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, 553 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
new file mode 100644
index 000000000..c8b2b4478
--- /dev/null
+++ b/arch/powerpc/kvm/e500.c
@@ -0,0 +1,553 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/44x.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/kvm_ppc.h>
+
+#include "../mm/mmu_decl.h"
+#include "booke.h"
+#include "e500.h"
+
+struct id {
+	unsigned long val;
+	struct id **pentry;
+};
+
+#define NUM_TIDS 256
+
+/*
+ * This table provide mappings from:
+ * (guestAS,guestTID,guestPR) --> ID of physical cpu
+ * guestAS	[0..1]
+ * guestTID	[0..255]
+ * guestPR	[0..1]
+ * ID		[1..255]
+ * Each vcpu keeps one vcpu_id_table.
+ */
+struct vcpu_id_table {
+	struct id id[2][NUM_TIDS][2];
+};
+
+/*
+ * This table provide reversed mappings of vcpu_id_table:
+ * ID --> address of vcpu_id_table item.
+ * Each physical core has one pcpu_id_table.
+ */
+struct pcpu_id_table {
+	struct id *entry[NUM_TIDS];
+};
+
+static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
+
+/* This variable keeps last used shadow ID on local core.
+ * The valid range of shadow ID is [1..255] */
+static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
+
+/*
+ * Allocate a free shadow id and setup a valid sid mapping in given entry.
+ * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_setup_one(struct id *entry)
+{
+	unsigned long sid;
+	int ret = -1;
+
+	sid = __this_cpu_inc_return(pcpu_last_used_sid);
+	if (sid < NUM_TIDS) {
+		__this_cpu_write(pcpu_sids.entry[sid], entry);
+		entry->val = sid;
+		entry->pentry = this_cpu_ptr(&pcpu_sids.entry[sid]);
+		ret = sid;
+	}
+
+	/*
+	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
+	 * the caller will invalidate everything and start over.
+	 *
+	 * sid > NUM_TIDS indicates a race, which we disable preemption to
+	 * avoid.
+	 */
+	WARN_ON(sid > NUM_TIDS);
+
+	return ret;
+}
+
+/*
+ * Check if given entry contain a valid shadow id mapping.
+ * An ID mapping is considered valid only if
+ * both vcpu and pcpu know this mapping.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_lookup(struct id *entry)
+{
+	if (entry && entry->val != 0 &&
+	    __this_cpu_read(pcpu_sids.entry[entry->val]) == entry &&
+	    entry->pentry == this_cpu_ptr(&pcpu_sids.entry[entry->val]))
+		return entry->val;
+	return -1;
+}
+
+/* Invalidate all id mappings on local core -- call with preempt disabled */
+static inline void local_sid_destroy_all(void)
+{
+	__this_cpu_write(pcpu_last_used_sid, 0);
+	memset(this_cpu_ptr(&pcpu_sids), 0, sizeof(pcpu_sids));
+}
+
+static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
+	return vcpu_e500->idt;
+}
+
+static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->idt);
+	vcpu_e500->idt = NULL;
+}
+
+/* Map guest pid to shadow.
+ * We use PID to keep shadow of current guest non-zero PID,
+ * and use PID1 to keep shadow of guest zero PID.
+ * So that guest tlbe with TID=0 can be accessed at any time */
+static void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	preempt_disable();
+	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu),
+			get_cur_pid(&vcpu_e500->vcpu),
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu), 0,
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	preempt_enable();
+}
+
+/* Invalidate all mappings on vcpu */
+static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/* Invalidate one ID mapping on vcpu */
+static inline void kvmppc_e500_id_table_reset_one(
+			       struct kvmppc_vcpu_e500 *vcpu_e500,
+			       int as, int pid, int pr)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+
+	BUG_ON(as >= 2);
+	BUG_ON(pid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	idt->id[as][pid][pr].val = 0;
+	idt->id[as][pid][pr].pentry = NULL;
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/*
+ * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
+ * This function first lookup if a valid mapping exists,
+ * if not, then creates a new one.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 unsigned int as, unsigned int gid,
+				 unsigned int pr, int avoid_recursion)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	int sid;
+
+	BUG_ON(as >= 2);
+	BUG_ON(gid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	sid = local_sid_lookup(&idt->id[as][gid][pr]);
+
+	while (sid <= 0) {
+		/* No mapping yet */
+		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
+		if (sid <= 0) {
+			_tlbil_all();
+			local_sid_destroy_all();
+		}
+
+		/* Update shadow pid when mappings are changed */
+		if (!avoid_recursion)
+			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+
+	return sid;
+}
+
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+				      struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	return kvmppc_e500_get_sid(to_e500(vcpu), get_tlb_ts(gtlbe),
+				   get_tlb_tid(gtlbe), get_cur_pr(vcpu), 0);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	if (vcpu->arch.pid != pid) {
+		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
+		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+}
+
+/* gtlbe must not be mapped by more than one host tlbe */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+                           struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	unsigned int pr, tid, ts;
+	int pid;
+	u32 val, eaddr;
+	unsigned long flags;
+
+	ts = get_tlb_ts(gtlbe);
+	tid = get_tlb_tid(gtlbe);
+
+	preempt_disable();
+
+	/* One guest ID may be mapped to two shadow IDs */
+	for (pr = 0; pr < 2; pr++) {
+		/*
+		 * The shadow PID can have a valid mapping on at most one
+		 * host CPU.  In the common case, it will be valid on this
+		 * CPU, in which case we do a local invalidation of the
+		 * specific address.
