diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2008-04-27 17:13:52 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-04-27 17:13:52 (GMT) |
commit | 42cadc86008aae0fd9ff31642dc01ed50723cf32 (patch) | |
tree | b05d4c8f0561bad5a0183a89fb23ce4c8ee1653c /include | |
parent | fba5c1af5c4fd6645fe62ea84ccde0981282cf66 (diff) | |
parent | 66c0b394f08fd89236515c1c84485ea712a157be (diff) | |
download | linux-fsl-qoriq-42cadc86008aae0fd9ff31642dc01ed50723cf32.tar.xz |
Merge branch 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm
* 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (147 commits)
KVM: kill file->f_count abuse in kvm
KVM: MMU: kvm_pv_mmu_op should not take mmap_sem
KVM: SVM: remove selective CR0 comment
KVM: SVM: remove now obsolete FIXME comment
KVM: SVM: disable CR8 intercept when tpr is not masking interrupts
KVM: SVM: sync V_TPR with LAPIC.TPR if CR8 write intercept is disabled
KVM: export kvm_lapic_set_tpr() to modules
KVM: SVM: sync TPR value to V_TPR field in the VMCB
KVM: ppc: PowerPC 440 KVM implementation
KVM: Add MAINTAINERS entry for PowerPC KVM
KVM: ppc: Add DCR access information to struct kvm_run
ppc: Export tlb_44x_hwater for KVM
KVM: Rename debugfs_dir to kvm_debugfs_dir
KVM: x86 emulator: fix lea to really get the effective address
KVM: x86 emulator: fix smsw and lmsw with a memory operand
KVM: x86 emulator: initialize src.val and dst.val for register operands
KVM: SVM: force a new asid when initializing the vmcb
KVM: fix kvm_vcpu_kick vs __vcpu_run race
KVM: add ioctls to save/store mpstate
KVM: Rename VCPU_MP_STATE_* to KVM_MP_STATE_*
...
Diffstat (limited to 'include')
30 files changed, 2173 insertions, 45 deletions
diff --git a/include/asm-ia64/gcc_intrin.h b/include/asm-ia64/gcc_intrin.h index de2ed2c..2fe292c 100644 --- a/include/asm-ia64/gcc_intrin.h +++ b/include/asm-ia64/gcc_intrin.h @@ -21,6 +21,10 @@ #define ia64_invala_fr(regnum) asm volatile ("invala.e f%0" :: "i"(regnum)) +#define ia64_flushrs() asm volatile ("flushrs;;":::"memory") + +#define ia64_loadrs() asm volatile ("loadrs;;":::"memory") + extern void ia64_bad_param_for_setreg (void); extern void ia64_bad_param_for_getreg (void); @@ -517,6 +521,14 @@ do { \ #define ia64_ptrd(addr, size) \ asm volatile ("ptr.d %0,%1" :: "r"(addr), "r"(size) : "memory") +#define ia64_ttag(addr) \ +({ \ + __u64 ia64_intri_res; \ + asm volatile ("ttag %0=%1" : "=r"(ia64_intri_res) : "r" (addr)); \ + ia64_intri_res; \ +}) + + /* Values for lfhint in ia64_lfetch and ia64_lfetch_fault */ #define ia64_lfhint_none 0 diff --git a/include/asm-ia64/kvm.h b/include/asm-ia64/kvm.h index 030d29b..eb2d355 100644 --- a/include/asm-ia64/kvm.h +++ b/include/asm-ia64/kvm.h @@ -1,6 +1,205 @@ -#ifndef __LINUX_KVM_IA64_H -#define __LINUX_KVM_IA64_H +#ifndef __ASM_IA64_KVM_H +#define __ASM_IA64_KVM_H -/* ia64 does not support KVM */ +/* + * asm-ia64/kvm.h: kvm structure definitions for ia64 + * + * Copyright (C) 2007 Xiantao Zhang <xiantao.zhang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#include <asm/types.h> +#include <asm/fpu.h> + +#include <linux/ioctl.h> + +/* Architectural interrupt line count. */ +#define KVM_NR_INTERRUPTS 256 + +#define KVM_IOAPIC_NUM_PINS 24 + +struct kvm_ioapic_state { + __u64 base_address; + __u32 ioregsel; + __u32 id; + __u32 irr; + __u32 pad; + union { + __u64 bits; + struct { + __u8 vector; + __u8 delivery_mode:3; + __u8 dest_mode:1; + __u8 delivery_status:1; + __u8 polarity:1; + __u8 remote_irr:1; + __u8 trig_mode:1; + __u8 mask:1; + __u8 reserve:7; + __u8 reserved[4]; + __u8 dest_id; + } fields; + } redirtbl[KVM_IOAPIC_NUM_PINS]; +}; + +#define KVM_IRQCHIP_PIC_MASTER 0 +#define KVM_IRQCHIP_PIC_SLAVE 1 +#define KVM_IRQCHIP_IOAPIC 2 + +#define KVM_CONTEXT_SIZE 8*1024 + +union context { + /* 8K size */ + char dummy[KVM_CONTEXT_SIZE]; + struct { + unsigned long psr; + unsigned long pr; + unsigned long caller_unat; + unsigned long pad; + unsigned long gr[32]; + unsigned long ar[128]; + unsigned long br[8]; + unsigned long cr[128]; + unsigned long rr[8]; + unsigned long ibr[8]; + unsigned long dbr[8]; + unsigned long pkr[8]; + struct ia64_fpreg fr[128]; + }; +}; + +struct thash_data { + union { + struct { + unsigned long p : 1; /* 0 */ + unsigned long rv1 : 1; /* 1 */ + unsigned long ma : 3; /* 2-4 */ + unsigned long a : 1; /* 5 */ + unsigned long d : 1; /* 6 */ + unsigned long pl : 2; /* 7-8 */ + unsigned long ar : 3; /* 9-11 */ + unsigned long ppn : 38; /* 12-49 */ + unsigned long rv2 : 2; /* 50-51 */ + unsigned long ed : 1; /* 52 */ + unsigned long ig1 : 11; /* 53-63 */ + }; + struct { + unsigned long __rv1 : 53; /* 0-52 */ + unsigned long contiguous : 1; /*53 */ + unsigned long tc : 1; /* 54 TR or TC */ + unsigned long cl : 1; + /* 55 I side or D side cache line */ + unsigned long len : 4; /* 56-59 */ + unsigned long io : 1; /* 60 entry is for io or not */ + unsigned long nomap : 1; + /* 61 entry cann't be inserted into machine TLB.*/ + unsigned long checked : 1; + /* 62 for VTLB/VHPT sanity check */ + unsigned long invalid : 1; + /* 63 invalid entry */ + }; + unsigned long page_flags; + }; /* same for VHPT and TLB */ + + union { + struct { + unsigned long rv3 : 2; + unsigned long ps : 6; + unsigned long key : 24; + unsigned long rv4 : 32; + }; + unsigned long itir; + }; + union { + struct { + unsigned long ig2 : 12; + unsigned long vpn : 49; + unsigned long vrn : 3; + }; + unsigned long ifa; + unsigned long vadr; + struct { + unsigned long tag : 63; + unsigned long ti : 1; + }; + unsigned long etag; + }; + union { + struct thash_data *next; + unsigned long rid; + unsigned long gpaddr; + }; +}; + +#define NITRS 8 +#define NDTRS 8 + +struct saved_vpd { + unsigned long vhpi; + unsigned long vgr[16]; + unsigned long vbgr[16]; + unsigned long vnat; + unsigned long vbnat; + unsigned long vcpuid[5]; + unsigned long vpsr; + unsigned long vpr; + unsigned long vcr[128]; +}; + +struct kvm_regs { + char *saved_guest; + char *saved_stack; + struct saved_vpd vpd; + /*Arch-regs*/ + int mp_state; + unsigned long vmm_rr; + /* TR and TC. */ + struct thash_data itrs[NITRS]; + struct thash_data dtrs[NDTRS]; + /* Bit is set if there is a tr/tc for the region. */ + unsigned char itr_regions; + unsigned char dtr_regions; + unsigned char tc_regions; + + char irq_check; + unsigned long saved_itc; + unsigned long itc_check; + unsigned long timer_check; + unsigned long timer_pending; + unsigned long last_itc; + + unsigned long vrr[8]; + unsigned long ibr[8]; + unsigned long dbr[8]; + unsigned long insvc[4]; /* Interrupt in service. */ + unsigned long xtp; + + unsigned long metaphysical_rr0; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_rr4; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_saved_rr0; /* from kvm_arch */ + unsigned long metaphysical_saved_rr4; /* from kvm_arch */ + unsigned long fp_psr; /*used for lazy float register */ + unsigned long saved_gp; + /*for phycial emulation */ +}; + +struct kvm_sregs { +}; + +struct kvm_fpu { +}; #endif diff --git a/include/asm-ia64/kvm_host.h b/include/asm-ia64/kvm_host.h new file mode 100644 index 0000000..c082c20 --- /dev/null +++ b/include/asm-ia64/kvm_host.h @@ -0,0 +1,524 @@ +/* + * kvm_host.h: used for kvm module, and hold ia64-specific sections. + * + * Copyright (C) 2007, Intel Corporation. + * + * Xiantao Zhang <xiantao.zhang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#ifndef __ASM_KVM_HOST_H +#define __ASM_KVM_HOST_H + + +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/kvm.h> +#include <linux/kvm_para.h> +#include <linux/kvm_types.h> + +#include <asm/pal.h> +#include <asm/sal.h> + +#define KVM_MAX_VCPUS 4 +#define KVM_MEMORY_SLOTS 32 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + + +/* define exit reasons from vmm to kvm*/ +#define EXIT_REASON_VM_PANIC 0 +#define EXIT_REASON_MMIO_INSTRUCTION 1 +#define EXIT_REASON_PAL_CALL 2 +#define EXIT_REASON_SAL_CALL 3 +#define EXIT_REASON_SWITCH_RR6 4 +#define EXIT_REASON_VM_DESTROY 5 +#define EXIT_REASON_EXTERNAL_INTERRUPT 6 +#define EXIT_REASON_IPI 7 +#define EXIT_REASON_PTC_G 8 + +/*Define vmm address space and vm data space.*/ +#define KVM_VMM_SIZE (16UL<<20) +#define KVM_VMM_SHIFT 24 +#define KVM_VMM_BASE 0xD000000000000000UL +#define VMM_SIZE (8UL<<20) + +/* + * Define vm_buffer, used by PAL Services, base address. + * Note: vmbuffer is in the VMM-BLOCK, the size must be < 8M + */ +#define KVM_VM_BUFFER_BASE (KVM_VMM_BASE + VMM_SIZE) +#define KVM_VM_BUFFER_SIZE (8UL<<20) + +/*Define Virtual machine data layout.