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, 594 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
new file mode 100644
index 000000000..6d1dd6e87
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -0,0 +1,594 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * LocalPlus Bus FIFO driver for the Freescale MPC52xx.
+ *
+ * Copyright (C) 2009 Secret Lab Technologies Ltd.
+ *
+ * Todo:
+ * - Add support for multiple requests to be queued.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/mpc52xx.h>
+#include <asm/time.h>
+
+#include <linux/fsl/bestcomm/bestcomm.h>
+#include <linux/fsl/bestcomm/bestcomm_priv.h>
+#include <linux/fsl/bestcomm/gen_bd.h>
+
+MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
+MODULE_DESCRIPTION("MPC5200 LocalPlus FIFO device driver");
+MODULE_LICENSE("GPL");
+
+#define LPBFIFO_REG_PACKET_SIZE		(0x00)
+#define LPBFIFO_REG_START_ADDRESS	(0x04)
+#define LPBFIFO_REG_CONTROL		(0x08)
+#define LPBFIFO_REG_ENABLE		(0x0C)
+#define LPBFIFO_REG_BYTES_DONE_STATUS	(0x14)
+#define LPBFIFO_REG_FIFO_DATA		(0x40)
+#define LPBFIFO_REG_FIFO_STATUS		(0x44)
+#define LPBFIFO_REG_FIFO_CONTROL	(0x48)
+#define LPBFIFO_REG_FIFO_ALARM		(0x4C)
+
+struct mpc52xx_lpbfifo {
+	struct device *dev;
+	phys_addr_t regs_phys;
+	void __iomem *regs;
+	int irq;
+	spinlock_t lock;
+
+	struct bcom_task *bcom_tx_task;
+	struct bcom_task *bcom_rx_task;
+	struct bcom_task *bcom_cur_task;
+
+	/* Current state data */
+	struct mpc52xx_lpbfifo_request *req;
+	int dma_irqs_enabled;
+};
+
+/* The MPC5200 has only one fifo, so only need one instance structure */
+static struct mpc52xx_lpbfifo lpbfifo;
+
+/**
+ * mpc52xx_lpbfifo_kick - Trigger the next block of data to be transferred
+ *
+ * @req: Pointer to request structure
+ */
+static void mpc52xx_lpbfifo_kick(struct mpc52xx_lpbfifo_request *req)
+{
+	size_t transfer_size = req->size - req->pos;
+	struct bcom_bd *bd;
+	void __iomem *reg;
+	u32 *data;
+	int i;
+	int bit_fields;
+	int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
+	int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
+	int poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA;
+
+	/* Set and clear the reset bits; is good practice in User Manual */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+
+	/* set master enable bit */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000001);
+	if (!dma) {
+		/* While the FIFO can be setup for transfer sizes as large as
+		 * 16M-1, the FIFO itself is only 512 bytes deep and it does
+		 * not generate interrupts for FIFO full events (only transfer
+		 * complete will raise an IRQ).  Therefore when not using
+		 * Bestcomm to drive the FIFO it needs to either be polled, or
+		 * transfers need to constrained to the size of the fifo.
+		 *
+		 * This driver restricts the size of the transfer
+		 */
+		if (transfer_size > 512)
+			transfer_size = 512;
+
+		/* Load the FIFO with data */
+		if (write) {
+			reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA;
+			data = req->data + req->pos;
+			for (i = 0; i < transfer_size; i += 4)
+				out_be32(reg, *data++);
+		}
+
+		/* Unmask both error and completion irqs */
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000301);
+	} else {
+		/* Choose the correct direction
+		 *
+		 * Configure the watermarks so DMA will always complete correctly.
+		 * It may be worth experimenting with the ALARM value to see if
+		 * there is a performance impact.  However, if it is wrong there
+		 * is a risk of DMA not transferring the last chunk of data
+		 */
+		if (write) {
+			out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1e4);
+			out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 7);
+			lpbfifo.bcom_cur_task = lpbfifo.bcom_tx_task;
+		} else {
+			out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1ff);
+			out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 0);
+			lpbfifo.bcom_cur_task = lpbfifo.bcom_rx_task;
+
+			if (poll_dma) {
+				if (lpbfifo.dma_irqs_enabled) {
+					disable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task));
+					lpbfifo.dma_irqs_enabled = 0;
+				}
+			} else {
+				if (!lpbfifo.dma_irqs_enabled) {
+					enable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task));
+					lpbfifo.dma_irqs_enabled = 1;
+				}
+			}
+		}
+
+		bd = bcom_prepare_next_buffer(lpbfifo.bcom_cur_task);
+		bd->status = transfer_size;
+		if (!write) {
+			/*
+			 * In the DMA read case, the DMA doesn't complete,
+			 * possibly due to incorrect watermarks in the ALARM
+			 * and CONTROL regs. For now instead of trying to
+			 * determine the right watermarks that will make this
+			 * work, just increase the number of bytes the FIFO is
+			 * expecting.
