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, 655 insertions, 0 deletions

diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
new file mode 100644
index 000000000..e1bb6218b
--- /dev/null
+++ b/arch/x86/kvm/i8259.c
@@ -0,0 +1,655 @@
+/*
+ * 8259 interrupt controller emulation
+ *
+ * Copyright (c) 2003-2004 Fabrice Bellard
+ * Copyright (c) 2007 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:
+ *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *   Port from Qemu.
+ */
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+#include "irq.h"
+
+#include <linux/kvm_host.h>
+#include "trace.h"
+
+#define pr_pic_unimpl(fmt, ...)	\
+	pr_err_ratelimited("kvm: pic: " fmt, ## __VA_ARGS__)
+
+static void pic_irq_request(struct kvm *kvm, int level);
+
+static void pic_lock(struct kvm_pic *s)
+	__acquires(&s->lock)
+{
+	spin_lock(&s->lock);
+}
+
+static void pic_unlock(struct kvm_pic *s)
+	__releases(&s->lock)
+{
+	bool wakeup = s->wakeup_needed;
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+
+	s->wakeup_needed = false;
+
+	spin_unlock(&s->lock);
+
+	if (wakeup) {
+		kvm_for_each_vcpu(i, vcpu, s->kvm) {
+			if (kvm_apic_accept_pic_intr(vcpu)) {
+				kvm_make_request(KVM_REQ_EVENT, vcpu);
+				kvm_vcpu_kick(vcpu);
+				return;
+			}
+		}
+	}
+}
+
+static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
+{
+	s->isr &= ~(1 << irq);
+	if (s != &s->pics_state->pics[0])
+		irq += 8;
+	/*
+	 * We are dropping lock while calling ack notifiers since ack
+	 * notifier callbacks for assigned devices call into PIC recursively.
+	 * Other interrupt may be delivered to PIC while lock is dropped but
+	 * it should be safe since PIC state is already updated at this stage.
+	 */
+	pic_unlock(s->pics_state);
+	kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
+	pic_lock(s->pics_state);
+}
+
+/*
+ * set irq level. If an edge is detected, then the IRR is set to 1
+ */
+static inline int pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
+{
+	int mask, ret = 1;
+	mask = 1 << irq;
+	if (s->elcr & mask)	/* level triggered */
+		if (level) {
+			ret = !(s->irr & mask);
+			s->irr |= mask;
+			s->last_irr |= mask;
+		} else {
+			s->irr &= ~mask;
+			s->last_irr &= ~mask;
+		}
+	else	/* edge triggered */
+		if (level) {
+			if ((s->last_irr & mask) == 0) {
+				ret = !(s->irr & mask);
+				s->irr |= mask;
+			}
+			s->last_irr |= mask;
+		} else
+			s->last_irr &= ~mask;
+
+	return (s->imr & mask) ? -1 : ret;
+}
+
+/*
+ * return the highest priority found in mask (highest = smallest
+ * number). Return 8 if no irq
+ */
+static inline int get_priority(struct kvm_kpic_state *s, int mask)
+{
+	int priority;
+	if (mask == 0)
+		return 8;
+	priority = 0;
+	while ((mask & (1 << ((priority + s->priority_add) & 7))) == 0)
+		priority++;
+	return priority;
+}
+
+/*
+ * return the pic wanted interrupt. return -1 if none
+ */
+static int pic_get_irq(struct kvm_kpic_state *s)
+{
+	int mask, cur_priority, priority;
+
+	mask = s->irr & ~s->imr;
+	priority = get_priority(s, mask);
+	if (priority == 8)
+		return -1;
+	/*
+	 * compute current priority. If special fully nested mode on the
+	 * master, the IRQ coming from the slave is not taken into account
+	 * for the priority computation.
