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, 611 insertions, 0 deletions

diff --git a/sound/drivers/mpu401/mpu401_uart.c b/sound/drivers/mpu401/mpu401_uart.c
new file mode 100644
index 000000000..f435b9b4a
--- /dev/null
+++ b/sound/drivers/mpu401/mpu401_uart.c
@@ -0,0 +1,611 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>
+ *  Routines for control of MPU-401 in UART mode
+ *
+ *  MPU-401 supports UART mode which is not capable generate transmit
+ *  interrupts thus output is done via polling. Without interrupt,
+ *  input is done also via polling. Do not expect good performance.
+ *
+ *   13-03-2003:
+ *      Added support for different kind of hardware I/O. Build in choices
+ *      are port and mmio. For other kind of I/O, set mpu->read and
+ *      mpu->write to your own I/O functions.
+ */
+
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <sound/core.h>
+#include <sound/mpu401.h>
+
+MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
+MODULE_DESCRIPTION("Routines for control of MPU-401 in UART mode");
+MODULE_LICENSE("GPL");
+
+static void snd_mpu401_uart_input_read(struct snd_mpu401 * mpu);
+static void snd_mpu401_uart_output_write(struct snd_mpu401 * mpu);
+
+/*
+
+ */
+
+#define snd_mpu401_input_avail(mpu) \
+	(!(mpu->read(mpu, MPU401C(mpu)) & MPU401_RX_EMPTY))
+#define snd_mpu401_output_ready(mpu) \
+	(!(mpu->read(mpu, MPU401C(mpu)) & MPU401_TX_FULL))
+
+/* Build in lowlevel io */
+static void mpu401_write_port(struct snd_mpu401 *mpu, unsigned char data,
+			      unsigned long addr)
+{
+	outb(data, addr);
+}
+
+static unsigned char mpu401_read_port(struct snd_mpu401 *mpu,
+				      unsigned long addr)
+{
+	return inb(addr);
+}
+
+static void mpu401_write_mmio(struct snd_mpu401 *mpu, unsigned char data,
+			      unsigned long addr)
+{
+	writeb(data, (void __iomem *)addr);
+}
+
+static unsigned char mpu401_read_mmio(struct snd_mpu401 *mpu,
+				      unsigned long addr)
+{
+	return readb((void __iomem *)addr);
+}
+/*  */
+
+static void snd_mpu401_uart_clear_rx(struct snd_mpu401 *mpu)
+{
+	int timeout = 100000;
+	for (; timeout > 0 && snd_mpu401_input_avail(mpu); timeout--)
+		mpu->read(mpu, MPU401D(mpu));
+#ifdef CONFIG_SND_DEBUG
+	if (timeout <= 0)
+		snd_printk(KERN_ERR "cmd: clear rx timeout (status = 0x%x)\n",
+			   mpu->read(mpu, MPU401C(mpu)));
+#endif
+}
+
+static void uart_interrupt_tx(struct snd_mpu401 *mpu)
+{
+	unsigned long flags;
+
+	if (test_bit(MPU401_MODE_BIT_OUTPUT, &mpu->mode) &&
+	    test_bit(MPU401_MODE_BIT_OUTPUT_TRIGGER, &mpu->mode)) {
+		spin_lock_irqsave(&mpu->output_lock, flags);
+		snd_mpu401_uart_output_write(mpu);
+		spin_unlock_irqrestore(&mpu->output_lock, flags);
+	}
+}
+
+static void _snd_mpu401_uart_interrupt(struct snd_mpu401 *mpu)
+{
+	unsigned long flags;
+
+	if (mpu->info_flags & MPU401_INFO_INPUT) {
+		spin_lock_irqsave(&mpu->input_lock, flags);
+		if (test_bit(MPU401_MODE_BIT_INPUT, &mpu->mode))
+			snd_mpu401_uart_input_read(mpu);
+		else
+			snd_mpu401_uart_clear_rx(mpu);
+		spin_unlock_irqrestore(&mpu->input_lock, flags);
+	}
+	if (! (mpu->info_flags & MPU401_INFO_TX_IRQ))
+		/* ok. for better Tx performance try do some output
+		   when input is done */
+		uart_interrupt_tx(mpu);
+}
+
+/**
+ * snd_mpu401_uart_interrupt - generic MPU401-UART interrupt handler
+ * @irq: the irq number
+ * @dev_id: mpu401 instance
+ *
+ * Processes the interrupt for MPU401-UART i/o.
