2008-04-17 04:28:09 +00:00
|
|
|
/*
|
|
|
|
|
* 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 IBM Corp. 2008
|
|
|
|
|
*
|
|
|
|
|
* Authors: Hollis Blanchard <hollisb@us.ibm.com>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef __POWERPC_KVM_ASM_H__
|
|
|
|
|
#define __POWERPC_KVM_ASM_H__
|
|
|
|
|
|
2012-04-25 11:48:54 +00:00
|
|
|
#ifdef __ASSEMBLY__
|
2012-04-25 01:26:43 +00:00
|
|
|
#ifdef CONFIG_64BIT
|
|
|
|
|
#define PPC_STD(sreg, offset, areg) std sreg, (offset)(areg)
|
|
|
|
|
#define PPC_LD(treg, offset, areg) ld treg, (offset)(areg)
|
|
|
|
|
#else
|
|
|
|
|
#define PPC_STD(sreg, offset, areg) stw sreg, (offset+4)(areg)
|
|
|
|
|
#define PPC_LD(treg, offset, areg) lwz treg, (offset+4)(areg)
|
|
|
|
|
#endif
|
2012-04-25 11:48:54 +00:00
|
|
|
#endif
|
2012-04-25 01:26:43 +00:00
|
|
|
|
2008-04-17 04:28:09 +00:00
|
|
|
/* 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
|
2009-01-03 22:23:13 +00:00
|
|
|
|
|
|
|
|
/* E500 */
|
2013-06-07 00:16:29 +00:00
|
|
|
#define BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL 32
|
|
|
|
|
#define BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST 33
|
|
|
|
|
/*
|
|
|
|
|
* TODO: Unify 32-bit and 64-bit kernel exception handlers to use same defines
|
|
|
|
|
*/
|
|
|
|
|
#define BOOKE_INTERRUPT_SPE_UNAVAIL BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL
|
|
|
|
|
#define BOOKE_INTERRUPT_SPE_FP_DATA BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST
|
|
|
|
|
#define BOOKE_INTERRUPT_ALTIVEC_UNAVAIL BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL
|
|
|
|
|
#define BOOKE_INTERRUPT_ALTIVEC_ASSIST \
|
|
|
|
|
BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST
|
2009-01-03 22:23:13 +00:00
|
|
|
#define BOOKE_INTERRUPT_SPE_FP_ROUND 34
|
|
|
|
|
#define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
|
2011-12-20 15:34:43 +00:00
|
|
|
#define BOOKE_INTERRUPT_DOORBELL 36
|
|
|
|
|
#define BOOKE_INTERRUPT_DOORBELL_CRITICAL 37
|
|
|
|
|
|
|
|
|
|
/* booke_hv */
|
|
|
|
|
#define BOOKE_INTERRUPT_GUEST_DBELL 38
|
|
|
|
|
#define BOOKE_INTERRUPT_GUEST_DBELL_CRIT 39
|
|
|
|
|
#define BOOKE_INTERRUPT_HV_SYSCALL 40
|
|
|
|
|
#define BOOKE_INTERRUPT_HV_PRIV 41
|
2013-08-08 12:56:09 +00:00
|
|
|
#define BOOKE_INTERRUPT_LRAT_ERROR 42
|
2008-04-17 04:28:09 +00:00
|
|
|
|
2009-10-30 05:47:03 +00:00
|
|
|
/* book3s */
|
|
|
|
|
|
|
|
|
|
#define BOOK3S_INTERRUPT_SYSTEM_RESET 0x100
|
|
|
|
|
#define BOOK3S_INTERRUPT_MACHINE_CHECK 0x200
|
|
|
|
|
#define BOOK3S_INTERRUPT_DATA_STORAGE 0x300
|
|
|
|
|
#define BOOK3S_INTERRUPT_DATA_SEGMENT 0x380
|
|
|
|
|
#define BOOK3S_INTERRUPT_INST_STORAGE 0x400
|
|
|
|
|
#define BOOK3S_INTERRUPT_INST_SEGMENT 0x480
|
|
|
|
|
#define BOOK3S_INTERRUPT_EXTERNAL 0x500
|
2010-08-30 08:44:15 +00:00
|
|
|
#define BOOK3S_INTERRUPT_EXTERNAL_LEVEL 0x501
|
2011-04-05 04:20:31 +00:00
|
|
|
#define BOOK3S_INTERRUPT_EXTERNAL_HV 0x502
|
2009-10-30 05:47:03 +00:00
|
|
|
#define BOOK3S_INTERRUPT_ALIGNMENT 0x600
|
|
|
|
|
#define BOOK3S_INTERRUPT_PROGRAM 0x700
|
|
|
|
|
#define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800
|
|
|
|
|
#define BOOK3S_INTERRUPT_DECREMENTER 0x900
|
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 00:21:34 +00:00
|
|
|
#define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980
|
2009-10-30 05:47:03 +00:00
|
|
|
#define BOOK3S_INTERRUPT_SYSCALL 0xc00
|
|
|
|
|
#define BOOK3S_INTERRUPT_TRACE 0xd00
|
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 00:21:34 +00:00
|
|
|
#define BOOK3S_INTERRUPT_H_DATA_STORAGE 0xe00
|
|
|
|
|
#define BOOK3S_INTERRUPT_H_INST_STORAGE 0xe20
|
