2009-10-30 12:47:05 +07:00
|
|
|
/*
|
|
|
|
|
* 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 SUSE Linux Products GmbH 2009
|
|
|
|
|
*
|
|
|
|
|
* Authors: Alexander Graf <agraf@suse.de>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef __ASM_KVM_BOOK3S_H__
|
|
|
|
|
#define __ASM_KVM_BOOK3S_H__
|
|
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
|
#include <linux/kvm_host.h>
|
2010-04-16 05:11:32 +07:00
|
|
|
#include <asm/kvm_book3s_asm.h>
|
2009-10-30 12:47:05 +07:00
|
|
|
|
|
|
|
|
struct kvmppc_bat {
|
2009-11-30 10:02:02 +07:00
|
|
|
u64 raw;
|
2009-10-30 12:47:05 +07:00
|
|
|
u32 bepi;
|
|
|
|
|
u32 bepi_mask;
|
|
|
|
|
u32 brpn;
|
|
|
|
|
u8 wimg;
|
|
|
|
|
u8 pp;
|
2010-03-25 03:48:36 +07:00
|
|
|
bool vs : 1;
|
|
|
|
|
bool vp : 1;
|
2009-10-30 12:47:05 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct kvmppc_sid_map {
|
|
|
|
|
u64 guest_vsid;
|
|
|
|
|
u64 guest_esid;
|
|
|
|
|
u64 host_vsid;
|
2010-03-25 03:48:36 +07:00
|
|
|
bool valid : 1;
|
2009-10-30 12:47:05 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#define SID_MAP_BITS 9
|
|
|
|
|
#define SID_MAP_NUM (1 << SID_MAP_BITS)
|
|
|
|
|
#define SID_MAP_MASK (SID_MAP_NUM - 1)
|
|
|
|
|
|
2010-08-15 13:04:24 +07:00
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
|
|
|
#define SID_CONTEXTS 1
|
|
|
|
|
#else
|
|
|
|
|
#define SID_CONTEXTS 128
|
|
|
|
|
#define VSID_POOL_SIZE (SID_CONTEXTS * 16)
|
|
|
|
|
#endif
|
|
|
|
|
|
2011-06-29 07:17:33 +07:00
|
|
|
struct hpte_cache {
|
|
|
|
|
struct hlist_node list_pte;
|
|
|
|
|
struct hlist_node list_pte_long;
|
|
|
|
|
struct hlist_node list_vpte;
|
|
|
|
|
struct hlist_node list_vpte_long;
|
|
|
|
|
struct rcu_head rcu_head;
|
|
|
|
|
u64 host_va;
|
|
|
|
|
u64 pfn;
|
|
|
|
|
ulong slot;
|
|
|
|
|
struct kvmppc_pte pte;
|
|
|
|
|
};
|
|
|
|
|
|
2009-10-30 12:47:05 +07:00
|
|
|
struct kvmppc_vcpu_book3s {
|
|
|
|
|
struct kvm_vcpu vcpu;
|
2010-04-16 05:11:40 +07:00
|
|
|
struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
|
2009-10-30 12:47:05 +07:00
|
|
|
struct kvmppc_sid_map sid_map[SID_MAP_NUM];
|
|
|
|
|
struct {
|
|
|
|
|
u64 esid;
|
|
|
|
|
u64 vsid;
|
|
|
|
|
} slb_shadow[64];
|
|
|
|
|
u8 slb_shadow_max;
|
|
|
|
|
struct kvmppc_bat ibat[8];
|
|
|
|
|
struct kvmppc_bat dbat[8];
|
|
|
|
|
u64 hid[6];
|
2010-02-19 17:00:33 +07:00
|
|
|
u64 gqr[8];
|
2009-10-30 12:47:05 +07:00
|
|
|
u64 sdr1;
|
|
|
|
|
u64 hior;
|
|
|
|
|
u64 msr_mask;
|
|
|
|
|
u64 vsid_next;
|
2010-08-15 13:04:24 +07:00
|
|
|
#ifdef CONFIG_PPC_BOOK3S_32
|
|
|
|
|
u32 vsid_pool[VSID_POOL_SIZE];
|
|
|
|
|
#else
|
|
|
|
|
u64 vsid_first;
|
2009-10-30 12:47:05 +07:00
|
|
|
u64 vsid_max;
|
2010-08-15 13:04:24 +07:00
|
|
|
#endif
|
|
|
|
|
int context_id[SID_CONTEXTS];
|
2011-06-29 07:17:33 +07:00
|
|
|
|
|
|
|
|
struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
|
|
|
|
|
struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
|
|
|
|
|
struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
|
|
|
|
|
struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
|
|
|
|
|
int hpte_cache_count;
|
|
|
|
|
spinlock_t mmu_lock;
|
2009-10-30 12:47:05 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#define CONTEXT_HOST 0
|
|
|
|
|
#define CONTEXT_GUEST 1
|
|
|
|
|
#define CONTEXT_GUEST_END 2
|
|
|
|
|
|
2010-04-20 07:49:48 +07:00
|
|
|
#define VSID_REAL 0x1fffffffffc00000ULL
|
|
|
|
|
#define VSID_BAT 0x1fffffffffb00000ULL
|
|
|
|
|
#define VSID_REAL_DR 0x2000000000000000ULL
|
|
|
|
|
#define VSID_REAL_IR 0x4000000000000000ULL
|
2010-03-25 03:48:35 +07:00
|
|
|
#define VSID_PR 0x8000000000000000ULL
|
2009-10-30 12:47:05 +07:00
|
|
|
|
2010-04-20 07:49:46 +07:00
|
|
|
extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask);
|
2009-10-30 12:47:05 +07:00
|
|
|
extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask);
|
2010-04-20 07:49:46 +07:00
|
|
|
extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end);
|
2009-10-30 12:47:05 +07:00
|
|
|
extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
|
2011-06-29 07:17:58 +07:00
|
|
|
extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr);
|
2009-10-30 12:47:05 +07:00
|
|
|
extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
