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, 535 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
new file mode 100644
index 000000000..205545d82
--- /dev/null
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -0,0 +1,535 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+
+/* The host stack layout: */
+#define HOST_R1         0 /* Implied by stwu. */
+#define HOST_CALLEE_LR  4
+#define HOST_RUN        8
+/* r2 is special: it holds 'current', and it made nonvolatile in the
+ * kernel with the -ffixed-r2 gcc option. */
+#define HOST_R2         12
+#define HOST_CR         16
+#define HOST_NV_GPRS    20
+#define __HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * 4))
+#define HOST_NV_GPR(n)  __HOST_NV_GPR(__REG_##n)
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(R31) + 4)
+#define HOST_STACK_SIZE (((HOST_MIN_STACK_SIZE + 15) / 16) * 16) /* Align. */
+#define HOST_STACK_LR   (HOST_STACK_SIZE + 4) /* In caller stack frame. */
+
+#define NEED_INST_MASK ((1<<BOOKE_INTERRUPT_PROGRAM) | \
+                        (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                        (1<<BOOKE_INTERRUPT_DEBUG))
+
+#define NEED_DEAR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
+                        (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                        (1<<BOOKE_INTERRUPT_ALIGNMENT))
+
+#define NEED_ESR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
+                       (1<<BOOKE_INTERRUPT_INST_STORAGE) | \
+                       (1<<BOOKE_INTERRUPT_PROGRAM) | \
+                       (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                       (1<<BOOKE_INTERRUPT_ALIGNMENT))
+
+.macro __KVM_HANDLER ivor_nr scratch srr0
+	/* Get pointer to vcpu and record exit number. */
+	mtspr	\scratch , r4
+	mfspr   r4, SPRN_SPRG_THREAD
+	lwz     r4, THREAD_KVM_VCPU(r4)
+	stw	r3, VCPU_GPR(R3)(r4)
+	stw	r5, VCPU_GPR(R5)(r4)
+	stw	r6, VCPU_GPR(R6)(r4)
+	mfspr	r3, \scratch
+	mfctr	r5
+	stw	r3, VCPU_GPR(R4)(r4)
+	stw	r5, VCPU_CTR(r4)
+	mfspr	r3, \srr0
+	lis	r6, kvmppc_resume_host@h
+	stw	r3, VCPU_PC(r4)
+	li	r5, \ivor_nr
+	ori	r6, r6, kvmppc_resume_host@l
+	mtctr	r6
+	bctr
+.endm
+
+.macro KVM_HANDLER ivor_nr scratch srr0
+_GLOBAL(kvmppc_handler_\ivor_nr)
+	__KVM_HANDLER \ivor_nr \scratch \srr0
+.endm
+