*/ +#define KVM_VM_DATA_SHIFT 24 +#define KVM_VM_DATA_SIZE (1UL << KVM_VM_DATA_SHIFT) +#define KVM_VM_DATA_BASE (KVM_VMM_BASE + KVM_VMM_SIZE) + + +#define KVM_P2M_BASE KVM_VM_DATA_BASE +#define KVM_P2M_OFS 0 +#define KVM_P2M_SIZE (8UL << 20) + +#define KVM_VHPT_BASE (KVM_P2M_BASE + KVM_P2M_SIZE) +#define KVM_VHPT_OFS KVM_P2M_SIZE +#define KVM_VHPT_BLOCK_SIZE (2UL << 20) +#define VHPT_SHIFT 18 +#define VHPT_SIZE (1UL << VHPT_SHIFT) +#define VHPT_NUM_ENTRIES (1<<(VHPT_SHIFT-5)) + +#define KVM_VTLB_BASE (KVM_VHPT_BASE+KVM_VHPT_BLOCK_SIZE) +#define KVM_VTLB_OFS (KVM_VHPT_OFS+KVM_VHPT_BLOCK_SIZE) +#define KVM_VTLB_BLOCK_SIZE (1UL<<20) +#define VTLB_SHIFT 17 +#define VTLB_SIZE (1UL<<VTLB_SHIFT) +#define VTLB_NUM_ENTRIES (1<<(VTLB_SHIFT-5)) + +#define KVM_VPD_BASE (KVM_VTLB_BASE+KVM_VTLB_BLOCK_SIZE) +#define KVM_VPD_OFS (KVM_VTLB_OFS+KVM_VTLB_BLOCK_SIZE) +#define KVM_VPD_BLOCK_SIZE (2UL<<20) +#define VPD_SHIFT 16 +#define VPD_SIZE (1UL<<VPD_SHIFT) + +#define KVM_VCPU_BASE (KVM_VPD_BASE+KVM_VPD_BLOCK_SIZE) +#define KVM_VCPU_OFS (KVM_VPD_OFS+KVM_VPD_BLOCK_SIZE) +#define KVM_VCPU_BLOCK_SIZE (2UL<<20) +#define VCPU_SHIFT 18 +#define VCPU_SIZE (1UL<<VCPU_SHIFT) +#define MAX_VCPU_NUM KVM_VCPU_BLOCK_SIZE/VCPU_SIZE + +#define KVM_VM_BASE (KVM_VCPU_BASE+KVM_VCPU_BLOCK_SIZE) +#define KVM_VM_OFS (KVM_VCPU_OFS+KVM_VCPU_BLOCK_SIZE) +#define KVM_VM_BLOCK_SIZE (1UL<<19) + +#define KVM_MEM_DIRTY_LOG_BASE (KVM_VM_BASE+KVM_VM_BLOCK_SIZE) +#define KVM_MEM_DIRTY_LOG_OFS (KVM_VM_OFS+KVM_VM_BLOCK_SIZE) +#define KVM_MEM_DIRTY_LOG_SIZE (1UL<<19) + +/* Get vpd, vhpt, tlb, vcpu, base*/ +#define VPD_ADDR(n) (KVM_VPD_BASE+n*VPD_SIZE) +#define VHPT_ADDR(n) (KVM_VHPT_BASE+n*VHPT_SIZE) +#define VTLB_ADDR(n) (KVM_VTLB_BASE+n*VTLB_SIZE) +#define VCPU_ADDR(n) (KVM_VCPU_BASE+n*VCPU_SIZE) + +/*IO section definitions*/ +#define IOREQ_READ 1 +#define IOREQ_WRITE 0 + +#define STATE_IOREQ_NONE 0 +#define STATE_IOREQ_READY 1 +#define STATE_IOREQ_INPROCESS 2 +#define STATE_IORESP_READY 3 + +/*Guest Physical address layout.*/ +#define GPFN_MEM (0UL << 60) /* Guest pfn is normal mem */ +#define GPFN_FRAME_BUFFER (1UL << 60) /* VGA framebuffer */ +#define GPFN_LOW_MMIO (2UL << 60) /* Low MMIO range */ +#define GPFN_PIB (3UL << 60) /* PIB base */ +#define GPFN_IOSAPIC (4UL << 60) /* IOSAPIC base */ +#define GPFN_LEGACY_IO (5UL << 60) /* Legacy I/O base */ +#define GPFN_GFW (6UL << 60) /* Guest Firmware */ +#define GPFN_HIGH_MMIO (7UL << 60) /* High MMIO range */ + +#define GPFN_IO_MASK (7UL << 60) /* Guest pfn is I/O type */ +#define GPFN_INV_MASK (1UL << 63) /* Guest pfn is invalid */ +#define INVALID_MFN (~0UL) +#define MEM_G (1UL << 30) +#define MEM_M (1UL << 20) +#define MMIO_START (3 * MEM_G) +#define MMIO_SIZE (512 * MEM_M) +#define VGA_IO_START 0xA0000UL +#define VGA_IO_SIZE 0x20000 +#define LEGACY_IO_START (MMIO_START + MMIO_SIZE) +#define LEGACY_IO_SIZE (64 * MEM_M) +#define IO_SAPIC_START 0xfec00000UL +#define IO_SAPIC_SIZE 0x100000 +#define PIB_START 0xfee00000UL +#define PIB_SIZE 0x200000 +#define GFW_START (4 * MEM_G - 16 * MEM_M) +#define GFW_SIZE (16 * MEM_M) + +/*Deliver mode, defined for ioapic.c*/ +#define dest_Fixed IOSAPIC_FIXED +#define dest_LowestPrio IOSAPIC_LOWEST_PRIORITY + +#define NMI_VECTOR 2 +#define ExtINT_VECTOR 0 +#define NULL_VECTOR (-1) +#define IA64_SPURIOUS_INT_VECTOR 0x0f + +#define VCPU_LID(v) (((u64)(v)->vcpu_id) << 24) + +/* + *Delivery mode + */ +#define SAPIC_DELIV_SHIFT 8 +#define SAPIC_FIXED 0x0 +#define SAPIC_LOWEST_PRIORITY 0x1 +#define SAPIC_PMI 0x2 +#define SAPIC_NMI 0x4 +#define SAPIC_INIT 0x5 +#define SAPIC_EXTINT 0x7 + +/* + * vcpu->requests bit members for arch + */ +#define KVM_REQ_PTC_G 32 +#define KVM_REQ_RESUME 33 + +#define KVM_PAGES_PER_HPAGE 1 + +struct kvm; +struct kvm_vcpu; +struct kvm_guest_debug{ +}; + +struct kvm_mmio_req { + uint64_t addr; /* physical address */ + uint64_t size; /* size in bytes */ + uint64_t data; /* data (or paddr of data) */ + uint8_t state:4; + uint8_t dir:1; /* 1=read, 0=write */ +}; + +/*Pal data struct */ +struct kvm_pal_call{ + /*In area*/ + uint64_t gr28; + uint64_t gr29; + uint64_t gr30; + uint64_t gr31; + /*Out area*/ + struct ia64_pal_retval ret; +}; + +/* Sal data structure */ +struct kvm_sal_call{ + /*In area*/ + uint64_t in0; + uint64_t in1; + uint64_t in2; + uint64_t in3; + uint64_t in4; + uint64_t in5; + uint64_t in6; + uint64_t in7; + struct sal_ret_values ret; +}; + +/*Guest change rr6*/ +struct kvm_switch_rr6 { + uint64_t old_rr; + uint64_t new_rr; +}; + +union ia64_ipi_a{ + unsigned long val; + struct { + unsigned long rv : 3; + unsigned long ir : 1; + unsigned long eid : 8; + unsigned long id : 8; + unsigned long ib_base : 44; + }; +}; + +union ia64_ipi_d { + unsigned long val; + struct { + unsigned long vector : 8; + unsigned long dm : 3; + unsigned long ig : 53; + }; +}; + +/*ipi check exit data*/ +struct kvm_ipi_data{ + union ia64_ipi_a addr; + union ia64_ipi_d data; +}; + +/*global purge data*/ +struct kvm_ptc_g { + unsigned long vaddr; + unsigned long rr; + unsigned long ps; + struct kvm_vcpu *vcpu; +}; + +/*Exit control data */ +struct exit_ctl_data{ + uint32_t exit_reason; + uint32_t vm_status; + union { + struct kvm_mmio_req ioreq; + struct kvm_pal_call pal_data; + struct kvm_sal_call sal_data; + struct kvm_switch_rr6 rr_data; + struct kvm_ipi_data ipi_data; + struct kvm_ptc_g ptc_g_data; + } u; +}; + +union pte_flags { + unsigned long val; + struct { + unsigned long p : 1; /*0 */ + unsigned long : 1; /* 1 */ + unsigned long ma : 3; /* 2-4 */ + unsigned long a : 1; /* 5 */ + unsigned long d : 1; /* 6 */ + unsigned long pl : 2; /* 7-8 */ + unsigned long ar : 3; /* 9-11 */ + unsigned long ppn : 38; /* 12-49 */ + unsigned long : 2; /* 50-51 */ + unsigned long ed : 1; /* 52 */ + }; +}; + +union ia64_pta { + unsigned long val; + struct { + unsigned long ve : 1; + unsigned long reserved0 : 1; + unsigned long size : 6; + unsigned long vf : 1; + unsigned long reserved1 : 6; + unsigned long base : 49; + }; +}; + +struct thash_cb { + /* THASH base information */ + struct thash_data *hash; /* hash table pointer */ + union ia64_pta pta; + int num; +}; + +struct kvm_vcpu_stat { +}; + +struct kvm_vcpu_arch { + int launched; + int last_exit; + int last_run_cpu; + int vmm_tr_slot; + int vm_tr_slot; + +#define KVM_MP_STATE_RUNNABLE 0 +#define KVM_MP_STATE_UNINITIALIZED 1 +#define KVM_MP_STATE_INIT_RECEIVED 2 +#define KVM_MP_STATE_HALTED 3 + int mp_state; + +#define MAX_PTC_G_NUM 3 + int ptc_g_count; + struct kvm_ptc_g ptc_g_data[MAX_PTC_G_NUM]; + + /*halt timer to wake up sleepy vcpus*/ + struct hrtimer hlt_timer; + long ht_active; + + struct kvm_lapic *apic; /* kernel irqchip context */ + struct vpd *vpd; + + /* Exit data for vmm_transition*/ + struct exit_ctl_data exit_data; + + cpumask_t cache_coherent_map; + + unsigned long vmm_rr; + unsigned long host_rr6; + unsigned long psbits[8]; + unsigned long cr_iipa; + unsigned long cr_isr; + unsigned long vsa_base; + unsigned long dirty_log_lock_pa; + unsigned long __gp; + /* TR and TC. */ + struct thash_data itrs[NITRS]; + struct thash_data dtrs[NDTRS]; + /* Bit is set if there is a tr/tc for the region. */ + unsigned char itr_regions; + unsigned char dtr_regions; + unsigned char tc_regions; + /* purge all */ + unsigned long ptce_base; + unsigned long ptce_count[2]; + unsigned long ptce_stride[2]; + /* itc/itm */ + unsigned long last_itc; + long itc_offset; + unsigned long itc_check; + unsigned long timer_check; + unsigned long timer_pending; + + unsigned long vrr[8]; + unsigned long ibr[8]; + unsigned long dbr[8]; + unsigned long insvc[4]; /* Interrupt in service. */ + unsigned long xtp; + + unsigned long metaphysical_rr0; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_rr4; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_saved_rr0; /* from kvm_arch */ + unsigned long metaphysical_saved_rr4; /* from kvm_arch */ + unsigned long fp_psr; /*used for lazy float register */ + unsigned long saved_gp; + /*for phycial emulation */ + int mode_flags; + struct thash_cb vtlb; + struct thash_cb vhpt; + char irq_check; + char irq_new_pending; + + unsigned long opcode; + unsigned long cause; + union context host; + union context guest; +}; + +struct kvm_vm_stat { + u64 remote_tlb_flush; +}; + +struct kvm_sal_data { + unsigned long boot_ip; + unsigned long boot_gp; +}; + +struct kvm_arch { + unsigned long vm_base; + unsigned long metaphysical_rr0; + unsigned long metaphysical_rr4; + unsigned long vmm_init_rr; + unsigned long vhpt_base; + unsigned long vtlb_base; + unsigned long vpd_base; + spinlock_t dirty_log_lock; + struct kvm_ioapic *vioapic; + struct kvm_vm_stat stat; + struct kvm_sal_data rdv_sal_data; +}; + +union cpuid3_t { + u64 value; + struct { + u64 number : 8; + u64 revision : 8; + u64 model : 8; + u64 family : 8; + u64 archrev : 8; + u64 rv : 24; + }; +}; + +struct kvm_pt_regs { + /* The following registers are saved by SAVE_MIN: */ + unsigned long b6; /* scratch */ + unsigned long b7; /* scratch */ + + unsigned