+		 *
+		 * If the shadow PID is not valid on the current host CPU,
+		 * we invalidate the entire shadow PID.
+		 */
+		pid = local_sid_lookup(&idt->id[ts][tid][pr]);
+		if (pid <= 0) {
+			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
+			continue;
+		}
+
+		/*
+		 * The guest is invalidating a 4K entry which is in a PID
+		 * that has a valid shadow mapping on this host CPU.  We
+		 * search host TLB to invalidate it's shadow TLB entry,
+		 * similar to __tlbil_va except that we need to look in AS1.
+		 */
+		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
+		eaddr = get_tlb_eaddr(gtlbe);
+
+		local_irq_save(flags);
+
+		mtspr(SPRN_MAS6, val);
+		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
+		val = mfspr(SPRN_MAS1);
+		if (val & MAS1_VALID) {
+			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+			asm volatile("tlbwe");
+		}
+
+		local_irq_restore(flags);
+	}
+
+	preempt_enable();
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kvmppc_e500_id_table_reset_all(vcpu_e500);
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+	/* Recalc shadow pid since MSR changes */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
+}
+
+static void kvmppc_core_vcpu_load_e500(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvmppc_booke_vcpu_load(vcpu, cpu);
+
+	/* Shadow PID may be expired on local core */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
+}
+
+static void kvmppc_core_vcpu_put_e500(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_SPE
+	if (vcpu->arch.shadow_msr & MSR_SPE)
+		kvmppc_vcpu_disable_spe(vcpu);
+#endif
+
+	kvmppc_booke_vcpu_put(vcpu);
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	int r;
+
+	if (strcmp(cur_cpu_spec->cpu_name, "e500v2") == 0)
+		r = 0;
+	else
+		r = -ENOTSUPP;
+
+	return r;
+}
+
+static void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	struct kvm_book3e_206_tlb_entry *tlbe;
+
+	/* Insert large initial mapping for guest. */
+	tlbe = get_entry(vcpu_e500, 1, 0);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
+	tlbe->mas2 = 0;
+	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
+
+	/* 4K map for serial output. Used by kernel wrapper. */
+	tlbe = get_entry(vcpu_e500, 1, 1);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
+int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	kvmppc_e500_tlb_setup(vcpu_e500);
+
+	/* Registers init */
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
+	vcpu_e500->svr = mfspr(SPRN_SVR);
+
+	vcpu->arch.cpu_type = KVM_CPU_E500V2;
+
+	return 0;
+}
+
+static int kvmppc_core_get_sregs_e500(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	sregs->u.e.features |= KVM_SREGS_E_ARCH206_MMU | KVM_SREGS_E_SPE |
+	                       KVM_SREGS_E_PM;
+	sregs->u.e.impl_id = KVM_SREGS_E_IMPL_FSL;
+
+	sregs->u.e.impl.fsl.features = 0;
+	sregs->u.e.impl.fsl.svr = vcpu_e500->svr;
+	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
+	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
+
+	sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
+	sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
+	sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
+	sregs->u.e.ivor_high[3] =
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+
+	kvmppc_get_sregs_ivor(vcpu, sregs);
+	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
+	return 0;
+}
+
+static int kvmppc_core_set_sregs_e500(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int ret;
+
+	if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
+		vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
+		vcpu_e500->hid0 = sregs->u.e.impl.fsl.hid0;
+		vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
+	}
+
+	ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+	if (ret < 0)
+		return ret;
+
+	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
