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, 629 insertions, 0 deletions

diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
new file mode 100644
index 000000000..89f25af4b
--- /dev/null
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -0,0 +1,629 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Support for OLPC XO-1 System Control Interrupts (SCI)
+ *
+ * Copyright (C) 2010 One Laptop per Child
+ * Copyright (C) 2006 Red Hat, Inc.
+ * Copyright (C) 2006 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/cs5535.h>
+#include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_wakeup.h>
+#include <linux/power_supply.h>
+#include <linux/suspend.h>
+#include <linux/workqueue.h>
+#include <linux/olpc-ec.h>
+
+#include <asm/io.h>
+#include <asm/msr.h>
+#include <asm/olpc.h>
+
+#define DRV_NAME	"olpc-xo1-sci"
+#define PFX		DRV_NAME ": "
+
+static unsigned long acpi_base;
+static struct input_dev *power_button_idev;
+static struct input_dev *ebook_switch_idev;
+static struct input_dev *lid_switch_idev;
+
+static int sci_irq;
+
+static bool lid_open;
+static bool lid_inverted;
+static int lid_wake_mode;
+
+enum lid_wake_modes {
+	LID_WAKE_ALWAYS,
+	LID_WAKE_OPEN,
+	LID_WAKE_CLOSE,
+};
+
+static const char * const lid_wake_mode_names[] = {
+	[LID_WAKE_ALWAYS] = "always",
+	[LID_WAKE_OPEN] = "open",
+	[LID_WAKE_CLOSE] = "close",
+};
+
+static void battery_status_changed(void)
+{
+	struct power_supply *psy = power_supply_get_by_name("olpc_battery");
+
+	if (psy) {
+		power_supply_changed(psy);
+		power_supply_put(psy);
+	}
+}
+
+static void ac_status_changed(void)
+{
+	struct power_supply *psy = power_supply_get_by_name("olpc_ac");
+
+	if (psy) {
+		power_supply_changed(psy);
+		power_supply_put(psy);
+	}
+}
+
+/* Report current ebook switch state through input layer */
+static void send_ebook_state(void)
+{
+	unsigned char state;
+
+	if (olpc_ec_cmd(EC_READ_EB_MODE, NULL, 0, &state, 1)) {
+		pr_err(PFX "failed to get ebook state\n");
+		return;
+	}
+
+	if (test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == !!state)
+		return; /* Nothing new to report. */
+
+	input_report_switch(ebook_switch_idev, SW_TABLET_MODE, state);
+	input_sync(ebook_switch_idev);
+	pm_wakeup_event(&ebook_switch_idev->dev, 0);
+}
+
+static void flip_lid_inverter(void)
+{
+	/* gpio is high; invert so we'll get l->h event interrupt */
+	if (lid_inverted)
+		cs5535_gpio_clear(OLPC_GPIO_LID, GPIO_INPUT_INVERT);
+	else
+		cs5535_gpio_set(OLPC_GPIO_LID, GPIO_INPUT_INVERT);
+	lid_inverted = !lid_inverted;
+}
+
+static void detect_lid_state(void)
+{
+	/*
+	 * the edge detector hookup on the gpio inputs on the geode is
+	 * odd, to say the least.  See http://dev.laptop.org/ticket/5703
+	 * for details, but in a nutshell:  we don't use the edge
+	 * detectors.  instead, we make use of an anomaly:  with the both
+	 * edge detectors turned off, we still get an edge event on a
+	 * positive edge transition.  to take advantage of this, we use the
+	 * front-end inverter to ensure that that's the edge we're always
+	 * going to see next.