long ar_csd; /* used by cmp8xchg16 (scratch) */ + unsigned long ar_ssd; /* reserved for future use (scratch) */ + + unsigned long r8; /* scratch (return value register 0) */ + unsigned long r9; /* scratch (return value register 1) */ + unsigned long r10; /* scratch (return value register 2) */ + unsigned long r11; /* scratch (return value register 3) */ + + unsigned long cr_ipsr; /* interrupted task's psr */ + unsigned long cr_iip; /* interrupted task's instruction pointer */ + unsigned long cr_ifs; /* interrupted task's function state */ + + unsigned long ar_unat; /* interrupted task's NaT register (preserved) */ + unsigned long ar_pfs; /* prev function state */ + unsigned long ar_rsc; /* RSE configuration */ + /* The following two are valid only if cr_ipsr.cpl > 0: */ + unsigned long ar_rnat; /* RSE NaT */ + unsigned long ar_bspstore; /* RSE bspstore */ + + unsigned long pr; /* 64 predicate registers (1 bit each) */ + unsigned long b0; /* return pointer (bp) */ + unsigned long loadrs; /* size of dirty partition << 16 */ + + unsigned long r1; /* the gp pointer */ + unsigned long r12; /* interrupted task's memory stack pointer */ + unsigned long r13; /* thread pointer */ + + unsigned long ar_fpsr; /* floating point status (preserved) */ + unsigned long r15; /* scratch */ + + /* The remaining registers are NOT saved for system calls. */ + unsigned long r14; /* scratch */ + unsigned long r2; /* scratch */ + unsigned long r3; /* scratch */ + unsigned long r16; /* scratch */ + unsigned long r17; /* scratch */ + unsigned long r18; /* scratch */ + unsigned long r19; /* scratch */ + unsigned long r20; /* scratch */ + unsigned long r21; /* scratch */ + unsigned long r22; /* scratch */ + unsigned long r23; /* scratch */ + unsigned long r24; /* scratch */ + unsigned long r25; /* scratch */ + unsigned long r26; /* scratch */ + unsigned long r27; /* scratch */ + unsigned long r28; /* scratch */ + unsigned long r29; /* scratch */ + unsigned long r30; /* scratch */ + unsigned long r31; /* scratch */ + unsigned long ar_ccv; /* compare/exchange value (scratch) */ + + /* + * Floating point registers that the kernel considers scratch: + */ + struct ia64_fpreg f6; /* scratch */ + struct ia64_fpreg f7; /* scratch */ + struct ia64_fpreg f8; /* scratch */ + struct ia64_fpreg f9; /* scratch */ + struct ia64_fpreg f10; /* scratch */ + struct ia64_fpreg f11; /* scratch */ + + unsigned long r4; /* preserved */ + unsigned long r5; /* preserved */ + unsigned long r6; /* preserved */ + unsigned long r7; /* preserved */ + unsigned long eml_unat; /* used for emulating instruction */ + unsigned long pad0; /* alignment pad */ +}; + +static inline struct kvm_pt_regs *vcpu_regs(struct kvm_vcpu *v) +{ + return (struct kvm_pt_regs *) ((unsigned long) v + IA64_STK_OFFSET) - 1; +} + +typedef int kvm_vmm_entry(void); +typedef void kvm_tramp_entry(union context *host, union context *guest); + +struct kvm_vmm_info{ + struct module *module; + kvm_vmm_entry *vmm_entry; + kvm_tramp_entry *tramp_entry; + unsigned long vmm_ivt; +}; + +int kvm_highest_pending_irq(struct kvm_vcpu *vcpu); +int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); +void kvm_sal_emul(struct kvm_vcpu *vcpu); + +#endif diff --git a/include/asm-ia64/kvm_para.h b/include/asm-ia64/kvm_para.h new file mode 100644 index 0000000..9f9796b --- /dev/null +++ b/include/asm-ia64/kvm_para.h @@ -0,0 +1,29 @@ +#ifndef __IA64_KVM_PARA_H +#define __IA64_KVM_PARA_H + +/* + * asm-ia64/kvm_para.h + * + * Copyright (C) 2007 Xiantao Zhang <xiantao.zhang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + +#endif diff --git a/include/asm-ia64/processor.h b/include/asm-ia64/processor.h index 741f7ec..6aff126 100644 --- a/include/asm-ia64/processor.h +++ b/include/asm-ia64/processor.h @@ -119,6 +119,69 @@ struct ia64_psr { __u64 reserved4 : 19; }; +union ia64_isr { + __u64 val; + struct { + __u64 code : 16; + __u64 vector : 8; + __u64 reserved1 : 8; + __u64 x : 1; + __u64 w : 1; + __u64 r : 1; + __u64 na : 1; + __u64 sp : 1; + __u64 rs : 1; + __u64 ir : 1; + __u64 ni : 1; + __u64 so : 1; + __u64 ei : 2; + __u64 ed : 1; + __u64 reserved2 : 20; + }; +}; + +union ia64_lid { + __u64 val; + struct { + __u64 rv : 16; + __u64 eid : 8; + __u64 id : 8; + __u64 ig : 32; + }; +}; + +union ia64_tpr { + __u64 val; + struct { + __u64 ig0 : 4; + __u64 mic : 4; + __u64 rsv : 8; + __u64 mmi : 1; + __u64 ig1 : 47; + }; +}; + +union ia64_itir { + __u64 val; + struct { + __u64 rv3 : 2; /* 0-1 */ + __u64 ps : 6; /* 2-7 */ + __u64 key : 24; /* 8-31 */ + __u64 rv4 : 32; /* 32-63 */ + }; +}; + +union ia64_rr { + __u64 val; + struct { + __u64 ve : 1; /* enable hw walker */ + __u64 reserved0: 1; /* reserved */ + __u64 ps : 6; /* log page size */ + __u64 rid : 24; /* region id */ + __u64 reserved1: 32; /* reserved */ + }; +}; + /* * CPU type, hardware bug flags, and per-CPU state. Frequently used * state comes earlier: diff --git a/include/asm-powerpc/kvm.h b/include/asm-powerpc/kvm.h index d1b530f..f993e41 100644 --- a/include/asm-powerpc/kvm.h +++ b/include/asm-powerpc/kvm.h @@ -1,6 +1,55 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright IBM Corp. 2007 + * + * Authors: Hollis Blanchard <hollisb@us.ibm.com> + */ + #ifndef __LINUX_KVM_POWERPC_H #define __LINUX_KVM_POWERPC_H -/* powerpc does not support KVM */ +#include <asm/types.h> + +struct kvm_regs { + __u64 pc; + __u64 cr; + __u64 ctr; + __u64 lr; + __u64 xer; + __u64 msr; + __u64 srr0; + __u64 srr1; + __u64 pid; + + __u64 sprg0; + __u64 sprg1; + __u64 sprg2; + __u64 sprg3; + __u64 sprg4; + __u64 sprg5; + __u64 sprg6; + __u64 sprg7; + + __u64 gpr[32]; +}; + +struct kvm_sregs { +}; + +struct kvm_fpu { + __u64 fpr[32]; +}; -#endif +#endif /* __LINUX_KVM_POWERPC_H */ diff --git a/include/asm-powerpc/kvm_asm.h b/include/asm-powerpc/kvm_asm.h new file mode 100644 index 0000000..2197764 --- /dev/null +++ b/include/asm-powerpc/kvm_asm.h @@ -0,0 +1,55 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright IBM Corp. 2008 + * + * Authors: Hollis Blanchard <hollisb@us.ibm.com> + */ + +#ifndef __POWERPC_KVM_ASM_H__ +#define __POWERPC_KVM_ASM_H__ + +/* IVPR must be 64KiB-aligned. */ +#define VCPU_SIZE_ORDER 4 +#define VCPU_SIZE_LOG (VCPU_SIZE_ORDER + 12) +#define VCPU_TLB_PGSZ PPC44x_TLB_64K +#define VCPU_SIZE_BYTES (1<<VCPU_SIZE_LOG) + +#define BOOKE_INTERRUPT_CRITICAL 0 +#define BOOKE_INTERRUPT_MACHINE_CHECK 1 +#define BOOKE_INTERRUPT_DATA_STORAGE 2 +#define BOOKE_INTERRUPT_INST_STORAGE 3 +#define BOOKE_INTERRUPT_EXTERNAL 4 +#define BOOKE_INTERRUPT_ALIGNMENT 5 +#define BOOKE_INTERRUPT_PROGRAM 6 +#define BOOKE_INTERRUPT_FP_UNAVAIL 7 +#define BOOKE_INTERRUPT_SYSCALL 8 +#define BOOKE_INTERRUPT_AP_UNAVAIL 9 +#define BOOKE_INTERRUPT_DECREMENTER 10 +#define BOOKE_INTERRUPT_FIT 11 +#define BOOKE_INTERRUPT_WATCHDOG 12 +#define BOOKE_INTERRUPT_DTLB_MISS 13 +#define BOOKE_INTERRUPT_ITLB_MISS 14 +#define BOOKE_INTERRUPT_DEBUG 15 +#define BOOKE_MAX_INTERRUPT 15 + +#define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */ +#define RESUME_FLAG_HOST (1<<1) /* Resume host? */ + +#define RESUME_GUEST 0 +#define RESUME_GUEST_NV RESUME_FLAG_NV +#define RESUME_HOST RESUME_FLAG_HOST +#define RESUME_HOST_NV (RESUME_FLAG_HOST|RESUME_FLAG_NV) + +#endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/include/asm-powerpc/kvm_host.h b/include/asm-powerpc/kvm_host.h new file mode 100644 index 0000000..04ffbb8 --- /dev/null +++ b/include/asm-powerpc/kvm_host.h @@ -0,0 +1,152 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright IBM Corp. 2007 + * + * Authors: Hollis Blanchard <hollisb@us.ibm.com> + */ + +#ifndef __POWERPC_KVM_HOST_H__ +#define __POWERPC_KVM_HOST_H__ + +#include <linux/mutex.h> +#include <linux/timer.h> +#include <linux/types.h> +#include <linux/kvm_types.h> +#include <asm/kvm_asm.h> + +#define KVM_MAX_VCPUS 1 +#define KVM_MEMORY_SLOTS 32 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + +/* We don't currently support large pages. */ +#define KVM_PAGES_PER_HPAGE (1<<31) + +struct kvm; +struct kvm_run; +struct kvm_vcpu; + +struct kvm_vm_stat { + u32 remote_tlb_flush; +}; + +struct kvm_vcpu_stat { + u32 sum_exits; + u32 mmio_exits; + u32 dcr_exits; + u32 signal_exits; + u32 light_exits; + /* Account for special types of light exits: */ + u32 itlb_real_miss_exits; + u32 itlb_virt_miss_exits; + u32 dtlb_real_miss_exits; + u32 dtlb_virt_miss_exits; + u32 syscall_exits; + u32 isi_exits; + u32 dsi_exits; + u32 emulated_inst_exits; + u32 dec_exits; + u32 ext_intr_exits; +}; + +struct tlbe { + u32 tid; /* Only the low 8 bits are used. */ + u32 word0; + u32 word1; + u32 word2; +}; + +struct kvm_arch { +}; + +struct kvm_vcpu_arch { + /* Unmodified copy of the guest's TLB. */ + struct tlbe guest_tlb[PPC44x_TLB_SIZE]; + /* TLB