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
|
|
|
/*
|
|
|
|
* Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
|
|
|
|
* Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* Paul Mackerras <paulus@au1.ibm.com>
|
|
|
|
* Alexander Graf <agraf@suse.de>
|
|
|
|
* Kevin Wolf <mail@kevin-wolf.de>
|
|
|
|
*
|
|
|
|
* Description: KVM functions specific to running on Book 3S
|
|
|
|
* processors in hypervisor mode (specifically POWER7 and later).
|
|
|
|
*
|
|
|
|
* This file is derived from arch/powerpc/kvm/book3s.c,
|
|
|
|
* by Alexander Graf <agraf@suse.de>.
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kvm_host.h>
|
|
|
|
#include <linux/err.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/preempt.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/delay.h>
|
2011-05-27 21:46:24 +07:00
|
|
|
#include <linux/export.h>
|
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
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/anon_inodes.h>
|
2016-05-11 08:15:55 +07:00
|
|
|
#include <linux/cpu.h>
|
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
|
|
|
#include <linux/cpumask.h>
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/page-flags.h>
|
2012-09-11 20:27:01 +07:00
|
|
|
#include <linux/srcu.h>
|
2013-12-09 19:53:42 +07:00
|
|
|
#include <linux/miscdevice.h>
|
2015-03-28 10:21:01 +07:00
|
|
|
#include <linux/debugfs.h>
|
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
|
|
|
|
|
|
|
#include <asm/reg.h>
|
|
|
|
#include <asm/cputable.h>
|
|
|
|
#include <asm/cacheflush.h>
|
|
|
|
#include <asm/tlbflush.h>
|
2016-12-25 02:46:01 +07:00
|
|
|
#include <linux/uaccess.h>
|
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
|
|
|
#include <asm/io.h>
|
|
|
|
#include <asm/kvm_ppc.h>
|
|
|
|
#include <asm/kvm_book3s.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
#include <asm/lppaca.h>
|
|
|
|
#include <asm/processor.h>
|
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 07:23:08 +07:00
|
|
|
#include <asm/cputhreads.h>
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
#include <asm/page.h>
|
2011-11-10 03:39:49 +07:00
|
|
|
#include <asm/hvcall.h>
|
2012-03-29 00:30:02 +07:00
|
|
|
#include <asm/switch_to.h>
|
2012-10-15 08:15:41 +07:00
|
|
|
#include <asm/smp.h>
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
#include <asm/dbell.h>
|
KVM: PPC: Book3S HV: Fix TB corruption in guest exit path on HMI interrupt
When a guest is assigned to a core it converts the host Timebase (TB)
into guest TB by adding guest timebase offset before entering into
guest. During guest exit it restores the guest TB to host TB. This means
under certain conditions (Guest migration) host TB and guest TB can differ.
When we get an HMI for TB related issues the opal HMI handler would
try fixing errors and restore the correct host TB value. With no guest
running, we don't have any issues. But with guest running on the core
we run into TB corruption issues.
If we get an HMI while in the guest, the current HMI handler invokes opal
hmi handler before forcing guest to exit. The guest exit path subtracts
the guest TB offset from the current TB value which may have already
been restored with host value by opal hmi handler. This leads to incorrect
host and guest TB values.
With split-core, things become more complex. With split-core, TB also gets
split and each subcore gets its own TB register. When a hmi handler fixes
a TB error and restores the TB value, it affects all the TB values of
sibling subcores on the same core. On TB errors all the thread in the core
gets HMI. With existing code, the individual threads call opal hmi handle
independently which can easily throw TB out of sync if we have guest
running on subcores. Hence we will need to co-ordinate with all the
threads before making opal hmi handler call followed by TB resync.
This patch introduces a sibling subcore state structure (shared by all
threads in the core) in paca which holds information about whether sibling
subcores are in Guest mode or host mode. An array in_guest[] of size
MAX_SUBCORE_PER_CORE=4 is used to maintain the state of each subcore.
The subcore id is used as index into in_guest[] array. Only primary
thread entering/exiting the guest is responsible to set/unset its
designated array element.
On TB error, we get HMI interrupt on every thread on the core. Upon HMI,
this patch will now force guest to vacate the core/subcore. Primary
thread from each subcore will then turn off its respective bit
from the above bitmap during the guest exit path just after the
guest->host partition switch is complete.