+			 *
+			 * When submitting another operation, the FIFO will get
+			 * reset, so the condition of the FIFO waiting for a
+			 * non-existent 4 bytes will get cleared.
+			 */
+			transfer_size += 4; /* BLECH! */
+		}
+		bd->data[0] = req->data_phys + req->pos;
+		bcom_submit_next_buffer(lpbfifo.bcom_cur_task, NULL);
+
+		/* error irq & master enabled bit */
+		bit_fields = 0x00000201;
+
+		/* Unmask irqs */
+		if (write && (!poll_dma))
+			bit_fields |= 0x00000100; /* completion irq too */
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, bit_fields);
+	}
+
+	/* Set transfer size, width, chip select and READ mode */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_START_ADDRESS,
+		 req->offset + req->pos);
+	out_be32(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, transfer_size);
+
+	bit_fields = req->cs << 24 | 0x000008;
+	if (!write)
+		bit_fields |= 0x010000; /* read mode */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_CONTROL, bit_fields);
+
+	/* Kick it off */
+	if (!lpbfifo.req->defer_xfer_start)
+		out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
+	if (dma)
+		bcom_enable(lpbfifo.bcom_cur_task);
+}
+
+/**
+ * mpc52xx_lpbfifo_irq - IRQ handler for LPB FIFO
+ * @irq: IRQ number to be handled
+ * @dev_id: device ID cookie
+ *
+ * On transmit, the dma completion irq triggers before the fifo completion
+ * triggers.  Handle the dma completion here instead of the LPB FIFO Bestcomm
+ * task completion irq because everything is not really done until the LPB FIFO
+ * completion irq triggers.
+ *
+ * In other words:
+ * For DMA, on receive, the "Fat Lady" is the bestcom completion irq. on
+ * transmit, the fifo completion irq is the "Fat Lady". The opera (or in this
+ * case the DMA/FIFO operation) is not finished until the "Fat Lady" sings.
+ *
+ * Reasons for entering this routine:
+ * 1) PIO mode rx and tx completion irq
+ * 2) DMA interrupt mode tx completion irq
+ * 3) DMA polled mode tx
+ *
+ * Exit conditions:
+ * 1) Transfer aborted
+ * 2) FIFO complete without DMA; more data to do
+ * 3) FIFO complete without DMA; all data transferred
+ * 4) FIFO complete using DMA
+ *
+ * Condition 1 can occur regardless of whether or not DMA is used.
+ * It requires executing the callback to report the error and exiting
+ * immediately.
+ *
+ * Condition 2 requires programming the FIFO with the next block of data
+ *
+ * Condition 3 requires executing the callback to report completion
+ *
+ * Condition 4 means the same as 3, except that we also retrieve the bcom
+ * buffer so DMA doesn't get clogged up.
+ *
+ * To make things trickier, the spinlock must be dropped before
+ * executing the callback, otherwise we could end up with a deadlock
+ * or nested spinlock condition.  The out path is non-trivial, so
+ * extra fiddling is done to make sure all paths lead to the same
+ * outbound code.
+ *
+ * Return: irqreturn code (%IRQ_HANDLED)
+ */
+static irqreturn_t mpc52xx_lpbfifo_irq(int irq, void *dev_id)
+{
+	struct mpc52xx_lpbfifo_request *req;
+	u32 status = in_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS);
+	void __iomem *reg;
+	u32 *data;
+	int count, i;
+	int do_callback = 0;
+	u32 ts;
+	unsigned long flags;
+	int dma, write, poll_dma;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+	ts = mftb();
+
+	req = lpbfifo.req;
+	if (!req) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		pr_err("bogus LPBFIFO IRQ\n");
+		return IRQ_HANDLED;
+	}
+
+	dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
+	write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
+	poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA;
+
+	if (dma && !write) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		pr_err("bogus LPBFIFO IRQ (dma and not writing)\n");
+		return IRQ_HANDLED;
+	}
+
+	if ((status & 0x01) == 0) {
+		goto out;
+	}
+
+	/* check abort bit */
+	if (status & 0x10) {
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+		do_callback = 1;
+		goto out;
+	}
+
+	/* Read result from hardware */
+	count = in_be32(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS);
+	count &= 0x00ffffff;
+
+	if (!dma && !write) {
+		/* copy the data out of the FIFO */
+		reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA;
+		data = req->data + req->pos;
+		for (i = 0; i < count; i += 4)
+			*data++ = in_be32(reg);
+	}
+
+	/* Update transfer position and count */
+	req->pos += count;
+
+	/* Decide what to do next */
+	if (req->size - req->pos)
+		mpc52xx_lpbfifo_kick(req); /* more work to do */
+	else
+		do_callback = 1;
+
+ out:
+	/* Clear the IRQ */
+	out_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS, 0x01);
+
+	if (dma && (status & 0x11)) {
+		/*
+		 * Count the DMA as complete only when the FIFO completion
+		 * status or abort bits are set.