+.macro KVM_DBG_HANDLER ivor_nr scratch srr0
+_GLOBAL(kvmppc_handler_\ivor_nr)
+	mtspr   \scratch, r4
+	mfspr	r4, SPRN_SPRG_THREAD
+	lwz	r4, THREAD_KVM_VCPU(r4)
+	stw	r3, VCPU_CRIT_SAVE(r4)
+	mfcr	r3
+	mfspr	r4, SPRN_CSRR1
+	andi.	r4, r4, MSR_PR
+	bne	1f
+	/* debug interrupt happened in enter/exit path */
+	mfspr   r4, SPRN_CSRR1
+	rlwinm  r4, r4, 0, ~MSR_DE
+	mtspr   SPRN_CSRR1, r4
+	lis	r4, 0xffff
+	ori	r4, r4, 0xffff
+	mtspr	SPRN_DBSR, r4
+	mfspr	r4, SPRN_SPRG_THREAD
+	lwz	r4, THREAD_KVM_VCPU(r4)
+	mtcr	r3
+	lwz     r3, VCPU_CRIT_SAVE(r4)
+	mfspr   r4, \scratch
+	rfci
+1:	/* debug interrupt happened in guest */
+	mtcr	r3
+	mfspr	r4, SPRN_SPRG_THREAD
+	lwz	r4, THREAD_KVM_VCPU(r4)
+	lwz     r3, VCPU_CRIT_SAVE(r4)
+	mfspr   r4, \scratch
+	__KVM_HANDLER \ivor_nr \scratch \srr0
+.endm
+
+.macro KVM_HANDLER_ADDR ivor_nr
+	.long	kvmppc_handler_\ivor_nr
+.endm
+
+.macro KVM_HANDLER_END
+	.long	kvmppc_handlers_end
+.endm
+
+_GLOBAL(kvmppc_handlers_start)
+KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK  SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_PROGRAM SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SYSCALL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_DBG_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+_GLOBAL(kvmppc_handlers_end)
+
+/* Registers:
+ *  SPRG_SCRATCH0: guest r4
+ *  r4: vcpu pointer
+ *  r5: KVM exit number
+ */
+_GLOBAL(kvmppc_resume_host)
+	mfcr	r3
+	stw	r3, VCPU_CR(r4)
+	stw	r7, VCPU_GPR(R7)(r4)
+	stw	r8, VCPU_GPR(R8)(r4)
+	stw	r9, VCPU_GPR(R9)(r4)
+
+	li	r6, 1
+	slw	r6, r6, r5
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	/* save exit time */
+1:
+	mfspr	r7, SPRN_TBRU
+	mfspr	r8, SPRN_TBRL
+	mfspr	r9, SPRN_TBRU
+	cmpw	r9, r7
+	bne	1b
+	stw	r8, VCPU_TIMING_EXIT_TBL(r4)
+	stw	r9, VCPU_TIMING_EXIT_TBU(r4)
+#endif
+
+	/* Save the faulting instruction and all GPRs for emulation. */
+	andi.	r7, r6, NEED_INST_MASK
+	beq	..skip_inst_copy
+	mfspr	r9, SPRN_SRR0
+	mfmsr	r8
+	ori	r7, r8, MSR_DS
+	mtmsr	r7
+	isync
+	lwz	r9, 0(r9)
+	mtmsr	r8
+	isync
+	stw	r9, VCPU_LAST_INST(r4)
+
+	stw	r15, VCPU_GPR(R15)(r4)
+	stw	r16, VCPU_GPR(R16)(r4)
+	stw	r17, VCPU_GPR(R17)(r4)
+	stw	r18, VCPU_GPR(R18)(r4)
+	stw	r19, VCPU_GPR(R19)(r4)
+	stw	r20, VCPU_GPR(R20)(r4)
+	stw	r21, VCPU_GPR(R21)(r4)
+	stw	r22, VCPU_GPR(R22)(r4)
+	stw	r23, VCPU_GPR(R23)(r4)
+	stw	r24, VCPU_GPR(R24)(r4)