All other threads that have just exited the guest OR were already in host
will wait until all other subcores clears their respective bit.
Once all the subcores turn off their respective bit, all threads will
will make call to opal hmi handler.
It is not necessary that opal hmi handler would resync the TB value for
every HMI interrupts. It would do so only for the HMI caused due to
TB errors. For rest, it would not touch TB value. Hence to make things
simpler, primary thread would call TB resync explicitly once for each
core immediately after opal hmi handler instead of subtracting guest
offset from TB. TB resync call will restore the TB with host value.
Thus we can be sure about the TB state.
One of the primary threads exiting the guest will take up the
responsibility of calling TB resync. It will use one of the top bits
(bit 63) from subcore state flags bitmap to make the decision. The first
primary thread (among the subcores) that is able to set the bit will
have to call the TB resync. Rest all other threads will wait until TB
resync is complete. Once TB resync is complete all threads will then
proceed.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-05-15 11:14:26 +07:00
|
|
|
#include <asm/hmi.h>
|
2016-08-19 12:35:50 +07:00
|
|
|
#include <asm/pnv-pci.h>
|
2016-11-16 18:25:20 +07:00
|
|
|
#include <asm/mmu.h>
|
KVM: PPC: Book3S HV: Use OPAL XICS emulation on POWER9
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 05:02:08 +07:00
|
|
|
#include <asm/opal.h>
|
|
|
|
#include <asm/xics.h>
|
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
|
|
|
#include <linux/gfp.h>
|
|
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <linux/highmem.h>
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
#include <linux/hugetlb.h>
|
2016-08-19 12:35:50 +07:00
|
|
|
#include <linux/kvm_irqfd.h>
|
|
|
|
#include <linux/irqbypass.h>
|
2013-10-07 23:47:59 +07:00
|
|
|
#include <linux/module.h>
|
2016-08-02 11:03:20 +07:00
|
|
|
#include <linux/compiler.h>
|
KVM: PPC: Book3S HV: Use OPAL XICS emulation on POWER9
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 05:02:08 +07:00
|
|
|
#include <linux/of.h>
|
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
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
#include "book3s.h"
|
|
|
|
|
2014-12-04 07:48:10 +07:00
|
|
|
#define CREATE_TRACE_POINTS
|
|
|
|
#include "trace_hv.h"
|
|
|
|
|
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
|
|
|
/* #define EXIT_DEBUG */
|
|
|
|
/* #define EXIT_DEBUG_SIMPLE */
|
|
|
|
/* #define EXIT_DEBUG_INT */
|
|
|
|
|
2012-10-15 08:16:48 +07:00
|
|
|
/* Used to indicate that a guest page fault needs to be handled */
|
|
|
|
#define RESUME_PAGE_FAULT (RESUME_GUEST | RESUME_FLAG_ARCH1)
|
2016-08-19 12:35:52 +07:00
|
|
|
/* Used to indicate that a guest passthrough interrupt needs to be handled */
|
|
|
|
#define RESUME_PASSTHROUGH (RESUME_GUEST | RESUME_FLAG_ARCH2)
|
2012-10-15 08:16:48 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
/* Used as a "null" value for timebase values */
|
|
|
|
#define TB_NIL (~(u64)0)
|
|
|
|
|
2014-06-02 08:02:59 +07:00
|
|
|
static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
static int dynamic_mt_modes = 6;
|
|
|
|
module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR);
|
|
|
|
MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)");
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
static int target_smt_mode;
|
|
|
|
module_param(target_smt_mode, int, S_IRUGO | S_IWUSR);
|
|
|
|
MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
|
Use the POWER8 Micro Partition Prefetch Engine in KVM HV on POWER8
The POWER8 processor has a Micro Partition Prefetch Engine, which is
a fancy way of saying "has way to store and load contents of L2 or
L2+MRU way of L3 cache". We initiate the storing of the log (list of
addresses) using the logmpp instruction and start restore by writing
to a SPR.
The logmpp instruction takes parameters in a single 64bit register:
- starting address of the table to store log of L2/L2+L3 cache contents
- 32kb for L2
- 128kb for L2+L3
- Aligned relative to maximum size of the table (32kb or 128kb)
- Log control (no-op, L2 only, L2 and L3, abort logout)
We should abort any ongoing logging before initiating one.