+	 */
+	mask = s->isr;
+	if (s->special_fully_nested_mode && s == &s->pics_state->pics[0])
+		mask &= ~(1 << 2);
+	cur_priority = get_priority(s, mask);
+	if (priority < cur_priority)
+		/*
+		 * higher priority found: an irq should be generated
+		 */
+		return (priority + s->priority_add) & 7;
+	else
+		return -1;
+}
+
+/*
+ * raise irq to CPU if necessary. must be called every time the active
+ * irq may change
+ */
+static void pic_update_irq(struct kvm_pic *s)
+{
+	int irq2, irq;
+
+	irq2 = pic_get_irq(&s->pics[1]);
+	if (irq2 >= 0) {
+		/*
+		 * if irq request by slave pic, signal master PIC
+		 */
+		pic_set_irq1(&s->pics[0], 2, 1);
+		pic_set_irq1(&s->pics[0], 2, 0);
+	}
+	irq = pic_get_irq(&s->pics[0]);
+	pic_irq_request(s->kvm, irq >= 0);
+}
+
+void kvm_pic_update_irq(struct kvm_pic *s)
+{
+	pic_lock(s);
+	pic_update_irq(s);
+	pic_unlock(s);
+}
+
+int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level)
+{
+	int ret, irq_level;
+
+	BUG_ON(irq < 0 || irq >= PIC_NUM_PINS);
+
+	pic_lock(s);
+	irq_level = __kvm_irq_line_state(&s->irq_states[irq],
+					 irq_source_id, level);
+	ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, irq_level);
+	pic_update_irq(s);
+	trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
+			      s->pics[irq >> 3].imr, ret == 0);
+	pic_unlock(s);
+
+	return ret;
+}
+
+void kvm_pic_clear_all(struct kvm_pic *s, int irq_source_id)
+{
+	int i;
+
+	pic_lock(s);
+	for (i = 0; i < PIC_NUM_PINS; i++)
+		__clear_bit(irq_source_id, &s->irq_states[i]);
+	pic_unlock(s);
+}
+
+/*
+ * acknowledge interrupt 'irq'
+ */
+static inline void pic_intack(struct kvm_kpic_state *s, int irq)
+{
+	s->isr |= 1 << irq;
+	/*
+	 * We don't clear a level sensitive interrupt here
+	 */
+	if (!(s->elcr & (1 << irq)))
+		s->irr &= ~(1 << irq);
+
+	if (s->auto_eoi) {
+		if (s->rotate_on_auto_eoi)
+			s->priority_add = (irq + 1) & 7;
+		pic_clear_isr(s, irq);
+	}
+
+}
+
+int kvm_pic_read_irq(struct kvm *kvm)
+{
+	int irq, irq2, intno;
+	struct kvm_pic *s = kvm->arch.vpic;
+
+	s->output = 0;
+
+	pic_lock(s);
+	irq = pic_get_irq(&s->pics[0]);
+	if (irq >= 0) {
+		pic_intack(&s->pics[0], irq);
+		if (irq == 2) {
+			irq2 = pic_get_irq(&s->pics[1]);
+			if (irq2 >= 0)
+				pic_intack(&s->pics[1], irq2);
+			else
+				/*
+				 * spurious IRQ on slave controller
+				 */
+				irq2 = 7;
+			intno = s->pics[1].irq_base + irq2;
+		} else
+			intno = s->pics[0].irq_base + irq;
+	} else {
+		/*
+		 * spurious IRQ on host controller
+		 */
+		irq = 7;
+		intno = s->pics[0].irq_base + irq;
+	}
+	pic_update_irq(s);
+	pic_unlock(s);
+
+	return intno;
+}
+
+static void kvm_pic_reset(struct kvm_kpic_state *s)
+{
+	int irq;
+	unsigned long i;
+	struct kvm_vcpu *vcpu;
+	u8 edge_irr = s->irr & ~s->elcr;
+	bool found = false;
+
+	s->last_irr = 0;
+	s->irr &= s->elcr;
+	s->imr = 0;
+	s->priority_add = 0;
+	s->special_mask = 0;
+	s->read_reg_select = 0;
+	if (!s->init4) {
+		s->special_fully_nested_mode = 0;
+		s->auto_eoi = 0;
+	}
+	s->init_state = 1;
+
+	kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
+		if (kvm_apic_accept_pic_intr(vcpu)) {
+			found = true;
+			break;
+		}
+
+
+	if (!found)
+		return;
+
+	for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
+		if (edge_irr & (1 << irq))
+			pic_clear_isr(s, irq);
+}
+
+static void pic_ioport_write(void *opaque, u32 addr, u32 val)
+{
+	struct kvm_kpic_state *s = opaque;
+	int priority, cmd, irq;
+
+	addr &= 1;
+	if (addr == 0) {
+		if (val & 0x10) {
+			s->init4 = val & 1;
+			if (val & 0x02)
+				pr_pic_unimpl("single mode not supported");
+			if (val & 0x08)
+				pr_pic_unimpl(
+						"level sensitive irq not supported");
+			kvm_pic_reset(s);
+		} else if (val & 0x08) {
+			if (val & 0x04)