+	stw	r25, VCPU_GPR(R25)(r4)
+	stw	r26, VCPU_GPR(R26)(r4)
+	stw	r27, VCPU_GPR(R27)(r4)
+	stw	r28, VCPU_GPR(R28)(r4)
+	stw	r29, VCPU_GPR(R29)(r4)
+	stw	r30, VCPU_GPR(R30)(r4)
+	stw	r31, VCPU_GPR(R31)(r4)
+..skip_inst_copy:
+
+	/* Also grab DEAR and ESR before the host can clobber them. */
+
+	andi.	r7, r6, NEED_DEAR_MASK
+	beq	..skip_dear
+	mfspr	r9, SPRN_DEAR
+	stw	r9, VCPU_FAULT_DEAR(r4)
+..skip_dear:
+
+	andi.	r7, r6, NEED_ESR_MASK
+	beq	..skip_esr
+	mfspr	r9, SPRN_ESR
+	stw	r9, VCPU_FAULT_ESR(r4)
+..skip_esr:
+
+	/* Save remaining volatile guest register state to vcpu. */
+	stw	r0, VCPU_GPR(R0)(r4)
+	stw	r1, VCPU_GPR(R1)(r4)
+	stw	r2, VCPU_GPR(R2)(r4)
+	stw	r10, VCPU_GPR(R10)(r4)
+	stw	r11, VCPU_GPR(R11)(r4)
+	stw	r12, VCPU_GPR(R12)(r4)
+	stw	r13, VCPU_GPR(R13)(r4)
+	stw	r14, VCPU_GPR(R14)(r4) /* We need a NV GPR below. */
+	mflr	r3
+	stw	r3, VCPU_LR(r4)
+	mfxer	r3
+	stw	r3, VCPU_XER(r4)
+
+	/* Restore host stack pointer and PID before IVPR, since the host
+	 * exception handlers use them. */
+	lwz	r1, VCPU_HOST_STACK(r4)
+	lwz	r3, VCPU_HOST_PID(r4)
+	mtspr	SPRN_PID, r3
+
+#ifdef CONFIG_PPC_85xx
+	/* we cheat and know that Linux doesn't use PID1 which is always 0 */
+	lis	r3, 0
+	mtspr	SPRN_PID1, r3
+#endif
+
+	/* Restore host IVPR before re-enabling interrupts. We cheat and know
+	 * that Linux IVPR is always 0xc0000000. */
+	lis	r3, 0xc000
+	mtspr	SPRN_IVPR, r3
+
+	/* Switch to kernel stack and jump to handler. */
+	LOAD_REG_ADDR(r3, kvmppc_handle_exit)
+	mtctr	r3
+	mr	r3, r4
+	lwz	r2, HOST_R2(r1)
+	mr	r14, r4 /* Save vcpu pointer. */
+
+	bctrl	/* kvmppc_handle_exit() */
+
+	/* Restore vcpu pointer and the nonvolatiles we used. */
+	mr	r4, r14
+	lwz	r14, VCPU_GPR(R14)(r4)
+
+	/* Sometimes instruction emulation must restore complete GPR state. */
+	andi.	r5, r3, RESUME_FLAG_NV
+	beq	..skip_nv_load
+	lwz	r15, VCPU_GPR(R15)(r4)
+	lwz	r16, VCPU_GPR(R16)(r4)
+	lwz	r17, VCPU_GPR(R17)(r4)
+	lwz	r18, VCPU_GPR(R18)(r4)
+	lwz	r19, VCPU_GPR(R19)(r4)
+	lwz	r20, VCPU_GPR(R20)(r4)
+	lwz	r21, VCPU_GPR(R21)(r4)
+	lwz	r22, VCPU_GPR(R22)(r4)
+	lwz	r23, VCPU_GPR(R23)(r4)
+	lwz	r24, VCPU_GPR(R24)(r4)
+	lwz	r25, VCPU_GPR(R25)(r4)
+	lwz	r26, VCPU_GPR(R26)(r4)
+	lwz	r27, VCPU_GPR(R27)(r4)
+	lwz	r28, VCPU_GPR(R28)(r4)
+	lwz	r29, VCPU_GPR(R29)(r4)
+	lwz	r30, VCPU_GPR(R30)(r4)
+	lwz	r31, VCPU_GPR(R31)(r4)