To initiate restore, we write to the MPPR SPR. The format of what to write
to the SPR is similar to the logmpp instruction parameter:
- starting address of the table to read from (same alignment requirements)
- table size (no data, until end of table)
- prefetch rate (from fastest possible to slower. about every 8, 16, 24 or
32 cycles)
The idea behind loading and storing the contents of L2/L3 cache is to
reduce memory latency in a system that is frequently swapping vcores on
a physical CPU.
The best case scenario for doing this is when some vcores are doing very
cache heavy workloads. The worst case is when they have about 0 cache hits,
so we just generate needless memory operations.
This implementation just does L2 store/load. In my benchmarks this proves
to be useful.
Benchmark 1:
- 16 core POWER8
- 3x Ubuntu 14.04LTS guests (LE) with 8 VCPUs each
- No split core/SMT
- two guests running sysbench memory test.
sysbench --test=memory --num-threads=8 run
- one guest running apache bench (of default HTML page)
ab -n 490000 -c 400 http://localhost/
This benchmark aims to measure performance of real world application (apache)
where other guests are cache hot with their own workloads. The sysbench memory
benchmark does pointer sized writes to a (small) memory buffer in a loop.
In this benchmark with this patch I can see an improvement both in requests
per second (~5%) and in mean and median response times (again, about 5%).
The spread of minimum and maximum response times were largely unchanged.
benchmark 2:
- Same VM config as benchmark 1
- all three guests running sysbench memory benchmark
This benchmark aims to see if there is a positive or negative affect to this
cache heavy benchmark. Although due to the nature of the benchmark (stores) we
may not see a difference in performance, but rather hopefully an improvement
in consistency of performance (when vcore switched in, don't have to wait
many times for cachelines to be pulled in)
The results of this benchmark are improvements in consistency of performance
rather than performance itself. With this patch, the few outliers in duration
go away and we get more consistent performance in each guest.
benchmark 3:
- same 3 guests and CPU configuration as benchmark 1 and 2.
- two idle guests
- 1 guest running STREAM benchmark
This scenario also saw performance improvement with this patch. On Copy and
Scale workloads from STREAM, I got 5-6% improvement with this patch. For
Add and triad, it was around 10% (or more).
benchmark 4:
- same 3 guests as previous benchmarks
- two guests running sysbench --memory, distinctly different cache heavy
workload
- one guest running STREAM benchmark.
Similar improvements to benchmark 3.
benchmark 5:
- 1 guest, 8 VCPUs, Ubuntu 14.04
- Host configured with split core (SMT8, subcores-per-core=4)
- STREAM benchmark
In this benchmark, we see a 10-20% performance improvement across the board
of STREAM benchmark results with this patch.
Based on preliminary investigation and microbenchmarks
by Prerna Saxena <prerna@linux.vnet.ibm.com>
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-07-18 11:18:43 +07:00
|
|
|
|
2015-12-22 05:33:57 +07:00
|
|
|
#ifdef CONFIG_KVM_XICS
|
|
|
|
static struct kernel_param_ops module_param_ops = {
|
|
|
|
.set = param_set_int,
|
|
|
|
.get = param_get_int,
|
|
|
|
};
|
|
|
|
|
2016-08-19 12:35:54 +07:00
|
|
|
module_param_cb(kvm_irq_bypass, &module_param_ops, &kvm_irq_bypass,
|
|
|
|
S_IRUGO | S_IWUSR);
|
|
|
|
MODULE_PARM_DESC(kvm_irq_bypass, "Bypass passthrough interrupt optimization");
|
|
|
|
|
2015-12-22 05:33:57 +07:00
|
|
|
module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
|
|
|
|
S_IRUGO | S_IWUSR);
|
|
|
|
MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
|
|
|
|
#endif
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
|
2016-08-02 11:03:20 +07:00
|
|
|
static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
|
|
|
|
int *ip)
|
|
|
|
{
|
|
|
|
int i = *ip;
|
|
|
|
struct kvm_vcpu *vcpu;
|
|
|
|
|
|
|
|
while (++i < MAX_SMT_THREADS) {
|
|
|
|
vcpu = READ_ONCE(vc->runnable_threads[i]);
|
|
|
|
if (vcpu) {
|
|
|
|
*ip = i;
|
|
|
|