+ *
+ * Return: %IRQ_HANDLED if the interrupt was handled. %IRQ_NONE otherwise.
+ */
+irqreturn_t snd_mpu401_uart_interrupt(int irq, void *dev_id)
+{
+	struct snd_mpu401 *mpu = dev_id;
+	
+	if (!mpu)
+		return IRQ_NONE;
+	_snd_mpu401_uart_interrupt(mpu);
+	return IRQ_HANDLED;
+}
+
+EXPORT_SYMBOL(snd_mpu401_uart_interrupt);
+
+/**
+ * snd_mpu401_uart_interrupt_tx - generic MPU401-UART transmit irq handler
+ * @irq: the irq number
+ * @dev_id: mpu401 instance
+ *
+ * Processes the interrupt for MPU401-UART output.
+ *
+ * Return: %IRQ_HANDLED if the interrupt was handled. %IRQ_NONE otherwise.
+ */
+irqreturn_t snd_mpu401_uart_interrupt_tx(int irq, void *dev_id)
+{
+	struct snd_mpu401 *mpu = dev_id;
+	
+	if (!mpu)
+		return IRQ_NONE;
+	uart_interrupt_tx(mpu);
+	return IRQ_HANDLED;
+}
+
+EXPORT_SYMBOL(snd_mpu401_uart_interrupt_tx);
+
+/*
+ * timer callback
+ * reprogram the timer and call the interrupt job
+ */
+static void snd_mpu401_uart_timer(struct timer_list *t)
+{
+	struct snd_mpu401 *mpu = from_timer(mpu, t, timer);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mpu->timer_lock, flags);
+	/*mpu->mode |= MPU401_MODE_TIMER;*/
+	mod_timer(&mpu->timer,  1 + jiffies);
+	spin_unlock_irqrestore(&mpu->timer_lock, flags);
+	if (mpu->rmidi)
+		_snd_mpu401_uart_interrupt(mpu);
+}
+
+/*
+ * initialize the timer callback if not programmed yet
+ */
+static void snd_mpu401_uart_add_timer (struct snd_mpu401 *mpu, int input)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave (&mpu->timer_lock, flags);
+	if (mpu->timer_invoked == 0) {
+		timer_setup(&mpu->timer, snd_mpu401_uart_timer, 0);
+		mod_timer(&mpu->timer, 1 + jiffies);
+	} 
+	mpu->timer_invoked |= input ? MPU401_MODE_INPUT_TIMER :
+		MPU401_MODE_OUTPUT_TIMER;
+	spin_unlock_irqrestore (&mpu->timer_lock, flags);
+}
+
+/*
+ * remove the timer callback if still active
+ */
+static void snd_mpu401_uart_remove_timer (struct snd_mpu401 *mpu, int input)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave (&mpu->timer_lock, flags);
+	if (mpu->timer_invoked) {
+		mpu->timer_invoked &= input ? ~MPU401_MODE_INPUT_TIMER :
+			~MPU401_MODE_OUTPUT_TIMER;
+		if (! mpu->timer_invoked)
+			del_timer(&mpu->timer);
+	}
+	spin_unlock_irqrestore (&mpu->timer_lock, flags);
+}
+
+/*
+ * send a UART command
+ * return zero if successful, non-zero for some errors
+ */
+
+static int snd_mpu401_uart_cmd(struct snd_mpu401 * mpu, unsigned char cmd,
+			       int ack)
+{
+	unsigned long flags;
+	int timeout, ok;
+
+	spin_lock_irqsave(&mpu->input_lock, flags);
+	if (mpu->hardware != MPU401_HW_TRID4DWAVE) {
+		mpu->write(mpu, 0x00, MPU401D(mpu));