+..skip_nv_load:
+
+	/* Should we return to the guest? */
+	andi.	r5, r3, RESUME_FLAG_HOST
+	beq	lightweight_exit
+
+	srawi	r3, r3, 2 /* Shift -ERR back down. */
+
+heavyweight_exit:
+	/* Not returning to guest. */
+
+#ifdef CONFIG_SPE
+	/* save guest SPEFSCR and load host SPEFSCR */
+	mfspr	r9, SPRN_SPEFSCR
+	stw	r9, VCPU_SPEFSCR(r4)
+	lwz	r9, VCPU_HOST_SPEFSCR(r4)
+	mtspr	SPRN_SPEFSCR, r9
+#endif
+
+	/* We already saved guest volatile register state; now save the
+	 * non-volatiles. */
+	stw	r15, VCPU_GPR(R15)(r4)
+	stw	r16, VCPU_GPR(R16)(r4)
+	stw	r17, VCPU_GPR(R17)(r4)
+	stw	r18, VCPU_GPR(R18)(r4)
+	stw	r19, VCPU_GPR(R19)(r4)
+	stw	r20, VCPU_GPR(R20)(r4)
+	stw	r21, VCPU_GPR(R21)(r4)
+	stw	r22, VCPU_GPR(R22)(r4)
+	stw	r23, VCPU_GPR(R23)(r4)
+	stw	r24, VCPU_GPR(R24)(r4)
+	stw	r25, VCPU_GPR(R25)(r4)
+	stw	r26, VCPU_GPR(R26)(r4)
+	stw	r27, VCPU_GPR(R27)(r4)
+	stw	r28, VCPU_GPR(R28)(r4)
+	stw	r29, VCPU_GPR(R29)(r4)
+	stw	r30, VCPU_GPR(R30)(r4)
+	stw	r31, VCPU_GPR(R31)(r4)
+
+	/* Load host non-volatile register state from host stack. */
+	lwz	r14, HOST_NV_GPR(R14)(r1)
+	lwz	r15, HOST_NV_GPR(R15)(r1)
+	lwz	r16, HOST_NV_GPR(R16)(r1)
+	lwz	r17, HOST_NV_GPR(R17)(r1)
+	lwz	r18, HOST_NV_GPR(R18)(r1)
+	lwz	r19, HOST_NV_GPR(R19)(r1)
+	lwz	r20, HOST_NV_GPR(R20)(r1)
+	lwz	r21, HOST_NV_GPR(R21)(r1)
+	lwz	r22, HOST_NV_GPR(R22)(r1)
+	lwz	r23, HOST_NV_GPR(R23)(r1)
+	lwz	r24, HOST_NV_GPR(R24)(r1)
+	lwz	r25, HOST_NV_GPR(R25)(r1)
+	lwz	r26, HOST_NV_GPR(R26)(r1)
+	lwz	r27, HOST_NV_GPR(R27)(r1)
+	lwz	r28, HOST_NV_GPR(R28)(r1)
+	lwz	r29, HOST_NV_GPR(R29)(r1)
+	lwz	r30, HOST_NV_GPR(R30)(r1)
+	lwz	r31, HOST_NV_GPR(R31)(r1)
+
+	/* Return to kvm_vcpu_run(). */
+	lwz	r4, HOST_STACK_LR(r1)
+	lwz	r5, HOST_CR(r1)
+	addi	r1, r1, HOST_STACK_SIZE
+	mtlr	r4
+	mtcr	r5
+	/* r3 still contains the return code from kvmppc_handle_exit(). */
+	blr
+
+
+/* Registers:
+ *  r3: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcpu_run)
+	stwu	r1, -HOST_STACK_SIZE(r1)
+	stw	r1, VCPU_HOST_STACK(r3)	/* Save stack pointer to vcpu. */
+
+	/* Save host state to stack. */
+	mr	r4, r3
+	mflr	r3
+	stw	r3, HOST_STACK_LR(r1)
+	mfcr	r5
+	stw	r5, HOST_CR(r1)
+
+	/* Save host non-volatile register state to stack. */
+	stw	r14, HOST_NV_GPR(R14)(r1)
+	stw	r15, HOST_NV_GPR(R15)(r1)
+	stw	r16, HOST_NV_GPR(R16)(r1)
+	stw	r17, HOST_NV_GPR(R17)(r1)