return vcpu;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Used to traverse the list of runnable threads for a given vcore */
|
|
|
|
#define for_each_runnable_thread(i, vcpu, vc) \
|
|
|
|
for (i = -1; (vcpu = next_runnable_thread(vc, &i)); )
|
|
|
|
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
static bool kvmppc_ipi_thread(int cpu)
|
|
|
|
{
|
2016-11-18 04:47:08 +07:00
|
|
|
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
|
|
|
|
|
|
|
|
/* On POWER9 we can use msgsnd to IPI any cpu */
|
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
|
|
|
|
msg |= get_hard_smp_processor_id(cpu);
|
|
|
|
smp_mb();
|
|
|
|
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
/* On POWER8 for IPIs to threads in the same core, use msgsnd */
|
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
|
|
|
|
preempt_disable();
|
|
|
|
if (cpu_first_thread_sibling(cpu) ==
|
|
|
|
cpu_first_thread_sibling(smp_processor_id())) {
|
|
|
|
msg |= cpu_thread_in_core(cpu);
|
|
|
|
smp_mb();
|
|
|
|
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
|
|
|
|
preempt_enable();
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
preempt_enable();
|
|
|
|
}
|
|
|
|
|
|
|
|
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
|
KVM: PPC: Book3S HV: Use OPAL XICS emulation on POWER9
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 05:02:08 +07:00
|
|
|
if (cpu >= 0 && cpu < nr_cpu_ids) {
|
|
|
|
if (paca[cpu].kvm_hstate.xics_phys) {
|
|
|
|
xics_wake_cpu(cpu);
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
|
2013-04-18 03:30:50 +07:00
|
|
|
{
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
int cpu;
|
2016-02-19 15:46:39 +07:00
|
|
|
struct swait_queue_head *wqp;
|
2013-04-18 03:30:50 +07:00
|
|
|
|
|
|
|
wqp = kvm_arch_vcpu_wq(vcpu);
|
2016-02-19 15:46:39 +07:00
|
|
|
if (swait_active(wqp)) {
|
|
|
|
swake_up(wqp);
|
2013-04-18 03:30:50 +07:00
|
|
|
++vcpu->stat.halt_wakeup;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Don't try to signal cpu -1
If the target vcpu for kvmppc_fast_vcpu_kick_hv() is not running on
any CPU, then we will have vcpu->arch.thread_cpu == -1, and as it
happens, kvmppc_fast_vcpu_kick_hv will call kvmppc_ipi_thread with
-1 as the cpu argument. Although this is not meaningful, in the past,
before commit 1704a81ccebc ("KVM: PPC: Book3S HV: Use msgsnd for IPIs
to other cores on POWER9", 2016-11-18), it was harmless because CPU
-1 is not in the same core as any real CPU thread. On a POWER9,
however, we don't do the "same core" check, so we were trying to
do a msgsnd to thread -1, which is invalid. To avoid this, we add
a check to see that vcpu->arch.thread_cpu is >= 0 before calling
kvmppc_ipi_thread() with it. Since vcpu->arch.thread_vcpu can change
asynchronously, we use READ_ONCE to ensure that the value we check is
the same value that we use as the argument to kvmppc_ipi_thread().
Fixes: 1704a81ccebc ("KVM: PPC: Book3S HV: Use msgsnd for IPIs to other cores on POWER9")
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-12-20 10:02:29 +07:00
|
|
|
cpu = READ_ONCE(vcpu->arch.thread_cpu);
|
|
|
|
if (cpu >= 0 && kvmppc_ipi_thread(cpu))
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
return;
|
2013-04-18 03:30:50 +07:00
|
|
|
|
|
|
|
/* CPU points to the first thread of the core */
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
cpu = vcpu->cpu;
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
|
|
|
|
smp_send_reschedule(cpu);
|
2013-04-18 03:30:50 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
/*
|
|
|
|
* We use the vcpu_load/put functions to measure stolen time.
|
|
|
|
* Stolen time is counted as time when either the vcpu is able to
|
|
|
|
* run as part of a virtual core, but the task running the vcore
|
|
|
|
* is preempted or sleeping, or when the vcpu needs something done
|
|
|
|
* in the kernel by the task running the vcpu, but that task is
|
|
|
|
* preempted or sleeping. Those two things have to be counted
|
|
|
|
* separately, since one of the vcpu tasks will take on the job
|
|
|
|
* of running the core, and the other vcpu tasks in the vcore will
|
|
|
|
* sleep waiting for it to do that, but that sleep shouldn't count
|
|
|
|
* as stolen time.