+	 */
+
+	int state;
+
+	state = cs5535_gpio_isset(OLPC_GPIO_LID, GPIO_READ_BACK);
+	lid_open = !state ^ !lid_inverted; /* x ^^ y */
+	if (!state)
+		return;
+
+	flip_lid_inverter();
+}
+
+/* Report current lid switch state through input layer */
+static void send_lid_state(void)
+{
+	if (!!test_bit(SW_LID, lid_switch_idev->sw) == !lid_open)
+		return; /* Nothing new to report. */
+
+	input_report_switch(lid_switch_idev, SW_LID, !lid_open);
+	input_sync(lid_switch_idev);
+	pm_wakeup_event(&lid_switch_idev->dev, 0);
+}
+
+static ssize_t lid_wake_mode_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	const char *mode = lid_wake_mode_names[lid_wake_mode];
+	return sprintf(buf, "%s\n", mode);
+}
+static ssize_t lid_wake_mode_set(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(lid_wake_mode_names); i++) {
+		const char *mode = lid_wake_mode_names[i];
+		if (strlen(mode) != count || strncasecmp(mode, buf, count))
+			continue;
+
+		lid_wake_mode = i;
+		return count;
+	}
+	return -EINVAL;
+}
+static DEVICE_ATTR(lid_wake_mode, S_IWUSR | S_IRUGO, lid_wake_mode_show,
+		   lid_wake_mode_set);
+
+static struct attribute *lid_attrs[] = {
+	&dev_attr_lid_wake_mode.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(lid);
+
+/*
+ * Process all items in the EC's SCI queue.
+ *
+ * This is handled in a workqueue because olpc_ec_cmd can be slow (and
+ * can even timeout).
+ *
+ * If propagate_events is false, the queue is drained without events being
+ * generated for the interrupts.
+ */
+static void process_sci_queue(bool propagate_events)
+{
+	int r;
+	u16 data;
+
+	do {
+		r = olpc_ec_sci_query(&data);
+		if (r || !data)
+			break;
+
+		pr_debug(PFX "SCI 0x%x received\n", data);
+
+		switch (data) {
+		case EC_SCI_SRC_BATERR:
+		case EC_SCI_SRC_BATSOC:
+		case EC_SCI_SRC_BATTERY:
+		case EC_SCI_SRC_BATCRIT:
+			battery_status_changed();
+			break;
+		case EC_SCI_SRC_ACPWR:
+			ac_status_changed();
+			break;
+		}
+
+		if (data == EC_SCI_SRC_EBOOK && propagate_events)
+			send_ebook_state();
+	} while (data);
+
+	if (r)
+		pr_err(PFX "Failed to clear SCI queue");
+}
+
+static void process_sci_queue_work(struct work_struct *work)
+{
+	process_sci_queue(true);
+}
+
+static DECLARE_WORK(sci_work, process_sci_queue_work);
+
+static irqreturn_t xo1_sci_intr(int irq, void *dev_id)
+{
+	struct platform_device *pdev = dev_id;
+	u32 sts;
+	u32 gpe;
+
+	sts = inl(acpi_base + CS5536_PM1_STS);
+	outl(sts | 0xffff, acpi_base + CS5536_PM1_STS);
+
+	gpe = inl(acpi_base + CS5536_PM_GPE0_STS);
+	outl(0xffffffff, acpi_base + CS5536_PM_GPE0_STS);
+
+	dev_dbg(&pdev->dev, "sts %x gpe %x\n", sts, gpe);
+
+	if (sts & CS5536_PWRBTN_FLAG) {
+		if (!(sts & CS5536_WAK_FLAG)) {
+			/* Only report power button input when it was pressed
+			 * during regular operation (as opposed to when it
+			 * was used to wake the system). */
+			input_report_key(power_button_idev, KEY_POWER, 1);
+			input_sync(power_button_idev);
+			input_report_key(power_button_idev, KEY_POWER, 0);
+			input_sync(power_button_idev);
+		}
+		/* Report the wakeup event in all cases. */
+		pm_wakeup_event(&power_button_idev->dev, 0);
+	}
+
+	if ((sts & (CS5536_RTC_FLAG | CS5536_WAK_FLAG)) ==
+			(CS5536_RTC_FLAG | CS5536_WAK_FLAG)) {
+		/* When the system is woken by the RTC alarm, report the
