2009-10-30 13:47:06 +08:00
|
|
|
/*
|
|
|
|
|
* 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_ASM_H__
|
|
|
|
|
#define __ASM_KVM_BOOK3S_ASM_H__
|
|
|
|
|
|
2010-01-08 09:58:03 +08:00
|
|
|
#ifdef __ASSEMBLY__
|
|
|
|
|
|
2010-04-16 06:11:41 +08:00
|
|
|
#ifdef CONFIG_KVM_BOOK3S_HANDLER
|
2009-10-30 13:47:06 +08:00
|
|
|
|
|
|
|
|
#include <asm/kvm_asm.h>
|
|
|
|
|
|
|
|
|
|
.macro DO_KVM intno
|
|
|
|
|
.if (\intno == BOOK3S_INTERRUPT_SYSTEM_RESET) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_MACHINE_CHECK) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_DATA_STORAGE) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_INST_STORAGE) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_DATA_SEGMENT) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_INST_SEGMENT) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_EXTERNAL) || \
|
2011-04-05 12:20:31 +08:00
|
|
|
(\intno == BOOK3S_INTERRUPT_EXTERNAL_HV) || \
|
2009-10-30 13:47:06 +08:00
|
|
|
(\intno == BOOK3S_INTERRUPT_ALIGNMENT) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_PROGRAM) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_FP_UNAVAIL) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_DECREMENTER) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_SYSCALL) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_TRACE) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_PERFMON) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_ALTIVEC) || \
|
|
|
|
|
(\intno == BOOK3S_INTERRUPT_VSX)
|
|
|
|
|
|
|
|
|
|
b kvmppc_trampoline_\intno
|
|
|
|
|
kvmppc_resume_\intno:
|
|
|
|
|
|
|
|
|
|
.endif
|
|
|
|
|
.endm
|
|
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
|
|
.macro DO_KVM intno
|
|
|
|
|
.endm
|
|
|
|
|
|
2010-04-16 06:11:41 +08:00
|
|
|
#endif /* CONFIG_KVM_BOOK3S_HANDLER */
|
2009-10-30 13:47:06 +08:00
|
|
|
|
2010-01-08 09:58:03 +08:00
|
|
|
#else /*__ASSEMBLY__ */
|
|
|
|
|
|
2011-06-29 08:20:58 +08:00
|
|
|
/*
|
|
|
|
|
* This struct goes in the PACA on 64-bit processors. It is used
|
|
|
|
|
* to store host state that needs to be saved when we enter a guest
|
|
|
|
|
* and restored when we exit, but isn't specific to any particular
|
|
|
|
|
* guest or vcpu. It also has some scratch fields used by the guest
|
|
|
|
|
* exit code.
|
|
|
|
|
*/
|
|
|
|
|
struct kvmppc_host_state {
|
|
|
|
|
ulong host_r1;
|
|
|
|
|
ulong host_r2;
|
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 08:21:34 +08:00
|
|
|
ulong host_msr;
|
2011-06-29 08:20:58 +08:00
|
|
|
ulong vmhandler;
|
|
|
|
|
ulong scratch0;
|
|
|
|
|
ulong scratch1;
|
|
|
|
|
u8 in_guest;
|
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 08:21:34 +08:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_KVM_BOOK3S_64_HV
|
|
|
|
|
struct kvm_vcpu *kvm_vcpu;
|
KVM: PPC: Allow book3s_hv guests to use SMT processor modes
This lifts the restriction that book3s_hv guests can only run one
hardware thread per core, and allows them to use up to 4 threads
per core on POWER7. The host still has to run single-threaded.
This capability is advertised to qemu through a new KVM_CAP_PPC_SMT
capability. The return value of the ioctl querying this capability
is the number of vcpus per virtual CPU core (vcore), currently 4.
To use this, the host kernel should be booted with all threads
active, and then all the secondary threads should be offlined.
This will put the secondary threads into nap mode. KVM will then
wake them from nap mode and use them for running guest code (while
they are still offline). To wake the secondary threads, we send
them an IPI using a new xics_wake_cpu() function, implemented in
arch/powerpc/sysdev/xics/icp-native.c. In other words, at this stage
we assume that the platform has a XICS interrupt controller and
we are using icp-native.c to drive it. Since the woken thread will
need to acknowledge and clear the IPI, we also export the base
physical address of the XICS registers using kvmppc_set_xics_phys()
for use in the low-level KVM book3s code.