|
|
|
|
#define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40
|
2009-10-30 05:47:03 +00:00
|
|
|
#define BOOK3S_INTERRUPT_PERFMON 0xf00
|
|
|
|
|
#define BOOK3S_INTERRUPT_ALTIVEC 0xf20
|
|
|
|
|
#define BOOK3S_INTERRUPT_VSX 0xf40
|
|
|
|
|
|
|
|
|
|
#define BOOK3S_IRQPRIO_SYSTEM_RESET 0
|
|
|
|
|
#define BOOK3S_IRQPRIO_DATA_SEGMENT 1
|
|
|
|
|
#define BOOK3S_IRQPRIO_INST_SEGMENT 2
|
|
|
|
|
#define BOOK3S_IRQPRIO_DATA_STORAGE 3
|
|
|
|
|
#define BOOK3S_IRQPRIO_INST_STORAGE 4
|
|
|
|
|
#define BOOK3S_IRQPRIO_ALIGNMENT 5
|
|
|
|
|
#define BOOK3S_IRQPRIO_PROGRAM 6
|
|
|
|
|
#define BOOK3S_IRQPRIO_FP_UNAVAIL 7
|
|
|
|
|
#define BOOK3S_IRQPRIO_ALTIVEC 8
|
|
|
|
|
#define BOOK3S_IRQPRIO_VSX 9
|
|
|
|
|
#define BOOK3S_IRQPRIO_SYSCALL 10
|
|
|
|
|
#define BOOK3S_IRQPRIO_MACHINE_CHECK 11
|
|
|
|
|
#define BOOK3S_IRQPRIO_DEBUG 12
|
|
|
|
|
#define BOOK3S_IRQPRIO_EXTERNAL 13
|
|
|
|
|
#define BOOK3S_IRQPRIO_DECREMENTER 14
|
|
|
|
|
#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR 15
|
2010-08-30 08:44:15 +00:00
|
|
|
#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL 16
|
|
|
|
|
#define BOOK3S_IRQPRIO_MAX 17
|
2009-10-30 05:47:03 +00:00
|
|
|
|
|
|
|
|
#define BOOK3S_HFLAG_DCBZ32 0x1
|
2009-11-30 03:02:02 +00:00
|
|
|
#define BOOK3S_HFLAG_SLB 0x2
|
2010-02-19 10:00:32 +00:00
|
|
|
#define BOOK3S_HFLAG_PAIRED_SINGLE 0x4
|
2010-04-20 00:49:54 +00:00
|
|
|
#define BOOK3S_HFLAG_NATIVE_PS 0x8
|
2013-09-20 04:52:44 +00:00
|
|
|
#define BOOK3S_HFLAG_MULTI_PGSIZE 0x10
|
|
|
|
|
#define BOOK3S_HFLAG_NEW_TLBIE 0x20
|
2009-10-30 05:47:03 +00:00
|
|
|
|
2008-04-17 04:28:09 +00:00
|
|
|
#define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */
|
|
|
|
|
#define RESUME_FLAG_HOST (1<<1) /* Resume host? */
|
2012-10-15 01:16:48 +00:00
|
|
|
#define RESUME_FLAG_ARCH1 (1<<2)
|
2008-04-17 04:28:09 +00:00
|
|
|
|
|
|
|
|
#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)
|
|
|
|
|
|
2010-01-08 01:58:04 +00:00
|
|
|
#define KVM_GUEST_MODE_NONE 0
|
|
|
|
|
#define KVM_GUEST_MODE_GUEST 1
|
|
|
|
|
#define KVM_GUEST_MODE_SKIP 2
|
KVM: PPC: Book3S HV: Better handling of exceptions that happen in real mode
When an interrupt or exception happens in the guest that comes to the
host, the CPU goes to hypervisor real mode (MMU off) to handle the
exception but doesn't change the MMU context. After saving a few
registers, we then clear the "in guest" flag. If, for any reason,
we get an exception in the real-mode code, that then gets handled
by the normal kernel exception handlers, which turn the MMU on. This
is disastrous if the MMU is still set to the guest context, since we
end up executing instructions from random places in the guest kernel
with hypervisor privilege.
In order to catch this situation, we define a new value for the "in guest"
flag, KVM_GUEST_MODE_HOST_HV, to indicate that we are in hypervisor real
mode with guest MMU context. If the "in guest" flag is set to this value,
we branch off to an emergency handler. For the moment, this just does
a branch to self to stop the CPU from doing anything further.
While we're here, we define another new flag value to indicate that we
are in a HV guest, as distinct from a PR guest. This will be useful
when we have a kernel that can support both PR and HV guests concurrently.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-10-04 11:45:04 +00:00
|
|
|
#define KVM_GUEST_MODE_GUEST_HV 3
|
|
|
|
|
#define KVM_GUEST_MODE_HOST_HV 4
|
2010-01-08 01:58:04 +00:00
|
|
|
|
|
|
|
|
#define KVM_INST_FETCH_FAILED -1
|
|
|
|
|
|
2008-04-17 04:28:09 +00:00
|
|
|
#endif /* __POWERPC_KVM_ASM_H__ */
|