+		/*snd_mpu401_uart_clear_rx(mpu);*/
+	}
+	/* ok. standard MPU-401 initialization */
+	if (mpu->hardware != MPU401_HW_SB) {
+		for (timeout = 1000; timeout > 0 &&
+			     !snd_mpu401_output_ready(mpu); timeout--)
+			udelay(10);
+#ifdef CONFIG_SND_DEBUG
+		if (!timeout)
+			snd_printk(KERN_ERR "cmd: tx timeout (status = 0x%x)\n",
+				   mpu->read(mpu, MPU401C(mpu)));
+#endif
+	}
+	mpu->write(mpu, cmd, MPU401C(mpu));
+	if (ack && !(mpu->info_flags & MPU401_INFO_NO_ACK)) {
+		ok = 0;
+		timeout = 10000;
+		while (!ok && timeout-- > 0) {
+			if (snd_mpu401_input_avail(mpu)) {
+				if (mpu->read(mpu, MPU401D(mpu)) == MPU401_ACK)
+					ok = 1;
+			}
+		}
+		if (!ok && mpu->read(mpu, MPU401D(mpu)) == MPU401_ACK)
+			ok = 1;
+	} else
+		ok = 1;
+	spin_unlock_irqrestore(&mpu->input_lock, flags);
+	if (!ok) {
+		snd_printk(KERN_ERR "cmd: 0x%x failed at 0x%lx "
+			   "(status = 0x%x, data = 0x%x)\n", cmd, mpu->port,
+			   mpu->read(mpu, MPU401C(mpu)),
+			   mpu->read(mpu, MPU401D(mpu)));
+		return 1;
+	}
+	return 0;
+}
+
+static int snd_mpu401_do_reset(struct snd_mpu401 *mpu)
+{
+	if (snd_mpu401_uart_cmd(mpu, MPU401_RESET, 1))
+		return -EIO;
+	if (snd_mpu401_uart_cmd(mpu, MPU401_ENTER_UART, 0))
+		return -EIO;
+	return 0;
+}
+
+/*
+ * input/output open/close - protected by open_mutex in rawmidi.c
+ */
+static int snd_mpu401_uart_input_open(struct snd_rawmidi_substream *substream)
+{
+	struct snd_mpu401 *mpu;
+	int err;
+
+	mpu = substream->rmidi->private_data;
+	if (mpu->open_input) {
+		err = mpu->open_input(mpu);
+		if (err < 0)
+			return err;
+	}
+	if (! test_bit(MPU401_MODE_BIT_OUTPUT, &mpu->mode)) {
+		if (snd_mpu401_do_reset(mpu) < 0)
+			goto error_out;
+	}
+	mpu->substream_input = substream;
+	set_bit(MPU401_MODE_BIT_INPUT, &mpu->mode);
+	return 0;
+
+error_out:
+	if (mpu->open_input && mpu->close_input)
+		mpu->close_input(mpu);
+	return -EIO;
+}
+
+static int snd_mpu401_uart_output_open(struct snd_rawmidi_substream *substream)
+{
+	struct snd_mpu401 *mpu;
+	int err;
+
+	mpu = substream->rmidi->private_data;
+	if (mpu->open_output) {
+		err = mpu->open_output(mpu);
+		if (err < 0)
+			return err;
+	}
+	if (! test_bit(MPU401_MODE_BIT_INPUT, &mpu->mode)) {
+		if (snd_mpu401_do_reset(mpu) < 0)
+			goto error_out;
+	}
+	mpu->substream_output = substream;
+	set_bit(MPU401_MODE_BIT_OUTPUT, &mpu->mode);
+	return 0;
+
+error_out:
+	if (mpu->open_output && mpu->close_output)
+		mpu->close_output(mpu);
+	return -EIO;
+}
+
+static int snd_mpu401_uart_input_close(struct snd_rawmidi_substream *substream)
+{
+	struct snd_mpu401 *mpu;
+	int err = 0;
+
+	mpu = substream->rmidi->private_data;
