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, 751 insertions, 0 deletions

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
new file mode 100644
index 000000000..e0a7a0e7a
--- /dev/null
+++ b/arch/x86/kvm/i8254.c
@@ -0,0 +1,751 @@
+/*
+ * 8253/8254 interval timer emulation
+ *
+ * Copyright (c) 2003-2004 Fabrice Bellard
+ * Copyright (c) 2006 Intel Corporation
+ * Copyright (c) 2007 Keir Fraser, XenSource Inc
+ * Copyright (c) 2008 Intel Corporation
+ * Copyright 2009 Red Hat, Inc. and/or its affiliates.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ * Authors:
+ *   Sheng Yang <sheng.yang@intel.com>
+ *   Based on QEMU and Xen.
+ */
+
+#define pr_fmt(fmt) "pit: " fmt
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+
+#include "ioapic.h"
+#include "irq.h"
+#include "i8254.h"
+#include "x86.h"
+
+#ifndef CONFIG_X86_64
+#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
+
+#define RW_STATE_LSB 1
+#define RW_STATE_MSB 2
+#define RW_STATE_WORD0 3
+#define RW_STATE_WORD1 4
+
+static void pit_set_gate(struct kvm_pit *pit, int channel, u32 val)
+{
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
+
+	switch (c->mode) {
+	default:
+	case 0:
+	case 4:
+		/* XXX: just disable/enable counting */
+		break;
+	case 1:
+	case 2:
+	case 3:
+	case 5:
+		/* Restart counting on rising edge. */
+		if (c->gate < val)
+			c->count_load_time = ktime_get();
+		break;
+	}
+
+	c->gate = val;
+}
+
+static int pit_get_gate(struct kvm_pit *pit, int channel)
+{
+	return pit->pit_state.channels[channel].gate;
+}
+
+static s64 __kpit_elapsed(struct kvm_pit *pit)
+{
+	s64 elapsed;
+	ktime_t remaining;
+	struct kvm_kpit_state *ps = &pit->pit_state;
+
+	if (!ps->period)
+		return 0;
+
+	/*
+	 * The Counter does not stop when it reaches zero. In
+	 * Modes 0, 1, 4, and 5 the Counter ``wraps around'' to
+	 * the highest count, either FFFF hex for binary counting
+	 * or 9999 for BCD counting, and continues counting.
+	 * Modes 2 and 3 are periodic; the Counter reloads
+	 * itself with the initial count and continues counting
+	 * from there.
+	 */
+	remaining = hrtimer_get_remaining(&ps->timer);
+	elapsed = ps->period - ktime_to_ns(remaining);
+
+	return elapsed;
+}
+
+static s64 kpit_elapsed(struct kvm_pit *pit, struct kvm_kpit_channel_state *c,
+			int channel)
+{
+	if (channel == 0)
+		return __kpit_elapsed(pit);
+
+	return ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+}
+
+static int pit_get_count(struct kvm_pit *pit, int channel)
+{
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
+	s64 d, t;
+	int counter;
+
+	t = kpit_elapsed(pit, c, channel);
+	d = mul_u64_u32_div(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+
+	switch (c->mode) {
+	case 0:
+	case 1:
+	case 4:
+	case 5:
+		counter = (c->count - d) & 0xffff;
+		break;
+	case 3:
+		/* XXX: may be incorrect for odd counts */
+		counter = c->count - (mod_64((2 * d), c->count));
+		break;
+	default:
+		counter = c->count - mod_64(d, c->count);
+		break;
+	}
+	return counter;
+}
+
+static int pit_get_out(struct kvm_pit *pit, int channel)
+{
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
+	s64 d, t;
+	int out;
+
+	t = kpit_elapsed(pit, c, channel);
+	d = mul_u64_u32_div(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+
+	switch (c->mode) {
+	default:
+	case 0:
+		out = (d >= c->count);
+		break;
+	case 1:
+		out = (d < c->count);
+		break;
+	case 2:
+		out = ((mod_64(d, c->count) == 0) && (d != 0));
+		break;
+	case 3:
+		out = (mod_64(d, c->count) < ((c->count + 1) >> 1));
+		break;
+	case 4:
+	case 5:
+		out = (d == c->count);
+		break;
+	}
+
+	return out;
+}
+
+static void pit_latch_count(struct kvm_pit *pit, int channel)
+{
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
+
+	if (!c->count_latched) {
+		c->latched_count = pit_get_count(pit, channel);
+		c->count_latched = c->rw_mode;
+	}
+}
+
+static void pit_latch_status(struct kvm_pit *pit, int channel)
+{
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
+
+	if (!c->status_latched) {
+		/* TODO: Return NULL COUNT (bit 6). */
+		c->status = ((pit_get_out(pit, channel) << 7) |
+				(c->rw_mode << 4) |
+				(c->mode << 1) |
+				c->bcd);
+		c->status_latched = 1;
+	}
+}
+
+static inline struct kvm_pit *pit_state_to_pit(struct kvm_kpit_state *ps)
+{
+	return container_of(ps, struct kvm_pit, pit_state);
+}
+
+static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
+{
+	struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state,
+						 irq_ack_notifier);
+	struct kvm_pit *pit = pit_state_to_pit(ps);
+
+	atomic_set(&ps->irq_ack, 1);
+	/* irq_ack should be set before pending is read.  Order accesses with
+	 * inc(pending) in pit_timer_fn and xchg(irq_ack, 0) in pit_do_work.