+		 *
+		 * (status & 0x01) should always be the case except sometimes
+		 * when using polled DMA.
+		 *
+		 * (status & 0x10) {transfer aborted}: This case needs more
+		 * testing.
+		 */
+		bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL);
+	}
+	req->last_byte = ((u8 *)req->data)[req->size - 1];
+
+	/* When the do_callback flag is set; it means the transfer is finished
+	 * so set the FIFO as idle */
+	if (do_callback)
+		lpbfifo.req = NULL;
+
+	if (irq != 0) /* don't increment on polled case */
+		req->irq_count++;
+
+	req->irq_ticks += mftb() - ts;
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+
+	/* Spinlock is released; it is now safe to call the callback */
+	if (do_callback && req->callback)
+		req->callback(req);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * mpc52xx_lpbfifo_bcom_irq - IRQ handler for LPB FIFO Bestcomm task
+ * @irq: IRQ number to be handled
+ * @dev_id: device ID cookie
+ *
+ * Only used when receiving data.
+ *
+ * Return: irqreturn code (%IRQ_HANDLED)
+ */
+static irqreturn_t mpc52xx_lpbfifo_bcom_irq(int irq, void *dev_id)
+{
+	struct mpc52xx_lpbfifo_request *req;
+	unsigned long flags;
+	u32 status;
+	u32 ts;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+	ts = mftb();
+
+	req = lpbfifo.req;
+	if (!req || (req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA)) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		return IRQ_HANDLED;
+	}
+
+	if (irq != 0) /* don't increment on polled case */
+		req->irq_count++;
+
+	if (!bcom_buffer_done(lpbfifo.bcom_cur_task)) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+
+		req->buffer_not_done_cnt++;
+		if ((req->buffer_not_done_cnt % 1000) == 0)
+			pr_err("transfer stalled\n");
+
+		return IRQ_HANDLED;
+	}
+
+	bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL);
+
+	req->last_byte = ((u8 *)req->data)[req->size - 1];
+
+	req->pos = status & 0x00ffffff;
+
+	/* Mark the FIFO as idle */
+	lpbfifo.req = NULL;
+
+	/* Release the lock before calling out to the callback. */
+	req->irq_ticks += mftb() - ts;
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+
+	if (req->callback)
+		req->callback(req);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * mpc52xx_lpbfifo_poll - Poll for DMA completion
+ */
+void mpc52xx_lpbfifo_poll(void)
+{
+	struct mpc52xx_lpbfifo_request *req = lpbfifo.req;
+	int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
+	int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
+
+	/*
+	 * For more information, see comments on the "Fat Lady" 
+	 */
+	if (dma && write)
+		mpc52xx_lpbfifo_irq(0, NULL);
+	else 
+		mpc52xx_lpbfifo_bcom_irq(0, NULL);
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_poll);
+
+/**
+ * mpc52xx_lpbfifo_submit - Submit an LPB FIFO transfer request.