that's actually used when the guest is running. */ + struct tlbe shadow_tlb[PPC44x_TLB_SIZE]; + /* Pages which are referenced in the shadow TLB. */ + struct page *shadow_pages[PPC44x_TLB_SIZE]; + /* Copy of the host's TLB. */ + struct tlbe host_tlb[PPC44x_TLB_SIZE]; + + u32 host_stack; + u32 host_pid; + + u64 fpr[32]; + u32 gpr[32]; + + u32 pc; + u32 cr; + u32 ctr; + u32 lr; + u32 xer; + + u32 msr; + u32 mmucr; + u32 sprg0; + u32 sprg1; + u32 sprg2; + u32 sprg3; + u32 sprg4; + u32 sprg5; + u32 sprg6; + u32 sprg7; + u32 srr0; + u32 srr1; + u32 csrr0; + u32 csrr1; + u32 dsrr0; + u32 dsrr1; + u32 dear; + u32 esr; + u32 dec; + u32 decar; + u32 tbl; + u32 tbu; + u32 tcr; + u32 tsr; + u32 ivor[16]; + u32 ivpr; + u32 pir; + u32 pid; + u32 pvr; + u32 ccr0; + u32 ccr1; + u32 dbcr0; + u32 dbcr1; + + u32 last_inst; + u32 fault_dear; + u32 fault_esr; + gpa_t paddr_accessed; + + u8 io_gpr; /* GPR used as IO source/target */ + u8 mmio_is_bigendian; + u8 dcr_needed; + u8 dcr_is_write; + + u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ + + struct timer_list dec_timer; + unsigned long pending_exceptions; +}; + +struct kvm_guest_debug { + int enabled; + unsigned long bp[4]; + int singlestep; +}; + +#endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/include/asm-powerpc/kvm_para.h b/include/asm-powerpc/kvm_para.h new file mode 100644 index 0000000..2d48f6a --- /dev/null +++ b/include/asm-powerpc/kvm_para.h @@ -0,0 +1,37 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright IBM Corp. 2008 + * + * Authors: Hollis Blanchard <hollisb@us.ibm.com> + */ + +#ifndef __POWERPC_KVM_PARA_H__ +#define __POWERPC_KVM_PARA_H__ + +#ifdef __KERNEL__ + +static inline int kvm_para_available(void) +{ + return 0; +} + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + +#endif /* __KERNEL__ */ + +#endif /* __POWERPC_KVM_PARA_H__ */ diff --git a/include/asm-powerpc/kvm_ppc.h b/include/asm-powerpc/kvm_ppc.h new file mode 100644 index 0000000..7ac8203 --- /dev/null +++ b/include/asm-powerpc/kvm_ppc.h @@ -0,0 +1,88 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright IBM Corp. 2008 + * + * Authors: Hollis Blanchard <hollisb@us.ibm.com> + */ + +#ifndef __POWERPC_KVM_PPC_H__ +#define __POWERPC_KVM_PPC_H__ + +/* This file exists just so we can dereference kvm_vcpu, avoiding nested header + * dependencies. */ + +#include <linux/mutex.h> +#include <linux/timer.h> +#include <linux/types.h> +#include <linux/kvm_types.h> +#include <linux/kvm_host.h> + +struct kvm_tlb { + struct tlbe guest_tlb[PPC44x_TLB_SIZE]; + struct tlbe shadow_tlb[PPC44x_TLB_SIZE]; +}; + +enum emulation_result { + EMULATE_DONE, /* no further processing */ + EMULATE_DO_MMIO, /* kvm_run filled with MMIO request */ + EMULATE_DO_DCR, /* kvm_run filled with DCR request */ + EMULATE_FAIL, /* can't emulate this instruction */ +}; + +extern const unsigned char exception_priority[]; +extern const unsigned char priority_exception[]; + +extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); +extern char kvmppc_handlers_start[]; +extern unsigned long kvmppc_handler_len; + +extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); +extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, + int is_bigendian); +extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + u32 val, unsigned int bytes, int is_bigendian); + +extern int kvmppc_emulate_instruction(struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, + u64 asid, u32 flags); +extern void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, u64 eaddr, u64 asid); +extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); + +extern void kvmppc_check_and_deliver_interrupts(struct kvm_vcpu *vcpu); + +static inline void kvmppc_queue_exception(struct kvm_vcpu *vcpu, int exception) +{ + unsigned int priority = exception_priority[exception]; + set_bit(priority, &vcpu->arch.pending_exceptions); +} + +static inline void kvmppc_clear_exception(struct kvm_vcpu *vcpu, int exception) +{ + unsigned int priority = exception_priority[exception]; + clear_bit(priority, &vcpu->arch.pending_exceptions); +} + +static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr) +{ + if ((new_msr & MSR_PR) != (vcpu->arch.msr & MSR_PR)) + kvmppc_mmu_priv_switch(vcpu, new_msr & MSR_PR); + + vcpu->arch.msr = new_msr; +} + +#endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/include/asm-powerpc/mmu-44x.h b/include/asm-powerpc/mmu-44x.h index c8b02d9..a825524 100644 --- a/include/asm-powerpc/mmu-44x.h +++ b/include/asm-powerpc/mmu-44x.h @@ -53,6 +53,8 @@ #ifndef __ASSEMBLY__ +extern unsigned int tlb_44x_hwater; + typedef struct { unsigned long id; unsigned long vdso_base; diff --git a/include/asm-s390/Kbuild b/include/asm-s390/Kbuild index e92b429..13c9805 100644 --- a/include/asm-s390/Kbuild +++ b/include/asm-s390/Kbuild @@ -7,6 +7,7 @@ header-y += tape390.h header-y += ucontext.h header-y += vtoc.h header-y += zcrypt.h +header-y += kvm.h unifdef-y += cmb.h unifdef-y += debug.h diff --git a/include/asm-s390/kvm.h b/include/asm-s390/kvm.h index 573f2a3..d74002f 100644 --- a/include/asm-s390/kvm.h +++ b/include/asm-s390/kvm.h @@ -1,6 +1,45 @@ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H -/* s390 does not support KVM */ +/* + * asm-s390/kvm.h - KVM s390 specific structures and definitions + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ +#include <asm/types.h> + +/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ +struct kvm_pic_state { + /* no PIC for s390 */ +}; + +struct kvm_ioapic_state { + /* no IOAPIC for s390 */ +}; + +/* for KVM_GET_REGS and KVM_SET_REGS */ +struct kvm_regs { + /* general purpose regs for s390 */ + __u64 gprs[16]; +}; + +/* for KVM_GET_SREGS and KVM_SET_SREGS */ +struct kvm_sregs { + __u32 acrs[16]; + __u64 crs[16]; +}; + +/* for KVM_GET_FPU and KVM_SET_FPU */ +struct kvm_fpu { + __u32 fpc; + __u64 fprs[16]; +}; #endif diff --git a/include/asm-s390/kvm_host.h b/include/asm-s390/kvm_host.h new file mode 100644 index 0000000..f8204a4 --- /dev/null +++ b/include/asm-s390/kvm_host.h @@ -0,0 +1,234 @@ +/* + * asm-s390/kvm_host.h - definition for kernel virtual machines on s390 + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + */ + + +#ifndef ASM_KVM_HOST_H +#define ASM_KVM_HOST_H +#include <linux/kvm_host.h> +#include <asm/debug.h> + +#define KVM_MAX_VCPUS 64 +#define KVM_MEMORY_SLOTS 32 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + +struct kvm_guest_debug { +}; + +struct sca_entry { + atomic_t scn; + __u64 reserved; + __u64 sda; + __u64 reserved2[2]; +} __attribute__((packed)); + + +struct sca_block { + __u64 ipte_control; + __u64 reserved[5]; + __u64 mcn; + __u64 reserved2; + struct sca_entry cpu[64]; +} __attribute__((packed)); + +#define KVM_PAGES_PER_HPAGE 256 + +#define CPUSTAT_HOST 0x80000000 +#define CPUSTAT_WAIT 0x10000000 +#define CPUSTAT_ECALL_PEND 0x08000000 +#define CPUSTAT_STOP_INT 0x04000000 +#define CPUSTAT_IO_INT 0x02000000 +#define CPUSTAT_EXT_INT 0x01000000 +#define CPUSTAT_RUNNING 0x00800000 +#define CPUSTAT_RETAINED 0x00400000 +#define CPUSTAT_TIMING_SUB 0x00020000 +#define CPUSTAT_SIE_SUB 0x00010000 +#define CPUSTAT_RRF 0x00008000 +#define CPUSTAT_SLSV 0x00004000 +#define CPUSTAT_SLSR 0x00002000 +#define CPUSTAT_ZARCH 0x00000800 +#define CPUSTAT_MCDS 0x00000100 +#define CPUSTAT_SM 0x00000080 +#define CPUSTAT_G 0x00000008 +#define CPUSTAT_J 0x00000002 +#define CPUSTAT_P 0x00000001 + +struct sie_block { + atomic_t cpuflags; /* 0x0000 */ + __u32 prefix; /* 0x0004 */ + __u8 reserved8[32]; /* 0x0008 */ + __u64 cputm; /* 0x0028 */ + __u64 ckc; /* 0x0030 */ + __u64 epoch; /* 0x0038 */ + __u8 reserved40[4]; /* 0x0040 */ +#define LCTL_CR0 0x8000 + __u16 lctl; /* 0x0044 */ + __s16 icpua; /* 0x0046 */ + __u32 ictl; /* 0x0048 */ + __u32 eca; /* 0x004c */ + __u8 icptcode; /* 0x0050 */ + __u8 reserved51; /* 0x0051 */ + __u16 ihcpu; /* 0x0052 */ + __u8 reserved54[2]; /* 0x0054 */ + __u16 ipa; /* 0x0056 */ + __u32 ipb; /* 0x0058 */ + __u32 scaoh; /* 0x005c */ + __u8 reserved60; /* 0x0060 */ + __u8 ecb; /* 0x0061 */ + __u8 reserved62[2]; /* 0x0062 */ + __u32 scaol; /* 0x0064 */ + __u8 reserved68[4]; /* 0x0068 */ + __u32 todpr; /* 0x006c */ + __u8 reserved70[16]; /* 0x0070 */ + __u64 gmsor; /* 0x0080 */ + __u64 gmslm; /* 0x0088 */ + psw_t gpsw; /* 0x0090 */ + __u64 gg14; /* 0x00a0 */ + __u64 gg15; /* 0x00a8 */ + __u8 reservedb0[30]; /* 0x00b0 */ + __u16 iprcc; /* 0x00ce */ + __u8 reservedd0[48]; /* 0x00d0 */ + __u64 gcr[16]; /* 0x0100 */ + __u64 gbea; /* 0x0180 */ + __u8 reserved188[120]; /* 0x0188 */ +} __attribute__((packed)); + +struct kvm_vcpu_stat { + u32 exit_userspace; + u32 exit_external_request; + u32 exit_external_interrupt; + u32 exit_stop_request; + u32 exit_validity; + u32 exit_instruction; + u32 instruction_lctl; + u32 