+	 */
+	smp_mb();
+	if (atomic_dec_if_positive(&ps->pending) > 0)
+		kthread_queue_work(pit->worker, &pit->expired);
+}
+
+void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+	struct hrtimer *timer;
+
+	/* Somewhat arbitrarily make vcpu0 the owner of the PIT. */
+	if (vcpu->vcpu_id || !pit)
+		return;
+
+	timer = &pit->pit_state.timer;
+	mutex_lock(&pit->pit_state.lock);
+	if (hrtimer_cancel(timer))
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+	mutex_unlock(&pit->pit_state.lock);
+}
+
+static void destroy_pit_timer(struct kvm_pit *pit)
+{
+	hrtimer_cancel(&pit->pit_state.timer);
+	kthread_flush_work(&pit->expired);
+}
+
+static void pit_do_work(struct kthread_work *work)
+{
+	struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
+	struct kvm *kvm = pit->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+	struct kvm_kpit_state *ps = &pit->pit_state;
+
+	if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0))
+		return;
+
+	kvm_set_irq(kvm, pit->irq_source_id, 0, 1, false);
+	kvm_set_irq(kvm, pit->irq_source_id, 0, 0, false);
+
+	/*
+	 * Provides NMI watchdog support via Virtual Wire mode.
+	 * The route is: PIT -> LVT0 in NMI mode.
+	 *
+	 * Note: Our Virtual Wire implementation does not follow
+	 * the MP specification.  We propagate a PIT interrupt to all
+	 * VCPUs and only when LVT0 is in NMI mode.  The interrupt can
+	 * also be simultaneously delivered through PIC and IOAPIC.
+	 */
+	if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			kvm_apic_nmi_wd_deliver(vcpu);
+}
+
+static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
+{
+	struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
+	struct kvm_pit *pt = pit_state_to_pit(ps);
+
+	if (atomic_read(&ps->reinject))
+		atomic_inc(&ps->pending);
+
+	kthread_queue_work(pt->worker, &pt->expired);
+
+	if (ps->is_periodic) {
+		hrtimer_add_expires_ns(&ps->timer, ps->period);
+		return HRTIMER_RESTART;
+	} else
+		return HRTIMER_NORESTART;
+}
+
+static inline void kvm_pit_reset_reinject(struct kvm_pit *pit)
+{
+	atomic_set(&pit->pit_state.pending, 0);
+	atomic_set(&pit->pit_state.irq_ack, 1);
+}
+
+void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject)
+{
+	struct kvm_kpit_state *ps = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+
+	if (atomic_read(&ps->reinject) == reinject)
+		return;
+
+	/*
+	 * AMD SVM AVIC accelerates EOI write and does not trap.
+	 * This cause in-kernel PIT re-inject mode to fail
+	 * since it checks ps->irq_ack before kvm_set_irq()
+	 * and relies on the ack notifier to timely queue
+	 * the pt->worker work iterm and reinject the missed tick.
+	 * So, deactivate APICv when PIT is in reinject mode.