+		return 0;
+
+	if (sregs->u.e.features & KVM_SREGS_E_SPE) {
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] =
+			sregs->u.e.ivor_high[0];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] =
+			sregs->u.e.ivor_high[1];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] =
+			sregs->u.e.ivor_high[2];
+	}
+
+	if (sregs->u.e.features & KVM_SREGS_E_PM) {
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] =
+			sregs->u.e.ivor_high[3];
+	}
+
+	return kvmppc_set_sregs_ivor(vcpu, sregs);
+}
+
+static int kvmppc_get_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
+				   union kvmppc_one_reg *val)
+{
+	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
+	return r;
+}
+
+static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
+				   union kvmppc_one_reg *val)
+{
+	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
+	return r;
+}
+
+static int kvmppc_core_vcpu_create_e500(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500;
+	int err;
+
+	BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0);
+	vcpu_e500 = to_e500(vcpu);
+
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+		return -ENOMEM;
+
+	err = kvmppc_e500_tlb_init(vcpu_e500);
+	if (err)
+		goto uninit_id;
+
+	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!vcpu->arch.shared) {
+		err = -ENOMEM;
+		goto uninit_tlb;
+	}
+
+	return 0;
+
+uninit_tlb:
+	kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_id:
+	kvmppc_e500_id_table_free(vcpu_e500);
+	return err;
+}
+
+static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	free_page((unsigned long)vcpu->arch.shared);
+	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvmppc_e500_id_table_free(vcpu_e500);
+}
+
+static int kvmppc_core_init_vm_e500(struct kvm *kvm)
+{
+	return 0;
+}
+
+static void kvmppc_core_destroy_vm_e500(struct kvm *kvm)
+{
+}
+
+static struct kvmppc_ops kvm_ops_e500 = {
+	.get_sregs = kvmppc_core_get_sregs_e500,
+	.set_sregs = kvmppc_core_set_sregs_e500,
+	.get_one_reg = kvmppc_get_one_reg_e500,
+	.set_one_reg = kvmppc_set_one_reg_e500,
+	.vcpu_load   = kvmppc_core_vcpu_load_e500,
+	.vcpu_put    = kvmppc_core_vcpu_put_e500,
+	.vcpu_create = kvmppc_core_vcpu_create_e500,
+	.vcpu_free   = kvmppc_core_vcpu_free_e500,
+	.init_vm = kvmppc_core_init_vm_e500,
+	.destroy_vm = kvmppc_core_destroy_vm_e500,
+	.emulate_op = kvmppc_core_emulate_op_e500,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_e500,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_e500,
+	.create_vcpu_debugfs = kvmppc_create_vcpu_debugfs_e500,
+};
+
+static int __init kvmppc_e500_init(void)
+{
+	int r, i;
+	unsigned long ivor[3];
+	/* Process remaining handlers above the generic first 16 */
+	unsigned long *handler = &kvmppc_booke_handler_addr[16];
+	unsigned long handler_len;
+	unsigned long max_ivor = 0;
+
+	r = kvmppc_core_check_processor_compat();
+	if (r)
+		goto err_out;
+
+	r = kvmppc_booke_init();
+	if (r)
+		goto err_out;
+
+	/* copy extra E500 exception handlers */
+	ivor[0] = mfspr(SPRN_IVOR32);
+	ivor[1] = mfspr(SPRN_IVOR33);
+	ivor[2] = mfspr(SPRN_IVOR34);
+	for (i = 0; i < 3; i++) {
+		if (ivor[i] > ivor[max_ivor])
+			max_ivor = i;
+
+		handler_len = handler[i + 1] - handler[i];
+		memcpy((void *)kvmppc_booke_handlers + ivor[i],
+		       (void *)handler[i], handler_len);
+	}
+	handler_len = handler[max_ivor + 1] - handler[max_ivor];
+	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
+			   ivor[max_ivor] + handler_len);
+
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+	kvm_ops_e500.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500;
+
+err_out:
+	return r;
+}
+
+static void __exit kvmppc_e500_exit(void)
+{
+	kvmppc_pr_ops = NULL;
+	kvmppc_booke_exit();
+}
+
+module_init(kvmppc_e500_init);
+module_exit(kvmppc_e500_exit);
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");