+		 * event on the rtc device. */
+		struct device *rtc = bus_find_device_by_name(
+			&platform_bus_type, NULL, "rtc_cmos");
+		if (rtc) {
+			pm_wakeup_event(rtc, 0);
+			put_device(rtc);
+		}
+	}
+
+	if (gpe & CS5536_GPIOM7_PME_FLAG) { /* EC GPIO */
+		cs5535_gpio_set(OLPC_GPIO_ECSCI, GPIO_NEGATIVE_EDGE_STS);
+		schedule_work(&sci_work);
+	}
+
+	cs5535_gpio_set(OLPC_GPIO_LID, GPIO_NEGATIVE_EDGE_STS);
+	cs5535_gpio_set(OLPC_GPIO_LID, GPIO_POSITIVE_EDGE_STS);
+	detect_lid_state();
+	send_lid_state();
+
+	return IRQ_HANDLED;
+}
+
+static int xo1_sci_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	if (device_may_wakeup(&power_button_idev->dev))
+		olpc_xo1_pm_wakeup_set(CS5536_PM_PWRBTN);
+	else
+		olpc_xo1_pm_wakeup_clear(CS5536_PM_PWRBTN);
+
+	if (device_may_wakeup(&ebook_switch_idev->dev))
+		olpc_ec_wakeup_set(EC_SCI_SRC_EBOOK);
+	else
+		olpc_ec_wakeup_clear(EC_SCI_SRC_EBOOK);
+
+	if (!device_may_wakeup(&lid_switch_idev->dev)) {
+		cs5535_gpio_clear(OLPC_GPIO_LID, GPIO_EVENTS_ENABLE);
+	} else if ((lid_open && lid_wake_mode == LID_WAKE_OPEN) ||
+		   (!lid_open && lid_wake_mode == LID_WAKE_CLOSE)) {
+		flip_lid_inverter();
+
+		/* we may have just caused an event */
+		cs5535_gpio_set(OLPC_GPIO_LID, GPIO_NEGATIVE_EDGE_STS);
+		cs5535_gpio_set(OLPC_GPIO_LID, GPIO_POSITIVE_EDGE_STS);
+
+		cs5535_gpio_set(OLPC_GPIO_LID, GPIO_EVENTS_ENABLE);
+	}
+
+	return 0;
+}
+
+static int xo1_sci_resume(struct platform_device *pdev)
+{
+	/*
+	 * We don't know what may have happened while we were asleep.
+	 * Reestablish our lid setup so we're sure to catch all transitions.
+	 */
+	detect_lid_state();
+	send_lid_state();
+	cs5535_gpio_set(OLPC_GPIO_LID, GPIO_EVENTS_ENABLE);
+
+	/* Enable all EC events */
+	olpc_ec_mask_write(EC_SCI_SRC_ALL);
+
+	/* Power/battery status might have changed too */
+	battery_status_changed();
+	ac_status_changed();
+	return 0;
+}
+
+static int setup_sci_interrupt(struct platform_device *pdev)
+{
+	u32 lo, hi;
+	u32 sts;
+	int r;
+
+	rdmsr(0x51400020, lo, hi);
+	sci_irq = (lo >> 20) & 15;
+
+	if (sci_irq) {
+		dev_info(&pdev->dev, "SCI is mapped to IRQ %d\n", sci_irq);
+	} else {
+		/* Zero means masked */
+		dev_info(&pdev->dev, "SCI unmapped. Mapping to IRQ 3\n");
+		sci_irq = 3;
+		lo |= 0x00300000;
+		wrmsrl(0x51400020, lo);
+	}
+
+	/* Select level triggered in PIC */
+	if (sci_irq < 8) {
+		lo = inb(CS5536_PIC_INT_SEL1);
+		lo |= 1 << sci_irq;
+		outb(lo, CS5536_PIC_INT_SEL1);
+	} else {
+		lo = inb(CS5536_PIC_INT_SEL2);
+		lo |= 1 << (sci_irq - 8);
+		outb(lo, CS5536_PIC_INT_SEL2);
+	}
+
+	/* Enable interesting SCI events, and clear pending interrupts */
+	sts = inl(acpi_base + CS5536_PM1_STS);
+	outl(((CS5536_PM_PWRBTN | CS5536_PM_RTC) << 16) | 0xffff,
+	     acpi_base + CS5536_PM1_STS);
+
+	r = request_irq(sci_irq, xo1_sci_intr, 0, DRV_NAME, pdev);
+	if (r)
+		dev_err(&pdev->dev, "can't request interrupt\n");
+
+	return r;
+}
+
+static int setup_ec_sci(void)
+{
+	int r;
+
+	r = gpio_request(OLPC_GPIO_ECSCI, "OLPC-ECSCI");
+	if (r)
+		return r;
+
+	gpio_direction_input(OLPC_GPIO_ECSCI);
+
+	/* Clear pending EC SCI events */
+	cs5535_gpio_set(OLPC_GPIO_ECSCI, GPIO_NEGATIVE_EDGE_STS);
+	cs5535_gpio_set(OLPC_GPIO_ECSCI, GPIO_POSITIVE_EDGE_STS);
+
+	/*
+	 * Enable EC SCI events, and map them to both a PME and the SCI
+	 * interrupt.