+	clear_bit(MPU401_MODE_BIT_INPUT, &mpu->mode);
+	mpu->substream_input = NULL;
+	if (! test_bit(MPU401_MODE_BIT_OUTPUT, &mpu->mode))
+		err = snd_mpu401_uart_cmd(mpu, MPU401_RESET, 0);
+	if (mpu->close_input)
+		mpu->close_input(mpu);
+	if (err)
+		return -EIO;
+	return 0;
+}
+
+static int snd_mpu401_uart_output_close(struct snd_rawmidi_substream *substream)
+{
+	struct snd_mpu401 *mpu;
+	int err = 0;
+
+	mpu = substream->rmidi->private_data;
+	clear_bit(MPU401_MODE_BIT_OUTPUT, &mpu->mode);
+	mpu->substream_output = NULL;
+	if (! test_bit(MPU401_MODE_BIT_INPUT, &mpu->mode))
+		err = snd_mpu401_uart_cmd(mpu, MPU401_RESET, 0);
+	if (mpu->close_output)
+		mpu->close_output(mpu);
+	if (err)
+		return -EIO;
+	return 0;
+}
+
+/*
+ * trigger input callback
+ */
+static void
+snd_mpu401_uart_input_trigger(struct snd_rawmidi_substream *substream, int up)
+{
+	unsigned long flags;
+	struct snd_mpu401 *mpu;
+	int max = 64;
+
+	mpu = substream->rmidi->private_data;
+	if (up) {
+		if (! test_and_set_bit(MPU401_MODE_BIT_INPUT_TRIGGER,
+				       &mpu->mode)) {
+			/* first time - flush FIFO */
+			while (max-- > 0)
+				mpu->read(mpu, MPU401D(mpu));
+			if (mpu->info_flags & MPU401_INFO_USE_TIMER)
+				snd_mpu401_uart_add_timer(mpu, 1);
+		}
+		
+		/* read data in advance */
+		spin_lock_irqsave(&mpu->input_lock, flags);
+		snd_mpu401_uart_input_read(mpu);
+		spin_unlock_irqrestore(&mpu->input_lock, flags);
+	} else {
+		if (mpu->info_flags & MPU401_INFO_USE_TIMER)
+			snd_mpu401_uart_remove_timer(mpu, 1);
+		clear_bit(MPU401_MODE_BIT_INPUT_TRIGGER, &mpu->mode);
+	}
+
+}
+
+/*
+ * transfer input pending data
+ * call with input_lock spinlock held
+ */
+static void snd_mpu401_uart_input_read(struct snd_mpu401 * mpu)
+{
+	int max = 128;
+	unsigned char byte;
+
+	while (max-- > 0) {
+		if (! snd_mpu401_input_avail(mpu))
+			break; /* input not available */
+		byte = mpu->read(mpu, MPU401D(mpu));
+		if (test_bit(MPU401_MODE_BIT_INPUT_TRIGGER, &mpu->mode))
+			snd_rawmidi_receive(mpu->substream_input, &byte, 1);
+	}
+}
+
+/*
+ *  Tx FIFO sizes:
+ *    CS4237B			- 16 bytes
+ *    AudioDrive ES1688         - 12 bytes
+ *    S3 SonicVibes             -  8 bytes
+ *    SoundBlaster AWE 64       -  2 bytes (ugly hardware)
+ */
+
+/*
+ * write output pending bytes
+ * call with output_lock spinlock held
+ */
+static void snd_mpu401_uart_output_write(struct snd_mpu401 * mpu)
+{
+	unsigned char byte;
+	int max = 256;
+
+	do {
+		if (snd_rawmidi_transmit_peek(mpu->substream_output,
+					      &byte, 1) == 1) {
+			/*
+			 * Try twice because there is hardware that insists on
+			 * setting the output busy bit after each write.