|
|
|
|
|
extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
|
KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:21:34 +07:00
|
|
|
extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
|
2009-10-30 12:47:05 +07:00
|
|
|
extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
|
|
|
|
|
extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
|
|
|
|
|
extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
|
2010-06-30 20:18:46 +07:00
|
|
|
|
|
|
|
|
extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
|
|
|
|
|
extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
|
|
|
|
|
extern void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu);
|
|
|
|
|
extern int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu);
|
|
|
|
|
extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
|
|
|
|
|
extern int kvmppc_mmu_hpte_sysinit(void);
|
|
|
|
|
extern void kvmppc_mmu_hpte_sysexit(void);
|
KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:21:34 +07:00
|
|
|
extern int kvmppc_mmu_hv_init(void);
|
2010-06-30 20:18:46 +07:00
|
|
|
|
2010-02-19 17:00:38 +07:00
|
|
|
extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
|
|
|
|
|
extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
|
2009-10-30 12:47:05 +07:00
|
|
|
extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
|
KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:21:34 +07:00
|
|
|
extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags);
|
2009-11-30 10:02:02 +07:00
|
|
|
extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
|
|
|
|
|
bool upper, u32 val);
|
2010-02-19 17:00:39 +07:00
|
|
|
extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
|
2010-02-19 17:00:44 +07:00
|
|
|
extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
|
2010-07-29 19:47:54 +07:00
|
|
|
extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
|
2009-10-30 12:47:05 +07:00
|
|
|
|
2011-07-23 14:41:44 +07:00
|
|
|
extern void kvmppc_entry_trampoline(void);
|
KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:21:34 +07:00
|
|
|
extern void kvmppc_hv_entry_trampoline(void);
|
2010-01-15 20:49:10 +07:00
|
|
|
extern void kvmppc_load_up_fpu(void);
|
|
|
|
|
extern void kvmppc_load_up_altivec(void);
|
|
|
|
|
extern void kvmppc_load_up_vsx(void);
|
2010-03-25 03:48:28 +07:00
|
|
|
extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
|
|
|
|
|
extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
|
2011-08-08 22:21:15 +07:00
|
|
|
extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
|
2009-10-30 12:47:05 +07:00
|
|
|
|
|
|
|
|
static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu);
|
|
|
|
|
}
|
|
|
|
|
|
KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:21:34 +07:00
|
|
|
extern void kvm_return_point(void);
|
|
|
|
|
|
|
|
|
|
/* Also add subarch specific defines */
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
|
|
|
|
|
#include <asm/kvm_book3s_32.h>
|
|
|
|
|
#endif
|
|
|
|
|
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
|
|
|
|
|
#include <asm/kvm_book3s_64.h>
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_KVM_BOOK3S_PR
|
|
|
|
|
|
2011-06-29 07:17:58 +07:00
|
|
|
static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_book3s(vcpu)->hior;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
|
|
|
|
|
unsigned long pending_now, unsigned long old_pending)
|
|
|
|
|
{
|
|
|
|
|
if (pending_now)
|
|
|
|
|
vcpu->arch.shared->int_pending = 1;
|
|
|
|
|
else if (old_pending)
|
|
|
|
|
vcpu->arch.shared->int_pending = 0;
|
|
|
|
|
}
|
|
|
|
|
|
2010-04-16 05:11:40 +07:00
|
|
|
static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
|
|
|
|
|
{
|
|
|
|
|
if ( num < 14 ) {
|
|
|
|
|
to_svcpu(vcpu)->gpr[num] = val;
|
|
|
|
|
to_book3s(vcpu)->shadow_vcpu->gpr[num] = val;
|
|
|
|
|
} else
|
|
|
|
|
vcpu->arch.gpr[num] = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
|
|
|
|
|
{
|
|
|
|
|
if ( num < 14 )
|
|
|
|
|
return to_svcpu(vcpu)->gpr[num];
|
|
|
|
|
else
|
|
|
|
|
return vcpu->arch.gpr[num];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
|
|
|
|
|
{
|
|
|
|
|
to_svcpu(vcpu)->cr = val;
|
|
|
|
|