+	 */
+	if (reinject) {
+		kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PIT_REINJ);
+		/* The initial state is preserved while ps->reinject == 0. */
+		kvm_pit_reset_reinject(pit);
+		kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier);
+		kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	} else {
+		kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PIT_REINJ);
+		kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier);
+		kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	}
+
+	atomic_set(&ps->reinject, reinject);
+}
+
+static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period)
+{
+	struct kvm_kpit_state *ps = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+	s64 interval;
+
+	if (!ioapic_in_kernel(kvm) ||
+	    ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
+		return;
+
+	interval = mul_u64_u32_div(val, NSEC_PER_SEC, KVM_PIT_FREQ);
+
+	pr_debug("create pit timer, interval is %llu nsec\n", interval);
+
+	/* TODO The new value only affected after the retriggered */
+	hrtimer_cancel(&ps->timer);
+	kthread_flush_work(&pit->expired);
+	ps->period = interval;
+	ps->is_periodic = is_period;
+
+	kvm_pit_reset_reinject(pit);
+
+	/*
+	 * Do not allow the guest to program periodic timers with small
+	 * interval, since the hrtimers are not throttled by the host
+	 * scheduler.
+	 */
+	if (ps->is_periodic) {
+		s64 min_period = min_timer_period_us * 1000LL;
+
+		if (ps->period < min_period) {
+			pr_info_ratelimited(
+			    "kvm: requested %lld ns "
+			    "i8254 timer period limited to %lld ns\n",
+			    ps->period, min_period);
+			ps->period = min_period;
+		}
+	}
+
+	hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
+		      HRTIMER_MODE_ABS);
+}
+
+static void pit_load_count(struct kvm_pit *pit, int channel, u32 val)
+{
+	struct kvm_kpit_state *ps = &pit->pit_state;
+
+	pr_debug("load_count val is %u, channel is %d\n", val, channel);
+
+	/*
+	 * The largest possible initial count is 0; this is equivalent
+	 * to 216 for binary counting and 104 for BCD counting.
+	 */
+	if (val == 0)
+		val = 0x10000;
+
+	ps->channels[channel].count = val;
+
+	if (channel != 0) {
+		ps->channels[channel].count_load_time = ktime_get();
+		return;
+	}
+
+	/* Two types of timer
+	 * mode 1 is one shot, mode 2 is period, otherwise del timer */
+	switch (ps->channels[0].mode) {
+	case 0:
+	case 1:
+        /* FIXME: enhance mode 4 precision */
+	case 4:
+		create_pit_timer(pit, val, 0);
+		break;
+	case 2:
+	case 3:
+		create_pit_timer(pit, val, 1);
+		break;
+	default:
+		destroy_pit_timer(pit);
+	}
+}
+
+void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val,
+		int hpet_legacy_start)
+{
+	u8 saved_mode;
+
+	WARN_ON_ONCE(!mutex_is_locked(&pit->pit_state.lock));
+
+	if (hpet_legacy_start) {
+		/* save existing mode for later reenablement */
+		WARN_ON(channel != 0);
+		saved_mode = pit->pit_state.channels[0].mode;
+		pit->pit_state.channels[0].mode = 0xff; /* disable timer */
+		pit_load_count(pit, channel, val);
+		pit->pit_state.channels[0].mode = saved_mode;
+	} else {
+		pit_load_count(pit, channel, val);
+	}
+}
+
+static inline struct kvm_pit *dev_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, dev);
+}
+
+static inline struct kvm_pit *speaker_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, speaker_dev);
+}
+
+static inline int pit_in_range(gpa_t addr)
+{
+	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
+		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
+}
+
+static int pit_ioport_write(struct kvm_vcpu *vcpu,
+				struct kvm_io_device *this,
+			    gpa_t addr, int len, const void *data)
+{
+	struct kvm_pit *pit = dev_to_pit(this);
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	int channel, access;