+				s->poll = 1;
+			if (val & 0x02)
+				s->read_reg_select = val & 1;
+			if (val & 0x40)
+				s->special_mask = (val >> 5) & 1;
+		} else {
+			cmd = val >> 5;
+			switch (cmd) {
+			case 0:
+			case 4:
+				s->rotate_on_auto_eoi = cmd >> 2;
+				break;
+			case 1:	/* end of interrupt */
+			case 5:
+				priority = get_priority(s, s->isr);
+				if (priority != 8) {
+					irq = (priority + s->priority_add) & 7;
+					if (cmd == 5)
+						s->priority_add = (irq + 1) & 7;
+					pic_clear_isr(s, irq);
+					pic_update_irq(s->pics_state);
+				}
+				break;
+			case 3:
+				irq = val & 7;
+				pic_clear_isr(s, irq);
+				pic_update_irq(s->pics_state);
+				break;
+			case 6:
+				s->priority_add = (val + 1) & 7;
+				pic_update_irq(s->pics_state);
+				break;
+			case 7:
+				irq = val & 7;
+				s->priority_add = (irq + 1) & 7;
+				pic_clear_isr(s, irq);
+				pic_update_irq(s->pics_state);
+				break;
+			default:
+				break;	/* no operation */
+			}
+		}
+	} else
+		switch (s->init_state) {
+		case 0: { /* normal mode */
+			u8 imr_diff = s->imr ^ val,
+				off = (s == &s->pics_state->pics[0]) ? 0 : 8;
+			s->imr = val;
+			for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
+				if (imr_diff & (1 << irq))
+					kvm_fire_mask_notifiers(
+						s->pics_state->kvm,
+						SELECT_PIC(irq + off),
+						irq + off,
+						!!(s->imr & (1 << irq)));
+			pic_update_irq(s->pics_state);
+			break;
+		}
+		case 1:
+			s->irq_base = val & 0xf8;
+			s->init_state = 2;
+			break;
+		case 2:
+			if (s->init4)
+				s->init_state = 3;
+			else
+				s->init_state = 0;
+			break;
+		case 3:
+			s->special_fully_nested_mode = (val >> 4) & 1;
+			s->auto_eoi = (val >> 1) & 1;
+			s->init_state = 0;
+			break;
+		}
+}
+
+static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1)
+{
+	int ret;
+
+	ret = pic_get_irq(s);
+	if (ret >= 0) {
+		if (addr1 >> 7) {
+			s->pics_state->pics[0].isr &= ~(1 << 2);
+			s->pics_state->pics[0].irr &= ~(1 << 2);
+		}
+		s->irr &= ~(1 << ret);
+		pic_clear_isr(s, ret);
+		if (addr1 >> 7 || ret != 2)
+			pic_update_irq(s->pics_state);
+	} else {
+		ret = 0x07;
+		pic_update_irq(s->pics_state);
+	}
+
+	return ret;
+}
+
+static u32 pic_ioport_read(void *opaque, u32 addr)
+{
+	struct kvm_kpic_state *s = opaque;
+	int ret;
+
+	if (s->poll) {
+		ret = pic_poll_read(s, addr);
+		s->poll = 0;
+	} else
+		if ((addr & 1) == 0)
+			if (s->read_reg_select)
+				ret = s->isr;
+			else
+				ret = s->irr;
+		else
+			ret = s->imr;
+	return ret;
+}
+
+static void elcr_ioport_write(void *opaque, u32 val)
+{
+	struct kvm_kpic_state *s = opaque;
+	s->elcr = val & s->elcr_mask;
+}
+
+static u32 elcr_ioport_read(void *opaque)
+{
+	struct kvm_kpic_state *s = opaque;
+	return s->elcr;
+}
+
+static int picdev_write(struct kvm_pic *s,
+			 gpa_t addr, int len, const void *val)
+{
+	unsigned char data = *(unsigned char *)val;
+
+	if (len != 1) {
+		pr_pic_unimpl("non byte write\n");
+		return 0;
+	}
+	switch (addr) {
+	case 0x20:
+	case 0x21:
+		pic_lock(s);
+		pic_ioport_write(&s->pics[0], addr, data);
+		pic_unlock(s);
+		break;
+	case 0xa0:
+	case 0xa1:
+		pic_lock(s);
+		pic_ioport_write(&s->pics[1], addr, data);
+		pic_unlock(s);
+		break;
+	case 0x4d0:
+	case 0x4d1:
+		pic_lock(s);
+		elcr_ioport_write(&s->pics[addr & 1], data);
+		pic_unlock(s);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int picdev_read(struct kvm_pic *s,
+		       gpa_t addr, int len, void *val)
+{
+	unsigned char *data = (unsigned char *)val;
+
+	if (len != 1) {
+		memset(val, 0, len);
+		pr_pic_unimpl("non byte read\n");
+		return 0;
+	}
+	switch (addr) {
+	case 0x20:
+	case 0x21:
+	case 0xa0:
+	case 0xa1:
+		pic_lock(s);
+		*data = pic_ioport_read(&s->pics[addr >> 7], addr);