+	stw	r18, HOST_NV_GPR(R18)(r1)
+	stw	r19, HOST_NV_GPR(R19)(r1)
+	stw	r20, HOST_NV_GPR(R20)(r1)
+	stw	r21, HOST_NV_GPR(R21)(r1)
+	stw	r22, HOST_NV_GPR(R22)(r1)
+	stw	r23, HOST_NV_GPR(R23)(r1)
+	stw	r24, HOST_NV_GPR(R24)(r1)
+	stw	r25, HOST_NV_GPR(R25)(r1)
+	stw	r26, HOST_NV_GPR(R26)(r1)
+	stw	r27, HOST_NV_GPR(R27)(r1)
+	stw	r28, HOST_NV_GPR(R28)(r1)
+	stw	r29, HOST_NV_GPR(R29)(r1)
+	stw	r30, HOST_NV_GPR(R30)(r1)
+	stw	r31, HOST_NV_GPR(R31)(r1)
+
+	/* Load guest non-volatiles. */
+	lwz	r14, VCPU_GPR(R14)(r4)
+	lwz	r15, VCPU_GPR(R15)(r4)
+	lwz	r16, VCPU_GPR(R16)(r4)
+	lwz	r17, VCPU_GPR(R17)(r4)
+	lwz	r18, VCPU_GPR(R18)(r4)
+	lwz	r19, VCPU_GPR(R19)(r4)
+	lwz	r20, VCPU_GPR(R20)(r4)
+	lwz	r21, VCPU_GPR(R21)(r4)
+	lwz	r22, VCPU_GPR(R22)(r4)
+	lwz	r23, VCPU_GPR(R23)(r4)
+	lwz	r24, VCPU_GPR(R24)(r4)
+	lwz	r25, VCPU_GPR(R25)(r4)
+	lwz	r26, VCPU_GPR(R26)(r4)
+	lwz	r27, VCPU_GPR(R27)(r4)
+	lwz	r28, VCPU_GPR(R28)(r4)
+	lwz	r29, VCPU_GPR(R29)(r4)
+	lwz	r30, VCPU_GPR(R30)(r4)
+	lwz	r31, VCPU_GPR(R31)(r4)
+
+#ifdef CONFIG_SPE
+	/* save host SPEFSCR and load guest SPEFSCR */
+	mfspr	r3, SPRN_SPEFSCR
+	stw	r3, VCPU_HOST_SPEFSCR(r4)
+	lwz	r3, VCPU_SPEFSCR(r4)
+	mtspr	SPRN_SPEFSCR, r3
+#endif
+
+lightweight_exit:
+	stw	r2, HOST_R2(r1)
+
+	mfspr	r3, SPRN_PID
+	stw	r3, VCPU_HOST_PID(r4)
+	lwz	r3, VCPU_SHADOW_PID(r4)
+	mtspr	SPRN_PID, r3
+
+#ifdef CONFIG_PPC_85xx
+	lwz	r3, VCPU_SHADOW_PID1(r4)
+	mtspr	SPRN_PID1, r3
+#endif
+
+	/* Load some guest volatiles. */
+	lwz	r0, VCPU_GPR(R0)(r4)
+	lwz	r2, VCPU_GPR(R2)(r4)
+	lwz	r9, VCPU_GPR(R9)(r4)
+	lwz	r10, VCPU_GPR(R10)(r4)
+	lwz	r11, VCPU_GPR(R11)(r4)
+	lwz	r12, VCPU_GPR(R12)(r4)
+	lwz	r13, VCPU_GPR(R13)(r4)
+	lwz	r3, VCPU_LR(r4)
+	mtlr	r3
+	lwz	r3, VCPU_XER(r4)
+	mtxer	r3
+
+	/* Switch the IVPR. XXX If we take a TLB miss after this we're screwed,
+	 * so how do we make sure vcpu won't fault? */
+	lis	r8, kvmppc_booke_handlers@ha
+	lwz	r8, kvmppc_booke_handlers@l(r8)
+	mtspr	SPRN_IVPR, r8
+
+	lwz	r5, VCPU_SHARED(r4)
+
+	/* Can't switch the stack pointer until after IVPR is switched,
+	 * because host interrupt handlers would get confused. */
+	lwz	r1, VCPU_GPR(R1)(r4)
+
+	/*
+	 * Host interrupt handlers may have clobbered these
+	 * guest-readable SPRGs, or the guest kernel may have
+	 * written directly to the shared area, so we
+	 * need to reload them here with the guest's values.