+	struct kvm_kpit_channel_state *s;
+	u32 val = *(u32 *) data;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
+
+	val  &= 0xff;
+	addr &= KVM_PIT_CHANNEL_MASK;
+
+	mutex_lock(&pit_state->lock);
+
+	if (val != 0)
+		pr_debug("write addr is 0x%x, len is %d, val is 0x%x\n",
+			 (unsigned int)addr, len, val);
+
+	if (addr == 3) {
+		channel = val >> 6;
+		if (channel == 3) {
+			/* Read-Back Command. */
+			for (channel = 0; channel < 3; channel++) {
+				if (val & (2 << channel)) {
+					if (!(val & 0x20))
+						pit_latch_count(pit, channel);
+					if (!(val & 0x10))
+						pit_latch_status(pit, channel);
+				}
+			}
+		} else {
+			/* Select Counter <channel>. */
+			s = &pit_state->channels[channel];
+			access = (val >> 4) & KVM_PIT_CHANNEL_MASK;
+			if (access == 0) {
+				pit_latch_count(pit, channel);
+			} else {
+				s->rw_mode = access;
+				s->read_state = access;
+				s->write_state = access;
+				s->mode = (val >> 1) & 7;
+				if (s->mode > 5)
+					s->mode -= 4;
+				s->bcd = val & 1;
+			}
+		}
+	} else {
+		/* Write Count. */
+		s = &pit_state->channels[addr];
+		switch (s->write_state) {
+		default:
+		case RW_STATE_LSB:
+			pit_load_count(pit, addr, val);
+			break;
+		case RW_STATE_MSB:
+			pit_load_count(pit, addr, val << 8);
+			break;
+		case RW_STATE_WORD0:
+			s->write_latch = val;
+			s->write_state = RW_STATE_WORD1;
+			break;
+		case RW_STATE_WORD1:
+			pit_load_count(pit, addr, s->write_latch | (val << 8));
+			s->write_state = RW_STATE_WORD0;
+			break;
+		}
+	}
+
+	mutex_unlock(&pit_state->lock);
+	return 0;
+}
+
+static int pit_ioport_read(struct kvm_vcpu *vcpu,
+			   struct kvm_io_device *this,
+			   gpa_t addr, int len, void *data)
+{
+	struct kvm_pit *pit = dev_to_pit(this);
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	int ret, count;
+	struct kvm_kpit_channel_state *s;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
+
+	addr &= KVM_PIT_CHANNEL_MASK;
+	if (addr == 3)
+		return 0;
+
+	s = &pit_state->channels[addr];
+
+	mutex_lock(&pit_state->lock);
+
+	if (s->status_latched) {
+		s->status_latched = 0;
+		ret = s->status;
+	} else if (s->count_latched) {
+		switch (s->count_latched) {
+		default:
+		case RW_STATE_LSB:
+			ret = s->latched_count & 0xff;
+			s->count_latched = 0;
+			break;
+		case RW_STATE_MSB:
+			ret = s->latched_count >> 8;
+			s->count_latched = 0;
+			break;
+		case RW_STATE_WORD0:
+			ret = s->latched_count & 0xff;
+			s->count_latched = RW_STATE_MSB;
+			break;
+		}
+	} else {
+		switch (s->read_state) {
+		default:
+		case RW_STATE_LSB:
+			count = pit_get_count(pit, addr);
+			ret = count & 0xff;
+			break;
+		case RW_STATE_MSB:
+			count = pit_get_count(pit, addr);
+			ret = (count >> 8) & 0xff;
+			break;
+		case RW_STATE_WORD0:
+			count = pit_get_count(pit, addr);
+			ret = count & 0xff;
+			s->read_state = RW_STATE_WORD1;
+			break;
+		case RW_STATE_WORD1:
+			count = pit_get_count(pit, addr);
+			ret = (count >> 8) & 0xff;
+			s->read_state = RW_STATE_WORD0;
+			break;
+		}
+	}
+
+	if (len > sizeof(ret))
+		len = sizeof(ret);
+	memcpy(data, (char *)&ret, len);
+
+	mutex_unlock(&pit_state->lock);
+	return 0;
+}
+
+static int speaker_ioport_write(struct kvm_vcpu *vcpu,
+				struct kvm_io_device *this,
+				gpa_t addr, int len, const void *data)
+{
+	struct kvm_pit *pit = speaker_to_pit(this);
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	u32 val = *(u32 *) data;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&pit_state->lock);
+	if (val & (1 << 1))
+		pit_state->flags |= KVM_PIT_FLAGS_SPEAKER_DATA_ON;
+	else
+		pit_state->flags &= ~KVM_PIT_FLAGS_SPEAKER_DATA_ON;
+	pit_set_gate(pit, 2, val & 1);
+	mutex_unlock(&pit_state->lock);
+	return 0;
+}
+
+static int speaker_ioport_read(struct kvm_vcpu *vcpu,