instruction_lctg; + u32 exit_program_interruption; + u32 exit_instr_and_program; + u32 deliver_emergency_signal; + u32 deliver_service_signal; + u32 deliver_virtio_interrupt; + u32 deliver_stop_signal; + u32 deliver_prefix_signal; + u32 deliver_restart_signal; + u32 deliver_program_int; + u32 exit_wait_state; + u32 instruction_stidp; + u32 instruction_spx; + u32 instruction_stpx; + u32 instruction_stap; + u32 instruction_storage_key; + u32 instruction_stsch; + u32 instruction_chsc; + u32 instruction_stsi; + u32 instruction_stfl; + u32 instruction_sigp_sense; + u32 instruction_sigp_emergency; + u32 instruction_sigp_stop; + u32 instruction_sigp_arch; + u32 instruction_sigp_prefix; + u32 instruction_sigp_restart; + u32 diagnose_44; +}; + +struct io_info { + __u16 subchannel_id; /* 0x0b8 */ + __u16 subchannel_nr; /* 0x0ba */ + __u32 io_int_parm; /* 0x0bc */ + __u32 io_int_word; /* 0x0c0 */ +}; + +struct ext_info { + __u32 ext_params; + __u64 ext_params2; +}; + +#define PGM_OPERATION 0x01 +#define PGM_PRIVILEGED_OPERATION 0x02 +#define PGM_EXECUTE 0x03 +#define PGM_PROTECTION 0x04 +#define PGM_ADDRESSING 0x05 +#define PGM_SPECIFICATION 0x06 +#define PGM_DATA 0x07 + +struct pgm_info { + __u16 code; +}; + +struct prefix_info { + __u32 address; +}; + +struct interrupt_info { + struct list_head list; + u64 type; + union { + struct io_info io; + struct ext_info ext; + struct pgm_info pgm; + struct prefix_info prefix; + }; +}; + +/* for local_interrupt.action_flags */ +#define ACTION_STORE_ON_STOP 1 +#define ACTION_STOP_ON_STOP 2 + +struct local_interrupt { + spinlock_t lock; + struct list_head list; + atomic_t active; + struct float_interrupt *float_int; + int timer_due; /* event indicator for waitqueue below */ + wait_queue_head_t wq; + atomic_t *cpuflags; + unsigned int action_bits; +}; + +struct float_interrupt { + spinlock_t lock; + struct list_head list; + atomic_t active; + int next_rr_cpu; + unsigned long idle_mask [(64 + sizeof(long) - 1) / sizeof(long)]; + struct local_interrupt *local_int[64]; +}; + + +struct kvm_vcpu_arch { + struct sie_block *sie_block; + unsigned long guest_gprs[16]; + s390_fp_regs host_fpregs; + unsigned int host_acrs[NUM_ACRS]; + s390_fp_regs guest_fpregs; + unsigned int guest_acrs[NUM_ACRS]; + struct local_interrupt local_int; + struct timer_list ckc_timer; + union { + cpuid_t cpu_id; + u64 stidp_data; + }; +}; + +struct kvm_vm_stat { + u32 remote_tlb_flush; +}; + +struct kvm_arch{ + unsigned long guest_origin; + unsigned long guest_memsize; + struct sca_block *sca; + debug_info_t *dbf; + struct float_interrupt float_int; +}; + +extern int sie64a(struct sie_block *, __u64 *); +#endif diff --git a/include/asm-s390/kvm_para.h b/include/asm-s390/kvm_para.h new file mode 100644 index 0000000..2c50379 --- /dev/null +++ b/include/asm-s390/kvm_para.h @@ -0,0 +1,150 @@ +/* + * asm-s390/kvm_para.h - definition for paravirtual devices on s390 + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#ifndef __S390_KVM_PARA_H +#define __S390_KVM_PARA_H + +/* + * Hypercalls for KVM on s390. The calling convention is similar to the + * s390 ABI, so we use R2-R6 for parameters 1-5. In addition we use R1 + * as hypercall number and R7 as parameter 6. The return value is + * written to R2. We use the diagnose instruction as hypercall. To avoid + * conflicts with existing diagnoses for LPAR and z/VM, we do not use + * the instruction encoded number, but specify the number in R1 and + * use 0x500 as KVM hypercall + * + * Copyright IBM Corp. 2007,2008 + * Author(s): Christian Borntraeger <borntraeger@de.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ + +static inline long kvm_hypercall0(unsigned long nr) +{ + register unsigned long __nr asm("1") = nr; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr): "memory", "cc"); + return __rc; +} + +static inline long kvm_hypercall1(unsigned long nr, unsigned long p1) +{ + register unsigned long __nr asm("1") = nr; + register unsigned long __p1 asm("2") = p1; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "0" (__p1) : "memory", "cc"); + return __rc; +} + +static inline long kvm_hypercall2(unsigned long nr, unsigned long p1, + unsigned long p2) +{ + register unsigned long __nr asm("1") = nr; + register unsigned long __p1 asm("2") = p1; + register unsigned long __p2 asm("3") = p2; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2) + : "memory", "cc"); + return __rc; +} + +static inline long kvm_hypercall3(unsigned long nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + register unsigned long __nr asm("1") = nr; + register unsigned long __p1 asm("2") = p1; + register unsigned long __p2 asm("3") = p2; + register unsigned long __p3 asm("4") = p3; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2), + "d" (__p3) : "memory", "cc"); + return __rc; +} + + +static inline long kvm_hypercall4(unsigned long nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + register unsigned long __nr asm("1") = nr; + register unsigned long __p1 asm("2") = p1; + register unsigned long __p2 asm("3") = p2; + register unsigned long __p3 asm("4") = p3; + register unsigned long __p4 asm("5") = p4; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2), + "d" (__p3), "d" (__p4) : "memory", "cc"); + return __rc; +} + +static inline long kvm_hypercall5(unsigned long nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4, unsigned long p5) +{ + register unsigned long __nr asm("1") = nr; + register unsigned long __p1 asm("2") = p1; + register unsigned long __p2 asm("3") = p2; + register unsigned long __p3 asm("4") = p3; + register unsigned long __p4 asm("5") = p4; + register unsigned long __p5 asm("6") = p5; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2), + "d" (__p3), "d" (__p4), "d" (__p5) : "memory", "cc"); + return __rc; +} + +static inline long kvm_hypercall6(unsigned long nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4, unsigned long p5, + unsigned long p6) +{ + register unsigned long __nr asm("1") = nr; + register unsigned long __p1 asm("2") = p1; + register unsigned long __p2 asm("3") = p2; + register unsigned long __p3 asm("4") = p3; + register unsigned long __p4 asm("5") = p4; + register unsigned long __p5 asm("6") = p5; + register unsigned long __p6 asm("7") = p6; + register long __rc asm("2"); + + asm volatile ("diag 2,4,0x500\n" + : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2), + "d" (__p3), "d" (__p4), "d" (__p5), "d" (__p6) + : "memory", "cc"); + return __rc; +} + +/* kvm on s390 is always paravirtualization enabled */ +static inline int kvm_para_available(void) +{ + return 1; +} + +/* No feature bits are currently assigned for kvm on s390 */ +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + +#endif /* __S390_KVM_PARA_H */ diff --git a/include/asm-s390/kvm_virtio.h b/include/asm-s390/kvm_virtio.h new file mode 100644 index 0000000..5c871a9 --- /dev/null +++ b/include/asm-s390/kvm_virtio.h @@ -0,0 +1,53 @@ +/* + * kvm_virtio.h - definition for virtio for kvm on s390 + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#ifndef __KVM_S390_VIRTIO_H +#define __KVM_S390_VIRTIO_H + +#include <linux/types.h> + +struct kvm_device_desc { + /* The device type: console, network, disk etc. Type 0 terminates. */ + __u8 type; + /* The number of virtqueues (first in config array) */ + __u8 num_vq; + /* + * The number of bytes of feature bits. Multiply by 2: one for host + * features and one for guest acknowledgements. + */ + __u8 feature_len; + /* The number of bytes of the config array after virtqueues. */ + __u8 config_len; + /* A status byte, written by the Guest. */ + __u8 status; + __u8 config[0]; +}; + +/* + * This is how we expect the device configuration field for a virtqueue + * to be laid out in config space. + */ +struct kvm_vqconfig { + /* The token returned with an interrupt. Set by the guest */ + __u64 token; + /* The address of the virtio ring */ + __u64 address; + /* The number of entries in the virtio_ring */ + __u16 num; + +}; + +#define KVM_S390_VIRTIO_NOTIFY 0 +#define KVM_S390_VIRTIO_RESET 1 +#define KVM_S390_VIRTIO_SET_STATUS 2 + +#endif diff --git a/include/asm-s390/lowcore.h b/include/asm-s390/lowcore.h index 5de3efb..0bc51d5 100644 --- a/include/asm-s390/lowcore.h +++ b/include/asm-s390/lowcore.h @@ -381,27 +381,32 @@ struct _lowcore /* whether the kernel died with panic() or not */ __u32 panic_magic; /* 0xe00 */ - __u8 pad13[0x1200-0xe04]; /* 0xe04 */ + __u8 pad13[0x11b8-0xe04]; /* 0xe04 */ + + /* 64 bit extparam used for pfault, diag 250 etc */ + __u64 ext_params2; /* 0x11B8 */ + + __u8 pad14[0x1200-0x11C0]; /* 0x11C0 */ /* System info area */ __u64 floating_pt_save_area[16]; /* 0x1200 */ __u64 gpregs_save_area[16]; /* 0x1280 */ __u32 st_status_fixed_logout[4]; /* 0x1300 */ - __u8 pad14[0x1318-0x1310]; /* 0x1310 */ + __u8 pad15[0x1318-0x1310]; /* 0x1310 */ __u32 prefixreg_save_area; /* 0x1318 */ __u32 fpt_creg_save_area; /* 0x131c */ - __u8 pad15[0x1324-0x1320]; /* 0x1320 */ + __u8 pad16[0x1324-0x1320]; /* 0x1320 */ __u32 tod_progreg_save_area; /* 0x1324 */ __u32 cpu_timer_save_area[2]; /* 0x1328 */ __u32 clock_comp_save_area[2]; /* 0x1330 */ - __u8 pad16[0x1340-0x1338]; /* 0x1338 */ + __u8 pad17[0x1340-0x1338]; /* 0x1338 */ __u32 access_regs_save_area[16]; /* 0x1340 */ __u64 cregs_save_area[16]; /* 0x1380 */ /* align to the top of the prefix area */ - __u8 pad17[0x2000-0x1400]; /* 0x1400 */ + __u8 pad18[0x2000-0x1400]; /* 0x1400 */ #endif /* !