+ * @req: Pointer to request structure
+ *
+ * Return: %0 on success, -errno code on error
+ */
+int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req)
+{
+	unsigned long flags;
+
+	if (!lpbfifo.regs)
+		return -ENODEV;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+
+	/* If the req pointer is already set, then a transfer is in progress */
+	if (lpbfifo.req) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		return -EBUSY;
+	}
+
+	/* Setup the transfer */
+	lpbfifo.req = req;
+	req->irq_count = 0;
+	req->irq_ticks = 0;
+	req->buffer_not_done_cnt = 0;
+	req->pos = 0;
+
+	mpc52xx_lpbfifo_kick(req);
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_submit);
+
+int mpc52xx_lpbfifo_start_xfer(struct mpc52xx_lpbfifo_request *req)
+{
+	unsigned long flags;
+
+	if (!lpbfifo.regs)
+		return -ENODEV;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+
+	/*
+	 * If the req pointer is already set and a transfer was
+	 * started on submit, then this transfer is in progress
+	 */
+	if (lpbfifo.req && !lpbfifo.req->defer_xfer_start) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		return -EBUSY;
+	}
+
+	/*
+	 * If the req was previously submitted but not
+	 * started, start it now
+	 */
+	if (lpbfifo.req && lpbfifo.req == req &&
+	    lpbfifo.req->defer_xfer_start) {
+		out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
+	}
+
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_start_xfer);
+
+void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+	if (lpbfifo.req == req) {
+		/* Put it into reset and clear the state */
+		bcom_gen_bd_rx_reset(lpbfifo.bcom_rx_task);
+		bcom_gen_bd_tx_reset(lpbfifo.bcom_tx_task);
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+		lpbfifo.req = NULL;
+	}
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_abort);
+
+static int mpc52xx_lpbfifo_probe(struct platform_device *op)
+{
+	struct resource res;
+	int rc = -ENOMEM;
+
+	if (lpbfifo.dev != NULL)
+		return -ENOSPC;
+
+	lpbfifo.irq = irq_of_parse_and_map(op->dev.of_node, 0);
+	if (!lpbfifo.irq)
+		return -ENODEV;
+
+	if (of_address_to_resource(op->dev.of_node, 0, &res))
+		return -ENODEV;
+	lpbfifo.regs_phys = res.start;
+	lpbfifo.regs = of_iomap(op->dev.of_node, 0);
+	if (!lpbfifo.regs)
+		return -ENOMEM;
+
+	spin_lock_init(&lpbfifo.lock);
+
+	/* Put FIFO into reset */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+
+	/* Register the interrupt handler */
+	rc = request_irq(lpbfifo.irq, mpc52xx_lpbfifo_irq, 0,
+			 "mpc52xx-lpbfifo", &lpbfifo);
+	if (rc)
+		goto err_irq;
+
+	/* Request the Bestcomm receive (fifo --> memory) task and IRQ */
+	lpbfifo.bcom_rx_task =
+		bcom_gen_bd_rx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
+				    BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC,
+				    16*1024*1024);
+	if (!lpbfifo.bcom_rx_task)
+		goto err_bcom_rx;
+
+	rc = request_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task),
+			 mpc52xx_lpbfifo_bcom_irq, 0,
+			 "mpc52xx-lpbfifo-rx", &lpbfifo);
+	if (rc)
+		goto err_bcom_rx_irq;
+
+	lpbfifo.dma_irqs_enabled = 1;
+
+	/* Request the Bestcomm transmit (memory --> fifo) task and IRQ */
+	lpbfifo.bcom_tx_task =
+		bcom_gen_bd_tx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
+				    BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC);
+	if (!lpbfifo.bcom_tx_task)
+		goto err_bcom_tx;
+
+	lpbfifo.dev = &op->dev;
+	return 0;
+
+ err_bcom_tx:
+	free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo);
+ err_bcom_rx_irq:
+	bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task);
+ err_bcom_rx:
+	free_irq(lpbfifo.irq, &lpbfifo);
+ err_irq:
+	iounmap(lpbfifo.regs);
+	lpbfifo.regs = NULL;
+
+	dev_err(&op->dev, "mpc52xx_lpbfifo_probe() failed\n");
+	return -ENODEV;
+}
+
+
+static int mpc52xx_lpbfifo_remove(struct platform_device *op)
+{
+	if (lpbfifo.dev != &op->dev)
+		return 0;
+
+	/* Put FIFO in reset */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+
+	/* Release the bestcomm transmit task */
+	free_irq(bcom_get_task_irq(lpbfifo.bcom_tx_task), &lpbfifo);
+	bcom_gen_bd_tx_release(lpbfifo.bcom_tx_task);
+	
+	/* Release the bestcomm receive task */
+	free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo);
+	bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task);
+
+	free_irq(lpbfifo.irq, &lpbfifo);
+	iounmap(lpbfifo.regs);
+	lpbfifo.regs = NULL;
+	lpbfifo.dev = NULL;
+
+	return 0;
+}
+
+static const struct of_device_id mpc52xx_lpbfifo_match[] = {
+	{ .compatible = "fsl,mpc5200-lpbfifo", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mpc52xx_lpbfifo_match);
+
+static struct platform_driver mpc52xx_lpbfifo_driver = {
+	.driver = {
+		.name = "mpc52xx-lpbfifo",
+		.of_match_table = mpc52xx_lpbfifo_match,
+	},
+	.probe = mpc52xx_lpbfifo_probe,
+	.remove = mpc52xx_lpbfifo_remove,
+};
+module_platform_driver(mpc52xx_lpbfifo_driver);