When a vcpu is created, it is assigned to a virtual CPU core.
The vcore number is obtained by dividing the vcpu number by the
number of threads per core in the host. This number is exported
to userspace via the KVM_CAP_PPC_SMT capability. If qemu wishes
to run the guest in single-threaded mode, it should make all vcpu
numbers be multiples of the number of threads per core.
We distinguish three states of a vcpu: runnable (i.e., ready to execute
the guest), blocked (that is, idle), and busy in host. We currently
implement a policy that the vcore can run only when all its threads
are runnable or blocked. This way, if a vcpu needs to execute elsewhere
in the kernel or in qemu, it can do so without being starved of CPU
by the other vcpus.
When a vcore starts to run, it executes in the context of one of the
vcpu threads. The other vcpu threads all go to sleep and stay asleep
until something happens requiring the vcpu thread to return to qemu,
or to wake up to run the vcore (this can happen when another vcpu
thread goes from busy in host state to blocked).
It can happen that a vcpu goes from blocked to runnable state (e.g.
because of an interrupt), and the vcore it belongs to is already
running. In that case it can start to run immediately as long as
the none of the vcpus in the vcore have started to exit the guest.
We send the next free thread in the vcore an IPI to get it to start
to execute the guest. It synchronizes with the other threads via
the vcore->entry_exit_count field to make sure that it doesn't go
into the guest if the other vcpus are exiting by the time that it
is ready to actually enter the guest.
Note that there is no fixed relationship between the hardware thread
number and the vcpu number. Hardware threads are assigned to vcpus
as they become runnable, so we will always use the lower-numbered
hardware threads in preference to higher-numbered threads if not all
the vcpus in the vcore are runnable, regardless of which vcpus are
runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:23:08 +08:00
|
|
|
struct kvmppc_vcore *kvm_vcore;
|
|
|
|
|
unsigned long xics_phys;
|
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 08:21:34 +08:00
|
|
|
u64 dabr;
|
|
|
|
|
u64 host_mmcr[3];
|
|
|
|
|
u32 host_pmc[6];
|
|
|
|
|
u64 host_purr;
|
|
|
|
|
u64 host_spurr;
|
|
|
|
|
u64 host_dscr;
|
|
|
|
|
u64 dec_expires;
|
|
|
|
|
#endif
|
2011-06-29 08:20:58 +08:00
|
|
|
};
|
|
|
|
|
|
2010-01-08 09:58:03 +08:00
|
|
|
struct kvmppc_book3s_shadow_vcpu {
|
|
|
|
|
ulong gpr[14];
|
|
|
|
|
u32 cr;
|
|
|
|
|
u32 xer;
|
2010-04-16 06:11:39 +08:00
|
|
|
|
|
|
|
|
u32 fault_dsisr;
|
|
|
|
|
u32 last_inst;
|
|
|
|
|
ulong ctr;
|
|
|
|
|
ulong lr;
|
|
|
|
|
ulong pc;
|
|
|
|
|
ulong shadow_srr1;
|
|
|
|
|
ulong fault_dar;
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S_32
|
|
|
|
|
u32 sr[16]; /* Guest SRs */
|
2011-06-29 08:20:58 +08:00
|
|
|
|
|
|
|
|
struct kvmppc_host_state hstate;
|
2010-04-16 06:11:39 +08:00
|
|
|
#endif
|
2011-06-29 08:20:58 +08:00
|
|
|
|
2010-04-16 06:11:39 +08:00
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
|
|
|
u8 slb_max; /* highest used guest slb entry */
|
|
|
|
|
struct {
|
|
|
|
|
u64 esid;
|
|
|
|
|
u64 vsid;
|
|
|
|
|
} slb[64]; /* guest SLB */
|
|
|
|
|
#endif
|
2010-01-08 09:58:03 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#endif /*__ASSEMBLY__ */
|
|
|
|
|
|
2009-10-30 13:47:06 +08:00
|
|
|
#endif /* __ASM_KVM_BOOK3S_ASM_H__ */
|