__s390x__ */ } __attribute__((packed)); /* End structure*/ diff --git a/include/asm-s390/mmu.h b/include/asm-s390/mmu.h index 1698e29..5dd5e7b 100644 --- a/include/asm-s390/mmu.h +++ b/include/asm-s390/mmu.h @@ -7,6 +7,7 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; int noexec; + int pgstes; } mm_context_t; #endif diff --git a/include/asm-s390/mmu_context.h b/include/asm-s390/mmu_context.h index b5a34c6..4c2fbf4 100644 --- a/include/asm-s390/mmu_context.h +++ b/include/asm-s390/mmu_context.h @@ -20,7 +20,13 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_64BIT mm->context.asce_bits |= _ASCE_TYPE_REGION3; #endif - mm->context.noexec = s390_noexec; + if (current->mm->context.pgstes) { + mm->context.noexec = 0; + mm->context.pgstes = 1; + } else { + mm->context.noexec = s390_noexec; + mm->context.pgstes = 0; + } mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h index 65154dc..4c0698c 100644 --- a/include/asm-s390/pgtable.h +++ b/include/asm-s390/pgtable.h @@ -30,6 +30,7 @@ */ #ifndef __ASSEMBLY__ #include <linux/mm_types.h> +#include <asm/bitops.h> #include <asm/bug.h> #include <asm/processor.h> @@ -258,6 +259,13 @@ extern char empty_zero_page[PAGE_SIZE]; * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid. */ +/* Page status table bits for virtualization */ +#define RCP_PCL_BIT 55 +#define RCP_HR_BIT 54 +#define RCP_HC_BIT 53 +#define RCP_GR_BIT 50 +#define RCP_GC_BIT 49 + #ifndef __s390x__ /* Bits in the segment table address-space-control-element */ @@ -513,6 +521,48 @@ static inline int pte_file(pte_t pte) #define __HAVE_ARCH_PTE_SAME #define pte_same(a,b) (pte_val(a) == pte_val(b)) +static inline void rcp_lock(pte_t *ptep) +{ +#ifdef CONFIG_PGSTE + unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE); + preempt_disable(); + while (test_and_set_bit(RCP_PCL_BIT, pgste)) + ; +#endif +} + +static inline void rcp_unlock(pte_t *ptep) +{ +#ifdef CONFIG_PGSTE + unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE); + clear_bit(RCP_PCL_BIT, pgste); + preempt_enable(); +#endif +} + +/* forward declaration for SetPageUptodate in page-flags.h*/ +static inline void page_clear_dirty(struct page *page); +#include <linux/page-flags.h> + +static inline void ptep_rcp_copy(pte_t *ptep) +{ +#ifdef CONFIG_PGSTE + struct page *page = virt_to_page(pte_val(*ptep)); + unsigned int skey; + unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE); + + skey = page_get_storage_key(page_to_phys(page)); + if (skey & _PAGE_CHANGED) + set_bit_simple(RCP_GC_BIT, pgste); + if (skey & _PAGE_REFERENCED) + set_bit_simple(RCP_GR_BIT, pgste); + if (test_and_clear_bit_simple(RCP_HC_BIT, pgste)) + SetPageDirty(page); + if (test_and_clear_bit_simple(RCP_HR_BIT, pgste)) + SetPageReferenced(page); +#endif +} + /* * query functions pte_write/pte_dirty/pte_young only work if * pte_present() is true. Undefined behaviour if not.. @@ -599,6 +649,8 @@ static inline void pmd_clear(pmd_t *pmd) static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { + if (mm->context.pgstes) + ptep_rcp_copy(ptep); pte_val(*ptep) = _PAGE_TYPE_EMPTY; if (mm->context.noexec) pte_val(ptep[PTRS_PER_PTE]) = _PAGE_TYPE_EMPTY; @@ -667,6 +719,24 @@ static inline pte_t pte_mkyoung(pte_t pte) static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { +#ifdef CONFIG_PGSTE + unsigned long physpage; + int young; + unsigned long *pgste; + + if (!vma->vm_mm->context.pgstes) + return 0; + physpage = pte_val(*ptep) & PAGE_MASK; + pgste = (unsigned long *) (ptep + PTRS_PER_PTE); + + young = ((page_get_storage_key(physpage) & _PAGE_REFERENCED) != 0); + rcp_lock(ptep); + if (young) + set_bit_simple(RCP_GR_BIT, pgste); + young |= test_and_clear_bit_simple(RCP_HR_BIT, pgste); + rcp_unlock(ptep); + return young; +#endif return 0; } @@ -674,7 +744,13 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - /* No need to flush TLB; bits are in storage key */ + /* No need to flush TLB + * On s390 reference bits are in storage key and never in TLB + * With virtualization we handle the reference bit, without we + * we can simply return */ +#ifdef CONFIG_PGSTE + return ptep_test_and_clear_young(vma, address, ptep); +#endif return 0; } @@ -693,15 +769,25 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep) : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address)); } - pte_val(*ptep) = _PAGE_TYPE_EMPTY; } static inline void ptep_invalidate(struct mm_struct *mm, unsigned long address, pte_t *ptep) { + if (mm->context.pgstes) { + rcp_lock(ptep); + __ptep_ipte(address, ptep); + ptep_rcp_copy(ptep); + pte_val(*ptep) = _PAGE_TYPE_EMPTY; + rcp_unlock(ptep); + return; + } __ptep_ipte(address, ptep); - if (mm->context.noexec) + pte_val(*ptep) = _PAGE_TYPE_EMPTY; + if (mm->context.noexec) { __ptep_ipte(address, ptep + PTRS_PER_PTE); + pte_val(*(ptep + PTRS_PER_PTE)) = _PAGE_TYPE_EMPTY; + } } /* @@ -966,6 +1052,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) extern int add_shared_memory(unsigned long start, unsigned long size); extern int remove_shared_memory(unsigned long start, unsigned long size); +extern int s390_enable_sie(void); /* * No page table caches to initialise diff --git a/include/asm-s390/setup.h b/include/asm-s390/setup.h index a76a6b8..aaf4b51 100644 --- a/include/asm-s390/setup.h +++ b/include/asm-s390/setup.h @@ -62,6 +62,7 @@ extern unsigned long machine_flags; #define MACHINE_IS_VM (machine_flags & 1) #define MACHINE_IS_P390 (machine_flags & 4) #define MACHINE_HAS_MVPG (machine_flags & 16) +#define MACHINE_IS_KVM (machine_flags & 64) #define MACHINE_HAS_IDTE (machine_flags & 128) #define MACHINE_HAS_DIAG9C (machine_flags & 256) diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h index 7a71120..80eefef2 100644 --- a/include/asm-x86/kvm.h +++ b/include/asm-x86/kvm.h @@ -188,4 +188,45 @@ struct kvm_cpuid2 { struct kvm_cpuid_entry2 entries[0]; }; +/* for KVM_GET_PIT and KVM_SET_PIT */ +struct kvm_pit_channel_state { + __u32 count; /* can be 65536 */ + __u16 latched_count; + __u8 count_latched; + __u8 status_latched; + __u8 status; + __u8 read_state; + __u8 write_state; + __u8 write_latch; + __u8 rw_mode; + __u8 mode; + __u8 bcd; + __u8 gate; + __s64 count_load_time; +}; + +struct kvm_pit_state { + struct kvm_pit_channel_state channels[3]; +}; + +#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) +#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) +#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) +#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) +#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) +#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) +#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) +#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) +#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) +#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) +#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) +#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) +#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) +#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) +#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) +#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) +#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) +#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) +#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) + #endif diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h index 68ee390..9d963cd 100644 --- a/include/asm-x86/kvm_host.h +++ b/include/asm-x86/kvm_host.h @@ -20,6 +20,13 @@ #include <asm/desc.h> +#define KVM_MAX_VCPUS 16 +#define KVM_MEMORY_SLOTS 32 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + +#define KVM_PIO_PAGE_OFFSET 1 + #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ @@ -39,6 +46,13 @@ #define INVALID_PAGE (~(hpa_t)0) #define UNMAPPED_GVA (~(gpa_t)0) +/* shadow tables are PAE even on non-PAE hosts */ +#define KVM_HPAGE_SHIFT 21 +#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT) +#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1)) + +#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE) + #define