+	 */
+	PPC_LD(r3, VCPU_SHARED_SPRG4, r5)
+	mtspr	SPRN_SPRG4W, r3
+	PPC_LD(r3, VCPU_SHARED_SPRG5, r5)
+	mtspr	SPRN_SPRG5W, r3
+	PPC_LD(r3, VCPU_SHARED_SPRG6, r5)
+	mtspr	SPRN_SPRG6W, r3
+	PPC_LD(r3, VCPU_SHARED_SPRG7, r5)
+	mtspr	SPRN_SPRG7W, r3
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	/* save enter time */
+1:
+	mfspr	r6, SPRN_TBRU
+	mfspr	r7, SPRN_TBRL
+	mfspr	r8, SPRN_TBRU
+	cmpw	r8, r6
+	bne	1b
+	stw	r7, VCPU_TIMING_LAST_ENTER_TBL(r4)
+	stw	r8, VCPU_TIMING_LAST_ENTER_TBU(r4)
+#endif
+
+	/* Finish loading guest volatiles and jump to guest. */
+	lwz	r3, VCPU_CTR(r4)
+	lwz	r5, VCPU_CR(r4)
+	lwz	r6, VCPU_PC(r4)
+	lwz	r7, VCPU_SHADOW_MSR(r4)
+	mtctr	r3
+	mtcr	r5
+	mtsrr0	r6
+	mtsrr1	r7
+	lwz	r5, VCPU_GPR(R5)(r4)
+	lwz	r6, VCPU_GPR(R6)(r4)
+	lwz	r7, VCPU_GPR(R7)(r4)
+	lwz	r8, VCPU_GPR(R8)(r4)
+
+	/* Clear any debug events which occurred since we disabled MSR[DE].
+	 * XXX This gives us a 3-instruction window in which a breakpoint
+	 * intended for guest context could fire in the host instead. */
+	lis	r3, 0xffff
+	ori	r3, r3, 0xffff
+	mtspr	SPRN_DBSR, r3
+
+	lwz	r3, VCPU_GPR(R3)(r4)
+	lwz	r4, VCPU_GPR(R4)(r4)
+	rfi
+
+	.data
+	.align	4
+	.globl	kvmppc_booke_handler_addr
+kvmppc_booke_handler_addr:
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_CRITICAL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_MACHINE_CHECK
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DATA_STORAGE
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_INST_STORAGE
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_EXTERNAL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_ALIGNMENT
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_PROGRAM
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_FP_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SYSCALL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_AP_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DECREMENTER
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_FIT
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_WATCHDOG
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DTLB_MISS
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_ITLB_MISS
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DEBUG
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_FP_DATA
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_FP_ROUND
+KVM_HANDLER_END /*Always keep this in end*/
+
+#ifdef CONFIG_SPE
+_GLOBAL(kvmppc_save_guest_spe)
+	cmpi	0,r3,0
+	beqlr-
+	SAVE_32EVRS(0, r4, r3, VCPU_EVR)
+	evxor   evr6, evr6, evr6
+	evmwumiaa evr6, evr6, evr6
+	li	r4,VCPU_ACC
+	evstddx evr6, r4, r3		/* save acc */
+	blr
+
+_GLOBAL(kvmppc_load_guest_spe)
+	cmpi	0,r3,0
+	beqlr-
+	li      r4,VCPU_ACC
+	evlddx  evr6,r4,r3
+	evmra   evr6,evr6		/* load acc */
+	REST_32EVRS(0, r4, r3, VCPU_EVR)
+	blr
+#endif