+			 */
+			if (!snd_mpu401_output_ready(mpu) &&
+			    !snd_mpu401_output_ready(mpu))
+				break;	/* Tx FIFO full - try again later */
+			mpu->write(mpu, byte, MPU401D(mpu));
+			snd_rawmidi_transmit_ack(mpu->substream_output, 1);
+		} else {
+			snd_mpu401_uart_remove_timer (mpu, 0);
+			break;	/* no other data - leave the tx loop */
+		}
+	} while (--max > 0);
+}
+
+/*
+ * output trigger callback
+ */
+static void
+snd_mpu401_uart_output_trigger(struct snd_rawmidi_substream *substream, int up)
+{
+	unsigned long flags;
+	struct snd_mpu401 *mpu;
+
+	mpu = substream->rmidi->private_data;
+	if (up) {
+		set_bit(MPU401_MODE_BIT_OUTPUT_TRIGGER, &mpu->mode);
+
+		/* try to add the timer at each output trigger,
+		 * since the output timer might have been removed in
+		 * snd_mpu401_uart_output_write().
+		 */
+		if (! (mpu->info_flags & MPU401_INFO_TX_IRQ))
+			snd_mpu401_uart_add_timer(mpu, 0);
+
+		/* output pending data */
+		spin_lock_irqsave(&mpu->output_lock, flags);
+		snd_mpu401_uart_output_write(mpu);
+		spin_unlock_irqrestore(&mpu->output_lock, flags);
+	} else {
+		if (! (mpu->info_flags & MPU401_INFO_TX_IRQ))
+			snd_mpu401_uart_remove_timer(mpu, 0);
+		clear_bit(MPU401_MODE_BIT_OUTPUT_TRIGGER, &mpu->mode);
+	}
+}
+
+/*
+
+ */
+
+static const struct snd_rawmidi_ops snd_mpu401_uart_output =
+{
+	.open =		snd_mpu401_uart_output_open,
+	.close =	snd_mpu401_uart_output_close,
+	.trigger =	snd_mpu401_uart_output_trigger,
+};
+
+static const struct snd_rawmidi_ops snd_mpu401_uart_input =
+{
+	.open =		snd_mpu401_uart_input_open,
+	.close =	snd_mpu401_uart_input_close,
+	.trigger =	snd_mpu401_uart_input_trigger,
+};
+
+static void snd_mpu401_uart_free(struct snd_rawmidi *rmidi)
+{
+	struct snd_mpu401 *mpu = rmidi->private_data;
+	if (mpu->irq >= 0)
+		free_irq(mpu->irq, (void *) mpu);
+	release_and_free_resource(mpu->res);
+	kfree(mpu);
+}
+
+/**
+ * snd_mpu401_uart_new - create an MPU401-UART instance
+ * @card: the card instance
+ * @device: the device index, zero-based
+ * @hardware: the hardware type, MPU401_HW_XXXX
+ * @port: the base address of MPU401 port
+ * @info_flags: bitflags MPU401_INFO_XXX
+ * @irq: the ISA irq number, -1 if not to be allocated
+ * @rrawmidi: the pointer to store the new rawmidi instance
+ *
+ * Creates a new MPU-401 instance.
+ *
+ * Note that the rawmidi instance is returned on the rrawmidi argument,
+ * not the mpu401 instance itself.  To access to the mpu401 instance,
+ * cast from rawmidi->private_data (with struct snd_mpu401 magic-cast).
+ *
+ * Return: Zero if successful, or a negative error code.
