages && (node != NUMA_NO_NODE)) {
+		node = NUMA_NO_NODE;
+		goto again;
+	}
+
+	if (!pages)
+		return -ENOMEM;
+
+	/* Map the pages */
+	pages_dma = dma_map_page(pdata->dev, pages, 0,
+				 PAGE_SIZE << order, DMA_FROM_DEVICE);
+	if (dma_mapping_error(pdata->dev, pages_dma)) {
+		put_page(pages);
+		return -ENOMEM;
+	}
+
+	pa->pages = pages;
+	pa->pages_len = PAGE_SIZE << order;
+	pa->pages_offset = 0;
+	pa->pages_dma = pages_dma;
+
+	return 0;
+}
+
+static void xgbe_set_buffer_data(struct xgbe_buffer_data *bd,
+				 struct xgbe_page_alloc *pa,
+				 unsigned int len)
+{
+	get_page(pa->pages);
+	bd->pa = *pa;
+
+	bd->dma_base = pa->pages_dma;
+	bd->dma_off = pa->pages_offset;
+	bd->dma_len = len;
+
+	pa->pages_offset += len;
+	if ((pa->pages_offset + len) > pa->pages_len) {
+		/* This data descriptor is responsible for unmapping page(s) */
+		bd->pa_unmap = *pa;
+
+		/* Get a new allocation next time */
+		pa->pages = NULL;
+		pa->pages_len = 0;
+		pa->pages_offset = 0;
+		pa->pages_dma = 0;
+	}
+}
+
+static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
+			      struct xgbe_ring *ring,
+			      struct xgbe_ring_data *rdata)
+{
+	int ret;
+
+	if (!ring->rx_hdr_pa.pages) {
+		ret = xgbe_alloc_pages(pdata, &ring->rx_hdr_pa, 0, ring->node);
+		if (ret)
+			return ret;
+	}
+
+	if (!ring->rx_buf_pa.pages) {
+		ret = xgbe_alloc_pages(pdata, &ring->rx_buf_pa,
+				       PAGE_ALLOC_COSTLY_ORDER, ring->node);
+		if (ret)
+			return ret;
+	}
+
+	/* Set up the header page info */
+	xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+			     XGBE_SKB_ALLOC_SIZE);
+
+	/* Set up the buffer page info */
+	xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
+			     pdata->rx_buf_size);
+
+	return 0;
+}
+
+static void xgbe_wrapper_tx_descriptor_init(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	dma_addr_t rdesc_dma;
+	unsigned int i, j;
+
+	DBGPR("-->xgbe_wrapper_tx_descriptor_init\n");
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		channel = pdata->channel[i];
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		rdesc = ring->rdesc;
+		rdesc_dma = ring->rdesc_dma;
+
+		for (j = 0; j < ring->rdesc_count; j++) {
+			rdata = XGBE_GET_DESC_DATA(ring, j);
+
+			rdata->rdesc = rdesc;
+			rdata->rdesc_dma = rdesc_dma;
+
+			rdesc++;
+			rdesc_dma += sizeof(struct xgbe_ring_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+		memset(&ring->tx, 0, sizeof(ring->tx));
+
+		hw_if->tx_desc_init(channel);
+	}
+
+	DBGPR("<--xgbe_wrapper_tx_descriptor_init\n");
+}
+
+static void xgbe_wrapper_rx_descriptor_init(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_ring_desc *rdesc;
+	struct xgbe_ring_data *rdata;
+	dma_addr_t rdesc_dma;
+	unsigned int i, j;
+
+	DBGPR("-->xgbe_wrapper_rx_descriptor_init\n");
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		channel = pdata->channel[i];
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		rdesc = ring->rdesc;
+		rdesc_dma = ring->rdesc_dma;
+
+		for (j = 0; j < ring->rdesc_count; j++) {
+			rdata = XGBE_GET_DESC_DATA(ring, j);
+
+			rdata->rdesc = rdesc;
+			rdata->rdesc_dma = rdesc_dma;
+
+			if (xgbe_map_rx_buffer(pdata, ring, rdata))
+				break;
+
+			rdesc++;
+			rdesc_dma += sizeof(struct xgbe_ring_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+
+		hw_if->rx_desc_init(channel);
+	}
+
+	DBGPR("<--xgbe_wrapper_rx_descriptor_init\n");
+}
+
+static void xgbe_unmap_rdata(struct xgbe_prv_data *pdata,
+			     struct xgbe_ring_data *rdata)
+{
+	if (rdata->skb_dma) {
+		if (rdata->mapped_as_page) {
+			dma_unmap_page(pdata->dev, rdata->skb_dma,
+				       rdata->skb_dma_len, DMA_TO_DEVICE);
+		} else {
+			dma_unmap_single(pdata->dev, rdata->skb_dma,
+					 rdata->skb_dma_len, DMA_TO_DEVICE);
+		}
+		rdata->skb_dma = 0;
+		rdata->skb_dma_len = 0;
+	}
+
+	if (rdata->skb) {
+		dev_kfree_skb_any(rdata->skb);
+		rdata->skb = NULL;
+	}
+
+	if (rdata->rx.hdr.pa.pages)
+		put_page(rdata->rx.hdr.pa.pages);
+
+	if (rdata->rx.hdr.pa_unmap.pages) {
+		dma_unmap_page(pdata->dev, rdata->rx.hdr.pa_unmap.pages_dma,
+			       rdata->rx.hdr.pa_unmap.pages_len,
+			       DMA_FROM_DEVICE);
+		put_page(rdata->rx.hdr.pa_unmap.pages);
+	}
+
+	if (rdata->rx.buf.pa.pages)
+		put_page(rdata->rx.buf.pa.pages);
+
+	if (rdata->rx.buf.pa_unmap.pages) {
+		dma_unmap_page(pdata->dev, rdata->rx.buf.pa_unmap.pages_dma,
+			       rdata->rx.buf.pa_unmap.pages_len,
+			       DMA_FROM_DEVICE);