to_book3s(vcpu)->shadow_vcpu->cr = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_svcpu(vcpu)->cr;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
|
|
|
|
|
{
|
|
|
|
|
to_svcpu(vcpu)->xer = val;
|
|
|
|
|
to_book3s(vcpu)->shadow_vcpu->xer = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_svcpu(vcpu)->xer;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
|
|
|
|
|
{
|
|
|
|
|
to_svcpu(vcpu)->ctr = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_svcpu(vcpu)->ctr;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
|
|
|
|
|
{
|
|
|
|
|
to_svcpu(vcpu)->lr = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_svcpu(vcpu)->lr;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
|
|
|
|
|
{
|
|
|
|
|
to_svcpu(vcpu)->pc = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_svcpu(vcpu)->pc;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
ulong pc = kvmppc_get_pc(vcpu);
|
|
|
|
|
struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
|
|
|
|
|
|
|
|
|
|
/* Load the instruction manually if it failed to do so in the
|
|
|
|
|
* exit path */
|
|
|
|
|
if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
|
|
|
|
|
kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
|
|
|
|
|
|
|
|
|
|
return svcpu->last_inst;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return to_svcpu(vcpu)->fault_dar;
|
|
|
|
|
}
|
2009-10-30 12:47:05 +07:00
|
|
|
|
2011-06-29 07:17:58 +07:00
|
|
|
static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
ulong crit_raw = vcpu->arch.shared->critical;
|
|
|
|
|
ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
|
|
|
|
|
bool crit;
|
|
|
|
|
|
|
|
|
|
/* Truncate crit indicators in 32 bit mode */
|
|
|
|
|
if (!(vcpu->arch.shared->msr & MSR_SF)) {
|
|
|
|
|
crit_raw &= 0xffffffff;
|
|
|
|
|
crit_r1 &= 0xffffffff;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Critical section when crit == r1 */
|
|
|
|
|
crit = (crit_raw == crit_r1);
|
|
|
|
|
/* ... and we're in supervisor mode */
|
|
|
|
|
crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
|
|
|
|
|
|
|
|
|
|
return crit;
|
|
|
|
|
}
|
KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:21:34 +07:00
|
|
|
#else /* CONFIG_KVM_BOOK3S_PR */
|
|
|
|
|
|
|
|
|
|
static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
|
|
|
|
|
unsigned long pending_now, unsigned long old_pending)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
|
|
|
|
|
{
|
|
|
|
|
vcpu->arch.gpr[num] = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.gpr[num];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
|
|
|
|
|
{
|
|
|
|
|
vcpu->arch.cr = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.cr;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
|
|
|
|
|
{
|
|
|
|
|
vcpu->arch.xer = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.xer;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
|
|
|
|
|
{
|
|
|
|
|
vcpu->arch.ctr = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.ctr;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
|
|
|
|
|
{
|
|
|
|
|
vcpu->arch.lr = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.lr;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
|
|
|
|
|
{
|
|
|
|
|
vcpu->arch.pc = val;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.pc;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
ulong pc = kvmppc_get_pc(vcpu);
|
|
|
|
|
|
|
|
|
|
/* Load the instruction manually if it failed to do so in the
|
|
|
|
|
* exit path */
|
|
|
|
|
if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
|
|
|
|
|
kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
|
|
|
|
|
|
|
|
|
|
return vcpu->arch.last_inst;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return vcpu->arch.fault_dar;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
|
|
|
|
|
{
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
#endif
|
2011-06-29 07:17:58 +07:00
|
|
|
|
2010-03-25 03:48:30 +07:00
|
|
|
/* Magic register values loaded into r3 and r4 before the 'sc' assembly
|
|
|
|
|
* instruction for the OSI hypercalls */
|
|
|
|
|
#define OSI_SC_MAGIC_R3 0x113724FA
|
|
|
|
|
#define OSI_SC_MAGIC_R4 0x77810F9B
|
|
|
|
|
|
2009-10-30 12:47:05 +07:00
|
|
|
#define INS_DCBZ 0x7c0007ec
|
|
|
|
|
|
|
|
|
|
#endif /* __ASM_KVM_BOOK3S_H__ */
|