+				   struct kvm_io_device *this,
+				   gpa_t addr, int len, void *data)
+{
+	struct kvm_pit *pit = speaker_to_pit(this);
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	unsigned int refresh_clock;
+	int ret;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
+
+	/* Refresh clock toggles at about 15us. We approximate as 2^14ns. */
+	refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
+
+	mutex_lock(&pit_state->lock);
+	ret = (!!(pit_state->flags & KVM_PIT_FLAGS_SPEAKER_DATA_ON) << 1) |
+		pit_get_gate(pit, 2) | (pit_get_out(pit, 2) << 5) |
+		(refresh_clock << 4);
+	if (len > sizeof(ret))
+		len = sizeof(ret);
+	memcpy(data, (char *)&ret, len);
+	mutex_unlock(&pit_state->lock);
+	return 0;
+}
+
+static void kvm_pit_reset(struct kvm_pit *pit)
+{
+	int i;
+	struct kvm_kpit_channel_state *c;
+
+	pit->pit_state.flags = 0;
+	for (i = 0; i < 3; i++) {
+		c = &pit->pit_state.channels[i];
+		c->mode = 0xff;
+		c->gate = (i != 2);
+		pit_load_count(pit, i, 0);
+	}
+
+	kvm_pit_reset_reinject(pit);
+}
+
+static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
+{
+	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
+
+	if (!mask)
+		kvm_pit_reset_reinject(pit);
+}
+
+static const struct kvm_io_device_ops pit_dev_ops = {
+	.read     = pit_ioport_read,
+	.write    = pit_ioport_write,
+};
+
+static const struct kvm_io_device_ops speaker_dev_ops = {
+	.read     = speaker_ioport_read,
+	.write    = speaker_ioport_write,
+};
+
+struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
+{
+	struct kvm_pit *pit;
+	struct kvm_kpit_state *pit_state;
+	struct pid *pid;
+	pid_t pid_nr;
+	int ret;
+
+	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL_ACCOUNT);
+	if (!pit)
+		return NULL;
+
+	pit->irq_source_id = kvm_request_irq_source_id(kvm);
+	if (pit->irq_source_id < 0)
+		goto fail_request;
+
+	mutex_init(&pit->pit_state.lock);
+
+	pid = get_pid(task_tgid(current));
+	pid_nr = pid_vnr(pid);
+	put_pid(pid);
+
+	pit->worker = kthread_create_worker(0, "kvm-pit/%d", pid_nr);
+	if (IS_ERR(pit->worker))
+		goto fail_kthread;
+
+	kthread_init_work(&pit->expired, pit_do_work);
+
+	pit->kvm = kvm;
+
+	pit_state = &pit->pit_state;
+	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	pit_state->timer.function = pit_timer_fn;
+
+	pit_state->irq_ack_notifier.gsi = 0;
+	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
+	pit->mask_notifier.func = pit_mask_notifer;
+
+	kvm_pit_reset(pit);
+
+	kvm_pit_set_reinject(pit, true);
+
+	mutex_lock(&kvm->slots_lock);
+	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
+	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS,
+				      KVM_PIT_MEM_LENGTH, &pit->dev);
+	if (ret < 0)
+		goto fail_register_pit;
+
+	if (flags & KVM_PIT_SPEAKER_DUMMY) {
+		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
+		ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS,
+					      KVM_SPEAKER_BASE_ADDRESS, 4,
+					      &pit->speaker_dev);
+		if (ret < 0)
+			goto fail_register_speaker;
+	}
+	mutex_unlock(&kvm->slots_lock);
+
+	return pit;
+
+fail_register_speaker:
+	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
+fail_register_pit:
+	mutex_unlock(&kvm->slots_lock);
+	kvm_pit_set_reinject(pit, false);
+	kthread_destroy_worker(pit->worker);
+fail_kthread:
+	kvm_free_irq_source_id(kvm, pit->irq_source_id);
+fail_request:
+	kfree(pit);
+	return NULL;
+}
+
+void kvm_free_pit(struct kvm *kvm)
+{
+	struct kvm_pit *pit = kvm->arch.vpit;
+
+	if (pit) {
+		mutex_lock(&kvm->slots_lock);
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev);
+		mutex_unlock(&kvm->slots_lock);
+		kvm_pit_set_reinject(pit, false);
+		hrtimer_cancel(&pit->pit_state.timer);
+		kthread_destroy_worker(pit->worker);
+		kvm_free_irq_source_id(kvm, pit->irq_source_id);
+		kfree(pit);
+	}
+}