+		put_page(rdata->rx.buf.pa_unmap.pages);
+	}
+
+	memset(&rdata->tx, 0, sizeof(rdata->tx));
+	memset(&rdata->rx, 0, sizeof(rdata->rx));
+
+	rdata->mapped_as_page = 0;
+
+	if (rdata->state_saved) {
+		rdata->state_saved = 0;
+		rdata->state.skb = NULL;
+		rdata->state.len = 0;
+		rdata->state.error = 0;
+	}
+}
+
+static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_ring *ring = channel->tx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_packet_data *packet;
+	skb_frag_t *frag;
+	dma_addr_t skb_dma;
+	unsigned int start_index, cur_index;
+	unsigned int offset, tso, vlan, datalen, len;
+	unsigned int i;
+
+	DBGPR("-->xgbe_map_tx_skb: cur = %d\n", ring->cur);
+
+	offset = 0;
+	start_index = ring->cur;
+	cur_index = ring->cur;
+
+	packet = &ring->packet_data;
+	packet->rdesc_count = 0;
+	packet->length = 0;
+
+	tso = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			     TSO_ENABLE);
+	vlan = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			      VLAN_CTAG);
+
+	/* Save space for a context descriptor if needed */
+	if ((tso && (packet->mss != ring->tx.cur_mss)) ||
+	    (vlan && (packet->vlan_ctag != ring->tx.cur_vlan_ctag)))
+		cur_index++;
+	rdata = XGBE_GET_DESC_DATA(ring, cur_index);
+
+	if (tso) {
+		/* Map the TSO header */
+		skb_dma = dma_map_single(pdata->dev, skb->data,
+					 packet->header_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		rdata->skb_dma = skb_dma;
+		rdata->skb_dma_len = packet->header_len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb header: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, packet->header_len);
+
+		offset = packet->header_len;
+
+		packet->length += packet->header_len;
+
+		cur_index++;
+		rdata = XGBE_GET_DESC_DATA(ring, cur_index);
+	}
+
+	/* Map the (remainder of the) packet */
+	for (datalen = skb_headlen(skb) - offset; datalen; ) {
+		len = min_t(unsigned int, datalen, XGBE_TX_MAX_BUF_SIZE);
+
+		skb_dma = dma_map_single(pdata->dev, skb->data + offset, len,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		rdata->skb_dma = skb_dma;
+		rdata->skb_dma_len = len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb data: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, len);
+
+		datalen -= len;
+		offset += len;
+
+		packet->length += len;
+
+		cur_index++;
+		rdata = XGBE_GET_DESC_DATA(ring, cur_index);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "mapping frag %u\n", i);
+
+		frag = &skb_shinfo(skb)->frags[i];
+		offset = 0;
+
+		for (datalen = skb_frag_size(frag); datalen; ) {
+			len = min_t(unsigned int, datalen,
+				    XGBE_TX_MAX_BUF_SIZE);
+
+			skb_dma = skb_frag_dma_map(pdata->dev, frag, offset,
+						   len, DMA_TO_DEVICE);
+			if (dma_mapping_error(pdata->dev, skb_dma)) {
+				netdev_alert(pdata->netdev,
+					     "skb_frag_dma_map failed\n");
+				goto err_out;
+			}
+			rdata->skb_dma = skb_dma;
+			rdata->skb_dma_len = len;
+			rdata->mapped_as_page = 1;
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "skb frag: index=%u, dma=%pad, len=%u\n",
+				  cur_index, &skb_dma, len);
+
+			datalen -= len;
+			offset += len;
+
+			packet->length += len;
+
+			cur_index++;
+			rdata = XGBE_GET_DESC_DATA(ring, cur_index);
+		}
+	}
+
+	/* Save the skb address in the last entry. We always have some data
+	 * that has been mapped so rdata is always advanced past the last
+	 * piece of mapped data - use the entry pointed to by cur_index - 1.
+	 */
+	rdata = XGBE_GET_DESC_DATA(ring, cur_index - 1);
+	rdata->skb = skb;
+
+	/* Save the number of descriptor entries used */
+	packet->rdesc_count = cur_index - start_index;
+
+	DBGPR("<--xgbe_map_tx_skb: count=%u\n", packet->rdesc_count);
+
+	return packet->rdesc_count;
+
+err_out:
+	while (start_index < cur_index) {
+		rdata = XGBE_GET_DESC_DATA(ring, start_index++);
+		xgbe_unmap_rdata(pdata, rdata);
+	}
+
+	DBGPR("<--xgbe_map_tx_skb: count=0\n");
+
+	return 0;
+}
+
+void xgbe_init_function_ptrs_desc(struct xgbe_desc_if *desc_if)
+{
+	DBGPR("-->xgbe_init_function_ptrs_desc\n");
+
+	desc_if->alloc_ring_resources = xgbe_alloc_ring_resources;
+	desc_if->free_ring_resources = xgbe_free_ring_resources;
+	desc_if->map_tx_skb = xgbe_map_tx_skb;
+	desc_if->map_rx_buffer = xgbe_map_rx_buffer;
+	desc_if->unmap_rdata = xgbe_unmap_rdata;
+	desc_if->wrapper_tx_desc_init = xgbe_wrapper_tx_descriptor_init;
+	desc_if->wrapper_rx_desc_init = xgbe_wrapper_rx_descriptor_init;
+
+	DBGPR("<--xgbe_init_function_ptrs_desc\n");
+}