+		pic_unlock(s);
+		break;
+	case 0x4d0:
+	case 0x4d1:
+		pic_lock(s);
+		*data = elcr_ioport_read(&s->pics[addr & 1]);
+		pic_unlock(s);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int picdev_master_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+			       gpa_t addr, int len, const void *val)
+{
+	return picdev_write(container_of(dev, struct kvm_pic, dev_master),
+			    addr, len, val);
+}
+
+static int picdev_master_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+			      gpa_t addr, int len, void *val)
+{
+	return picdev_read(container_of(dev, struct kvm_pic, dev_master),
+			    addr, len, val);
+}
+
+static int picdev_slave_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+			      gpa_t addr, int len, const void *val)
+{
+	return picdev_write(container_of(dev, struct kvm_pic, dev_slave),
+			    addr, len, val);
+}
+
+static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+			     gpa_t addr, int len, void *val)
+{
+	return picdev_read(container_of(dev, struct kvm_pic, dev_slave),
+			    addr, len, val);
+}
+
+static int picdev_elcr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+			     gpa_t addr, int len, const void *val)
+{
+	return picdev_write(container_of(dev, struct kvm_pic, dev_elcr),
+			    addr, len, val);
+}
+
+static int picdev_elcr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
+			    gpa_t addr, int len, void *val)
+{
+	return picdev_read(container_of(dev, struct kvm_pic, dev_elcr),
+			    addr, len, val);
+}
+
+/*
+ * callback when PIC0 irq status changed
+ */
+static void pic_irq_request(struct kvm *kvm, int level)
+{
+	struct kvm_pic *s = kvm->arch.vpic;
+
+	if (!s->output)
+		s->wakeup_needed = true;
+	s->output = level;
+}
+
+static const struct kvm_io_device_ops picdev_master_ops = {
+	.read     = picdev_master_read,
+	.write    = picdev_master_write,
+};
+
+static const struct kvm_io_device_ops picdev_slave_ops = {
+	.read     = picdev_slave_read,
+	.write    = picdev_slave_write,
+};
+
+static const struct kvm_io_device_ops picdev_elcr_ops = {
+	.read     = picdev_elcr_read,
+	.write    = picdev_elcr_write,
+};
+
+int kvm_pic_init(struct kvm *kvm)
+{
+	struct kvm_pic *s;
+	int ret;
+
+	s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL_ACCOUNT);
+	if (!s)
+		return -ENOMEM;
+	spin_lock_init(&s->lock);
+	s->kvm = kvm;
+	s->pics[0].elcr_mask = 0xf8;
+	s->pics[1].elcr_mask = 0xde;
+	s->pics[0].pics_state = s;
+	s->pics[1].pics_state = s;
+
+	/*
+	 * Initialize PIO device
+	 */
+	kvm_iodevice_init(&s->dev_master, &picdev_master_ops);
+	kvm_iodevice_init(&s->dev_slave, &picdev_slave_ops);
+	kvm_iodevice_init(&s->dev_elcr, &picdev_elcr_ops);
+	mutex_lock(&kvm->slots_lock);
+	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x20, 2,
+				      &s->dev_master);
+	if (ret < 0)
+		goto fail_unlock;
+
+	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0xa0, 2, &s->dev_slave);
+	if (ret < 0)
+		goto fail_unreg_2;
+
+	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x4d0, 2, &s->dev_elcr);
+	if (ret < 0)
+		goto fail_unreg_1;
+
+	mutex_unlock(&kvm->slots_lock);
+
+	kvm->arch.vpic = s;
+
+	return 0;
+
+fail_unreg_1:
+	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_slave);
+
+fail_unreg_2:
+	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_master);
+
+fail_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	kfree(s);
+
+	return ret;
+}
+
+void kvm_pic_destroy(struct kvm *kvm)
+{
+	struct kvm_pic *vpic = kvm->arch.vpic;
+
+	if (!vpic)
+		return;
+
+	mutex_lock(&kvm->slots_lock);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
+	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_elcr);
+	mutex_unlock(&kvm->slots_lock);
+
+	kvm->arch.vpic = NULL;
+	kfree(vpic);
+}