+	 *
+	 * Ordinarily, in addition to functioning as GPIOs, Geode GPIOs can
+	 * be mapped to regular interrupts *or* Geode-specific Power
+	 * Management Events (PMEs) - events that bring the system out of
+	 * suspend. In this case, we want both of those things - the system
+	 * wakeup, *and* the ability to get an interrupt when an event occurs.
+	 *
+	 * To achieve this, we map the GPIO to a PME, and then we use one
+	 * of the many generic knobs on the CS5535 PIC to additionally map the
+	 * PME to the regular SCI interrupt line.
+	 */
+	cs5535_gpio_set(OLPC_GPIO_ECSCI, GPIO_EVENTS_ENABLE);
+
+	/* Set the SCI to cause a PME event on group 7 */
+	cs5535_gpio_setup_event(OLPC_GPIO_ECSCI, 7, 1);
+
+	/* And have group 7 also fire the SCI interrupt */
+	cs5535_pic_unreqz_select_high(7, sci_irq);
+
+	return 0;
+}
+
+static void free_ec_sci(void)
+{
+	gpio_free(OLPC_GPIO_ECSCI);
+}
+
+static int setup_lid_events(void)
+{
+	int r;
+
+	r = gpio_request(OLPC_GPIO_LID, "OLPC-LID");
+	if (r)
+		return r;
+
+	gpio_direction_input(OLPC_GPIO_LID);
+
+	cs5535_gpio_clear(OLPC_GPIO_LID, GPIO_INPUT_INVERT);
+	lid_inverted = 0;
+
+	/* Clear edge detection and event enable for now */
+	cs5535_gpio_clear(OLPC_GPIO_LID, GPIO_EVENTS_ENABLE);
+	cs5535_gpio_clear(OLPC_GPIO_LID, GPIO_NEGATIVE_EDGE_EN);
+	cs5535_gpio_clear(OLPC_GPIO_LID, GPIO_POSITIVE_EDGE_EN);
+	cs5535_gpio_set(OLPC_GPIO_LID, GPIO_NEGATIVE_EDGE_STS);
+	cs5535_gpio_set(OLPC_GPIO_LID, GPIO_POSITIVE_EDGE_STS);
+
+	/* Set the LID to cause an PME event on group 6 */
+	cs5535_gpio_setup_event(OLPC_GPIO_LID, 6, 1);
+
+	/* Set PME group 6 to fire the SCI interrupt */
+	cs5535_gpio_set_irq(6, sci_irq);
+
+	/* Enable the event */
+	cs5535_gpio_set(OLPC_GPIO_LID, GPIO_EVENTS_ENABLE);
+
+	return 0;
+}
+
+static void free_lid_events(void)
+{
+	gpio_free(OLPC_GPIO_LID);
+}
+
+static int setup_power_button(struct platform_device *pdev)
+{
+	int r;
+
+	power_button_idev = input_allocate_device();
+	if (!power_button_idev)
+		return -ENOMEM;
+
+	power_button_idev->name = "Power Button";
+	power_button_idev->phys = DRV_NAME "/input0";
+	set_bit(EV_KEY, power_button_idev->evbit);
+	set_bit(KEY_POWER, power_button_idev->keybit);
+
+	power_button_idev->dev.parent = &pdev->dev;
+	device_init_wakeup(&power_button_idev->dev, 1);
+
+	r = input_register_device(power_button_idev);
+	if (r) {
+		dev_err(&pdev->dev, "failed to register power button: %d\n", r);
+		input_free_device(power_button_idev);
+	}
+
+	return r;
+}
+
+static void free_power_button(void)
+{
+	input_unregister_device(power_button_idev);
+}
+
+static int setup_ebook_switch(struct platform_device *pdev)
+{
+	int r;
+
+	ebook_switch_idev = input_allocate_device();
+	if (!ebook_switch_idev)
+		return -ENOMEM;
+
+	ebook_switch_idev->name = "EBook Switch";
+	ebook_switch_idev->phys = DRV_NAME "/input1";
+	set_bit(EV_SW, ebook_switch_idev->evbit);
+	set_bit(SW_TABLET_MODE, ebook_switch_idev->swbit);
+
+	ebook_switch_idev->dev.parent = &pdev->dev;