DE_VECTOR 0 #define UD_VECTOR 6 #define NM_VECTOR 7 @@ -48,6 +62,7 @@ #define SS_VECTOR 12 #define GP_VECTOR 13 #define PF_VECTOR 14 +#define MC_VECTOR 18 #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 @@ -58,7 +73,8 @@ #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 -#define KVM_NUM_MMU_PAGES 1024 +#define KVM_MMU_HASH_SHIFT 10 +#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 40 @@ -106,6 +122,12 @@ enum { #define KVM_NR_MEM_OBJS 40 +struct kvm_guest_debug { + int enabled; + unsigned long bp[4]; + int singlestep; +}; + /* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache. @@ -140,6 +162,7 @@ union kvm_mmu_page_role { unsigned pad_for_nice_hex_output:6; unsigned metaphysical:1; unsigned access:3; + unsigned invalid:1; }; }; @@ -204,11 +227,6 @@ struct kvm_vcpu_arch { u64 shadow_efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ -#define VCPU_MP_STATE_RUNNABLE 0 -#define VCPU_MP_STATE_UNINITIALIZED 1 -#define VCPU_MP_STATE_INIT_RECEIVED 2 -#define VCPU_MP_STATE_SIPI_RECEIVED 3 -#define VCPU_MP_STATE_HALTED 4 int mp_state; int sipi_vector; u64 ia32_misc_enable_msr; @@ -226,8 +244,9 @@ struct kvm_vcpu_arch { u64 *last_pte_updated; struct { - gfn_t gfn; /* presumed gfn during guest pte update */ - struct page *page; /* page corresponding to that gfn */ + gfn_t gfn; /* presumed gfn during guest pte update */ + pfn_t pfn; /* pfn corresponding to that gfn */ + int largepage; } update_pte; struct i387_fxsave_struct host_fx_image; @@ -261,6 +280,11 @@ struct kvm_vcpu_arch { /* emulate context */ struct x86_emulate_ctxt emulate_ctxt; + + gpa_t time; + struct kvm_vcpu_time_info hv_clock; + unsigned int time_offset; + struct page *time_page; }; struct kvm_mem_alias { @@ -283,10 +307,13 @@ struct kvm_arch{ struct list_head active_mmu_pages; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; + struct kvm_pit *vpit; int round_robin_prev_vcpu; unsigned int tss_addr; struct page *apic_access_page; + + gpa_t wall_clock; }; struct kvm_vm_stat { @@ -298,6 +325,7 @@ struct kvm_vm_stat { u32 mmu_recycled; u32 mmu_cache_miss; u32 remote_tlb_flush; + u32 lpages; }; struct kvm_vcpu_stat { @@ -320,6 +348,7 @@ struct kvm_vcpu_stat { u32 fpu_reload; u32 insn_emulation; u32 insn_emulation_fail; + u32 hypercalls; }; struct descriptor_table { @@ -355,6 +384,7 @@ struct kvm_x86_ops { u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); + int (*get_cpl)(struct kvm_vcpu *vcpu); void (*set_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); @@ -410,6 +440,15 @@ void kvm_mmu_zap_all(struct kvm *kvm); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); + +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes); +int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, + gpa_t addr, unsigned long *ret); + +extern bool tdp_enabled; + enum emulation_result { EMULATE_DONE, /* no further processing */ EMULATE_DO_MMIO, /* kvm_run filled with mmio request */ @@ -429,6 +468,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr); void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, unsigned long *rflags); +void kvm_enable_efer_bits(u64); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); @@ -448,12 +488,14 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value); -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0); -unsigned long get_cr8(struct kvm_vcpu *vcpu); -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw); +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason); + +void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); +void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); +unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); +void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); @@ -491,6 +533,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code); +void kvm_enable_tdp(void); + int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int complete_pio(struct kvm_vcpu *vcpu); @@ -600,6 +644,7 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) #define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4" #define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4" #define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30" +#define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08" #define MSR_IA32_TIME_STAMP_COUNTER 0x010 @@ -610,4 +655,30 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) #define RMODE_TSS_SIZE \ (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1) +enum { + TASK_SWITCH_CALL = 0, + TASK_SWITCH_IRET = 1, + TASK_SWITCH_JMP = 2, + TASK_SWITCH_GATE = 3, +}; + +#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 5, d1, d2, d3, d4, d5) +#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 4, d1, d2, d3, d4, 0) +#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 3, d1, d2, d3, 0, 0) +#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 2, d1, d2, 0, 0, 0) +#define KVMTRACE_1D(evt, vcpu, d1, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 1, d1, 0, 0, 0, 0) +#define KVMTRACE_0D(evt, vcpu, name) \ + trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \ + vcpu, 0, 0, 0, 0, 0, 0) + #endif diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h index c6f3fd8..5098459 100644 --- a/include/asm-x86/kvm_para.h +++ b/include/asm-x86/kvm_para.h @@ -10,10 +10,65 @@ * paravirtualization, the appropriate feature bit should be checked. */ #define KVM_CPUID_FEATURES 0x40000001 +#define KVM_FEATURE_CLOCKSOURCE 0 +#define KVM_FEATURE_NOP_IO_DELAY 1 +#define KVM_FEATURE_MMU_OP 2 + +#define MSR_KVM_WALL_CLOCK 0x11 +#define MSR_KVM_SYSTEM_TIME 0x12 + +#define KVM_MAX_MMU_OP_BATCH 32 + +/* Operations for KVM_HC_MMU_OP */ +#define KVM_MMU_OP_WRITE_PTE 1 +#define KVM_MMU_OP_FLUSH_TLB 2 +#define KVM_MMU_OP_RELEASE_PT 3 + +/* Payload for KVM_HC_MMU_OP */ +struct kvm_mmu_op_header { + __u32 op; + __u32 pad; +}; + +struct kvm_mmu_op_write_pte { + struct kvm_mmu_op_header header; + __u64 pte_phys; + __u64 pte_val; +}; + +struct kvm_mmu_op_flush_tlb { + struct kvm_mmu_op_header header; +}; + +struct kvm_mmu_op_release_pt { + struct kvm_mmu_op_header header; + __u64 pt_phys; +}; #ifdef __KERNEL__ #include <asm/processor.h> +/* xen binary-compatible interface. See xen headers for details */ +struct kvm_vcpu_time_info { + uint32_t version; + uint32_t pad0; + uint64_t tsc_timestamp; + uint64_t system_time; + uint32_t tsc_to_system_mul; + int8_t tsc_shift; + int8_t pad[3]; +} __attribute__((__packed__)); /* 32 bytes */ + +struct kvm_wall_clock { + uint32_t wc_version; + uint32_t wc_sec; + uint32_t wc_nsec; +} __attribute__((__packed__)); + + +extern void kvmclock_init(void); + + /* This instruction is vmcall. On non-VT architectures, it will generate a * trap that we will then rewrite to the appropriate instruction. */ diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h index 6b5233b..e63741f 100644 --- a/include/asm-x86/reboot.h +++ b/include/asm-x86/reboot.h @@ -15,5 +15,7 @@ struct machine_ops { extern struct machine_ops machine_ops; void machine_real_restart(unsigned char *code, int length); +void native_machine_crash_shutdown(struct pt_regs *regs); +void native_machine_shutdown(void); #endif /* _ASM_REBOOT_H */ diff --git a/include/linux/kvm.h b/include/linux/kvm.h index c1ec04f..a281afe 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -8,11 +8,18 @@ */ #include <asm/types.h> +#include <linux/compiler.h> #include <linux/ioctl.h> #include <asm/kvm.h> #define KVM_API_VERSION 12 +/* for KVM_TRACE_ENABLE */ +struct kvm_user_trace_setup { + __u32 buf_size; /* sub_buffer size of each per-cpu */ + __u32 buf_nr; /* the number of sub_buffers of each per-cpu */ +}; + /* for KVM_CREATE_MEMORY_REGION */ struct kvm_memory_region { __u32 slot; @@ -73,6 +80,9 @@ struct kvm_irqchip { #define KVM_EXIT_INTR 10 #define KVM_EXIT_SET_TPR 11 #define KVM_EXIT_TPR_ACCESS 12 +#define KVM_EXIT_S390_SIEIC 13 +#define KVM_EXIT_S390_RESET 14 +#define KVM_EXIT_DCR 15 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { @@ -137,6 +147,27 @@ struct kvm_run { __u32 is_write; __u32 pad; } tpr_access; + /* KVM_EXIT_S390_SIEIC */ + struct { + __u8 icptcode; + __u64 mask; /* psw upper half */ + __u64 addr; /* psw lower half */ + __u16 ipa; + __u32 ipb; + } s390_sieic; + /* KVM_EXIT_S390_RESET */ +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + __u64 s390_reset_flags; + /* KVM_EXIT_DCR */ + struct { + __u32 dcrn; + __u32 data; + __u8 is_write; + } dcr; /* Fix the size of the union. */ char padding[256]; }; @@ -204,6 +235,74 @@ struct kvm_vapic_addr { __u64 vapic_addr; }; +/* for KVM_SET_MPSTATE */ + +#define KVM_MP_STATE_RUNNABLE 0 +#define KVM_MP_STATE_UNINITIALIZED 1 +#define KVM_MP_STATE_INIT_RECEIVED 2 +#define KVM_MP_STATE_HALTED 3 +#define KVM_MP_STATE_SIPI_RECEIVED 4 + +struct kvm_mp_state { + __u32 mp_state; +}; + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +#define KVM_TRC_SHIFT 16 +/* + * kvm trace categories + */ +#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) +#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) /* only 12 bits */ + +/* + * kvm trace action + */ +#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) +#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) +#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) + +#define KVM_TRC_HEAD_SIZE 12 +#define KVM_TRC_CYCLE_SIZE 8 +#define KVM_TRC_EXTRA_MAX 7 + +/* This structure represents a single trace buffer record. */ +struct kvm_trace_rec { + __u32 event:28; + __u32 extra_u32:3; + __u32 cycle_in:1; + __u32 pid; + __u32 vcpu_id; + union { + struct { + __u32 cycle_lo, cycle_hi; + __u32 extra_u32[KVM_TRC_EXTRA_MAX]; + } cycle; + struct { + __u32 extra_u32[KVM_TRC_EXTRA_MAX]; + } nocycle; + } u; +}; + #define KVMIO 0xAE /* @@ -212,6 +311,8 @@ struct kvm_vapic_addr { #define KVM_GET_API_VERSION _IO(KVMIO, 0x00) #define KVM_CREATE_VM _IO(KVMIO, 0x01) /* returns a VM fd */ #define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 0x02, struct kvm_msr_list) + +#define KVM_S390_ENABLE_SIE _IO(KVMIO, 0x06) /* * Check if a kvm extension is available. Argument is extension number, * return is 1 (yes) or 0 (no, sorry). @@ -222,7 +323,12 @@ struct kvm_vapic_addr { */ #define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ #define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) - +/* + * ioctls for kvm trace + */ +#define KVM_TRACE_ENABLE _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) +#define KVM_TRACE_PAUSE _IO(KVMIO, 0x07) +#define KVM_TRACE_DISABLE _IO(KVMIO, 0x08) /* * Extension capability list. */ @@ -233,6 +339,13 @@ struct kvm_vapic_addr { #define KVM_CAP_SET_TSS_ADDR 4 #define KVM_CAP_VAPIC 6 #define KVM_CAP_EXT_CPUID 7 +#define KVM_CAP_CLOCKSOURCE 8 +#define KVM_CAP_NR_VCPUS 9 /* returns max vcpus per vm */ +#define KVM_CAP_NR_MEMSLOTS 10 /* returns max memory slots per vm */ +#define KVM_CAP_PIT 11 +#define KVM_CAP_NOP_IO_DELAY 12 +#define KVM_CAP_PV_MMU 13 +#define KVM_CAP_MP_STATE 14 /* * ioctls for VM fds @@ -255,6 +368,9 @@ struct kvm_vapic_addr { #define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) #define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) #define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) +#define KVM_CREATE_PIT _IO(KVMIO, 0x64) +#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) +#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) /* * ioctls for vcpu fds @@ -281,5 +397,17 @@ struct kvm_vapic_addr { #define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) /* Available with KVM_CAP_VAPIC */ #define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr) +/* valid for virtual machine (for floating interrupt)_and_ vcpu */ +#define KVM_S390_INTERRUPT _IOW(KVMIO, 0x94, struct kvm_s390_interrupt) +/* store status for s390 */ +#define KVM_S390_STORE_STATUS_NOADDR (-1ul) +#define KVM_S390_STORE_STATUS_PREFIXED (-2ul) +#define KVM_S390_STORE_STATUS _IOW(KVMIO, 0x95, unsigned long) +/* initial ipl psw for s390 */ +#define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw) +/* initial reset for s390 */ +#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) +#define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state) +#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 928b0d59..3989789 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/preempt.h> +#include <linux/marker.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -24,29 +25,18 @@ #include <asm/kvm_host.h> -#define KVM_MAX_VCPUS 4 -#define KVM_MEMORY_SLOTS 8 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 4 - -#define KVM_PIO_PAGE_OFFSET 1 - /* * vcpu->requests bit members */ #define KVM_REQ_TLB_FLUSH 0 #define KVM_REQ_MIGRATE_TIMER 1 #define KVM_REQ_REPORT_TPR_ACCESS 2 +#define KVM_REQ_MMU_RELOAD 3 +#define KVM_REQ_TRIPLE_FAULT 4 struct kvm_vcpu; extern struct kmem_cache *kvm_vcpu_cache; -struct kvm_guest_debug { - int enabled; - unsigned long bp[4]; - int singlestep; -}; - /* * It would be nice to use something smarter than a linear search, TBD... * Thankfully we dont expect many devices to register (famous last words :), @@ -67,7 +57,9 @@ void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_vcpu { struct kvm *kvm; +#ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier preempt_notifier; +#endif int vcpu_id; struct mutex mutex; int cpu; @@ -100,6 +92,10 @@ struct kvm_memory_slot { unsigned long flags; unsigned long *rmap; unsigned long *dirty_bitmap; + struct { + unsigned long rmap_pde; + int write_count; + } *lpage_info; unsigned long userspace_addr; int user_alloc; }; @@ -114,11 +110,11 @@ struct kvm { KVM_PRIVATE_MEM_SLOTS]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; struct list_head vm_list; - struct file *filp; struct kvm_io_bus mmio_bus; struct kvm_io_bus pio_bus; struct kvm_vm_stat stat; struct kvm_arch arch; + atomic_t users_count; }; /* The guest did something we don't support. */ @@ -145,14 +141,19 @@ int kvm_init(void *opaque, unsigned int vcpu_size, struct module *module); void kvm_exit(void); +void kvm_get_kvm(struct kvm *kvm); +void kvm_put_kvm(struct kvm *kvm); + #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva); extern struct page *bad_page; +extern pfn_t bad_pfn; int is_error_page(struct page *page); +int is_error_pfn(pfn_t pfn); int kvm_is_error_hva(unsigned long addr); int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, @@ -166,8 +167,19 @@ int kvm_arch_set_memory_region(struct kvm *kvm, int user_alloc); gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn); struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); +unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); +void kvm_set_page_dirty(struct page *page); +void kvm_set_page_accessed(struct page *page); + +pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +void kvm_release_pfn_dirty(pfn_t); +void kvm_release_pfn_clean(pfn_t pfn); +void kvm_set_pfn_dirty(pfn_t pfn); +void kvm_set_pfn_accessed(pfn_t pfn); +void kvm_get_pfn(pfn_t pfn); + int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, @@ -188,6 +200,7 @@ void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); +void kvm_reload_remote_mmus(struct kvm *kvm); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -223,6 +236,10 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state); +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); @@ -255,6 +272,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *v); +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); static inline void kvm_guest_enter(void) @@ -296,5 +314,18 @@ struct kvm_stats_debugfs_item { struct dentry *dentry; }; extern struct kvm_stats_debugfs_item debugfs_entries[]; +extern struct dentry *kvm_debugfs_dir; + +#ifdef CONFIG_KVM_TRACE +int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg); +void kvm_trace_cleanup(void); +#else +static inline +int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg) +{ + return -EINVAL; +} +#define kvm_trace_cleanup() ((void)0) +#endif #endif diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index 5497aac..3ddce03 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -11,8 +11,11 @@ /* Return values for hypercalls */ #define KVM_ENOSYS 1000 +#define KVM_EFAULT EFAULT +#define KVM_E2BIG E2BIG -#define KVM_HC_VAPIC_POLL_IRQ 1 +#define KVM_HC_VAPIC_POLL_IRQ 1 +#define KVM_HC_MMU_OP 2 /* * hypercalls use architecture specific @@ -20,6 +23,12 @@ #include <asm/kvm_para.h> #ifdef __KERNEL__ +#ifdef CONFIG_KVM_GUEST +void __init kvm_guest_init(void); +#else +#define kvm_guest_init() do { } while (0) +#endif + static inline int kvm_para_has_feature(unsigned int feature) { if (kvm_arch_para_features() & (1UL << feature)) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 1c4e46d..9b6f395 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -38,6 +38,8 @@ typedef unsigned long hva_t; typedef u64 hpa_t; typedef unsigned long hfn_t; +typedef hfn_t pfn_t; + struct kvm_pio_request { unsigned long count; int cur_count; diff --git a/include/linux/sched.h b/include/linux/sched.h index d0bd970..9a4f3e6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1798,6 +1798,8 @@ extern void mmput(struct mm_struct *); extern struct mm_struct *get_task_mm(struct task_struct *task); /* Remove the current tasks stale references to the old mm_struct */ extern void mm_release(struct task_struct *, struct mm_struct *); +/* Allocate a new mm structure and copy contents from tsk->mm */ +extern struct mm_struct *dup_mm(struct task_struct *tsk); extern int copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *); extern void flush_thread(void); |