+ */
+int snd_mpu401_uart_new(struct snd_card *card, int device,
+			unsigned short hardware,
+			unsigned long port,
+			unsigned int info_flags,
+			int irq,
+			struct snd_rawmidi ** rrawmidi)
+{
+	struct snd_mpu401 *mpu;
+	struct snd_rawmidi *rmidi;
+	int in_enable, out_enable;
+	int err;
+
+	if (rrawmidi)
+		*rrawmidi = NULL;
+	if (! (info_flags & (MPU401_INFO_INPUT | MPU401_INFO_OUTPUT)))
+		info_flags |= MPU401_INFO_INPUT | MPU401_INFO_OUTPUT;
+	in_enable = (info_flags & MPU401_INFO_INPUT) ? 1 : 0;
+	out_enable = (info_flags & MPU401_INFO_OUTPUT) ? 1 : 0;
+	err = snd_rawmidi_new(card, "MPU-401U", device,
+			      out_enable, in_enable, &rmidi);
+	if (err < 0)
+		return err;
+	mpu = kzalloc(sizeof(*mpu), GFP_KERNEL);
+	if (!mpu) {
+		err = -ENOMEM;
+		goto free_device;
+	}
+	rmidi->private_data = mpu;
+	rmidi->private_free = snd_mpu401_uart_free;
+	spin_lock_init(&mpu->input_lock);
+	spin_lock_init(&mpu->output_lock);
+	spin_lock_init(&mpu->timer_lock);
+	mpu->hardware = hardware;
+	mpu->irq = -1;
+	if (! (info_flags & MPU401_INFO_INTEGRATED)) {
+		int res_size = hardware == MPU401_HW_PC98II ? 4 : 2;
+		mpu->res = request_region(port, res_size, "MPU401 UART");
+		if (!mpu->res) {
+			snd_printk(KERN_ERR "mpu401_uart: "
+				   "unable to grab port 0x%lx size %d\n",
+				   port, res_size);
+			err = -EBUSY;
+			goto free_device;
+		}
+	}
+	if (info_flags & MPU401_INFO_MMIO) {
+		mpu->write = mpu401_write_mmio;
+		mpu->read = mpu401_read_mmio;
+	} else {
+		mpu->write = mpu401_write_port;
+		mpu->read = mpu401_read_port;
+	}
+	mpu->port = port;
+	if (hardware == MPU401_HW_PC98II)
+		mpu->cport = port + 2;
+	else
+		mpu->cport = port + 1;
+	if (irq >= 0) {
+		if (request_irq(irq, snd_mpu401_uart_interrupt, 0,
+				"MPU401 UART", (void *) mpu)) {
+			snd_printk(KERN_ERR "mpu401_uart: "
+				   "unable to grab IRQ %d\n", irq);
+			err = -EBUSY;
+			goto free_device;
+		}
+	}
+	if (irq < 0 && !(info_flags & MPU401_INFO_IRQ_HOOK))
+		info_flags |= MPU401_INFO_USE_TIMER;
+	mpu->info_flags = info_flags;
+	mpu->irq = irq;
+	if (card->shortname[0])
+		snprintf(rmidi->name, sizeof(rmidi->name), "%s MIDI",
+			 card->shortname);
+	else
+		sprintf(rmidi->name, "MPU-401 MIDI %d-%d",card->number, device);
+	if (out_enable) {
+		snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT,
+				    &snd_mpu401_uart_output);
+		rmidi->info_flags |= SNDRV_RAWMIDI_INFO_OUTPUT;
+	}
+	if (in_enable) {
+		snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_INPUT,
+				    &snd_mpu401_uart_input);
+		rmidi->info_flags |= SNDRV_RAWMIDI_INFO_INPUT;
+		if (out_enable)
+			rmidi->info_flags |= SNDRV_RAWMIDI_INFO_DUPLEX;
+	}
+	mpu->rmidi = rmidi;
+	if (rrawmidi)
+		*rrawmidi = rmidi;
+	return 0;
+free_device:
+	snd_device_free(card, rmidi);
+	return err;
+}
+
+EXPORT_SYMBOL(snd_mpu401_uart_new);