+	device_set_wakeup_capable(&ebook_switch_idev->dev, true);
+
+	r = input_register_device(ebook_switch_idev);
+	if (r) {
+		dev_err(&pdev->dev, "failed to register ebook switch: %d\n", r);
+		input_free_device(ebook_switch_idev);
+	}
+
+	return r;
+}
+
+static void free_ebook_switch(void)
+{
+	input_unregister_device(ebook_switch_idev);
+}
+
+static int setup_lid_switch(struct platform_device *pdev)
+{
+	int r;
+
+	lid_switch_idev = input_allocate_device();
+	if (!lid_switch_idev)
+		return -ENOMEM;
+
+	lid_switch_idev->name = "Lid Switch";
+	lid_switch_idev->phys = DRV_NAME "/input2";
+	set_bit(EV_SW, lid_switch_idev->evbit);
+	set_bit(SW_LID, lid_switch_idev->swbit);
+
+	lid_switch_idev->dev.parent = &pdev->dev;
+	device_set_wakeup_capable(&lid_switch_idev->dev, true);
+
+	r = input_register_device(lid_switch_idev);
+	if (r) {
+		dev_err(&pdev->dev, "failed to register lid switch: %d\n", r);
+		goto err_register;
+	}
+
+	return 0;
+
+err_register:
+	input_free_device(lid_switch_idev);
+	return r;
+}
+
+static void free_lid_switch(void)
+{
+	input_unregister_device(lid_switch_idev);
+}
+
+static int xo1_sci_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	int r;
+
+	/* don't run on non-XOs */
+	if (!machine_is_olpc())
+		return -ENODEV;
+
+	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "can't fetch device resource info\n");
+		return -EIO;
+	}
+	acpi_base = res->start;
+
+	r = setup_power_button(pdev);
+	if (r)
+		return r;
+
+	r = setup_ebook_switch(pdev);
+	if (r)
+		goto err_ebook;
+
+	r = setup_lid_switch(pdev);
+	if (r)
+		goto err_lid;
+
+	r = setup_lid_events();
+	if (r)
+		goto err_lidevt;
+
+	r = setup_ec_sci();
+	if (r)
+		goto err_ecsci;
+
+	/* Enable PME generation for EC-generated events */
+	outl(CS5536_GPIOM6_PME_EN | CS5536_GPIOM7_PME_EN,
+		acpi_base + CS5536_PM_GPE0_EN);
+
+	/* Clear pending events */
+	outl(0xffffffff, acpi_base + CS5536_PM_GPE0_STS);
+	process_sci_queue(false);
+
+	/* Initial sync */
+	send_ebook_state();
+	detect_lid_state();
+	send_lid_state();
+
+	r = setup_sci_interrupt(pdev);
+	if (r)
+		goto err_sci;
+
+	/* Enable all EC events */
+	olpc_ec_mask_write(EC_SCI_SRC_ALL);
+
+	return r;
+
+err_sci:
+	free_ec_sci();
+err_ecsci:
+	free_lid_events();
+err_lidevt:
+	free_lid_switch();
+err_lid:
+	free_ebook_switch();
+err_ebook:
+	free_power_button();
+	return r;
+}
+
+static int xo1_sci_remove(struct platform_device *pdev)
+{
+	free_irq(sci_irq, pdev);
+	cancel_work_sync(&sci_work);
+	free_ec_sci();
+	free_lid_events();
+	free_lid_switch();
+	free_ebook_switch();
+	free_power_button();
+	acpi_base = 0;
+	return 0;
+}
+
+static struct platform_driver xo1_sci_driver = {
+	.driver = {
+		.name = "olpc-xo1-sci-acpi",
+		.dev_groups = lid_groups,
+	},
+	.probe = xo1_sci_probe,
+	.remove = xo1_sci_remove,
+	.suspend = xo1_sci_suspend,
+	.resume = xo1_sci_resume,
+};
+
+static int __init xo1_sci_init(void)
+{
+	return platform_driver_register(&xo1_sci_driver);
+}
+arch_initcall(xo1_sci_init);