|
|
|
|
*
|
|
|
|
* Hence we accumulate stolen time when the vcpu can run as part of
|
|
|
|
* a vcore using vc->stolen_tb, and the stolen time when the vcpu
|
|
|
|
* needs its task to do other things in the kernel (for example,
|
|
|
|
* service a page fault) in busy_stolen. We don't accumulate
|
|
|
|
* stolen time for a vcore when it is inactive, or for a vcpu
|
|
|
|
* when it is in state RUNNING or NOTREADY. NOTREADY is a bit of
|
|
|
|
* a misnomer; it means that the vcpu task is not executing in
|
|
|
|
* the KVM_VCPU_RUN ioctl, i.e. it is in userspace or elsewhere in
|
|
|
|
* the kernel. We don't have any way of dividing up that time
|
|
|
|
* between time that the vcpu is genuinely stopped, time that
|
|
|
|
* the task is actively working on behalf of the vcpu, and time
|
|
|
|
* that the task is preempted, so we don't count any of it as
|
|
|
|
* stolen.
|
|
|
|
*
|
|
|
|
* Updates to busy_stolen are protected by arch.tbacct_lock;
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
* updates to vc->stolen_tb are protected by the vcore->stoltb_lock
|
|
|
|
* lock. The stolen times are measured in units of timebase ticks.
|
|
|
|
* (Note that the != TB_NIL checks below are purely defensive;
|
|
|
|
* they should never fail.)
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
*/
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&vc->stoltb_lock, flags);
|
|
|
|
vc->preempt_tb = mftb();
|
|
|
|
spin_unlock_irqrestore(&vc->stoltb_lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&vc->stoltb_lock, flags);
|
|
|
|
if (vc->preempt_tb != TB_NIL) {
|
|
|
|
vc->stolen_tb += mftb() - vc->preempt_tb;
|
|
|
|
vc->preempt_tb = TB_NIL;
|
|
|
|
}
|
|
|
|
spin_unlock_irqrestore(&vc->stoltb_lock, flags);
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
|
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
|
|
|
{
|
2012-02-03 07:56:21 +07:00
|
|
|
struct kvmppc_vcore *vc = vcpu->arch.vcore;
|
2013-11-16 13:46:04 +07:00
|
|
|
unsigned long flags;
|
2012-02-03 07:56:21 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
/*
|
|
|
|
* We can test vc->runner without taking the vcore lock,
|
|
|
|
* because only this task ever sets vc->runner to this
|
|
|
|
* vcpu, and once it is set to this vcpu, only this task
|
|
|
|
* ever sets it to NULL.
|
|
|
|
*/
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
|
|
|
|
kvmppc_core_end_stolen(vc);
|
|
|
|
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST &&
|
|
|
|
vcpu->arch.busy_preempt != TB_NIL) {
|
|
|
|
vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
|
|
|
|
vcpu->arch.busy_preempt = TB_NIL;
|
|
|
|
}
|
2013-11-16 13:46:04 +07:00
|
|
|
spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
|
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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_core_vcpu_put_hv(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
|
|
|
{
|
2012-02-03 07:56:21 +07:00
|
|
|
struct kvmppc_vcore *vc = vcpu->arch.vcore;
|
2013-11-16 13:46:04 +07:00
|
|
|
unsigned long flags;
|
2012-02-03 07:56:21 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
|
|
|
|
kvmppc_core_start_stolen(vc);
|
|
|
|
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
|
|
|
|
vcpu->arch.busy_preempt = mftb();
|
2013-11-16 13:46:04 +07:00
|
|
|
spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
|
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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
|
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
|
|
|
{
|
2015-11-12 12:43:02 +07:00
|
|
|
/*
|
|
|
|
* Check for illegal transactional state bit combination
|
|
|
|
* and if we find it, force the TS field to a safe state.
|
|
|
|
*/
|
|
|
|
if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
|
|
|
|
msr &= ~MSR_TS_MASK;
|
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
|
|
|
vcpu->arch.shregs.msr = msr;
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
kvmppc_end_cede(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
|
|
|
}
|
|
|
|
|
2015-05-22 14:25:02 +07:00
|
|
|
static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
|
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
|
|
|
{
|
|
|
|
vcpu->arch.pvr = pvr;
|
|
|
|
}
|
|
|
|
|
2016-11-14 07:35:08 +07:00
|
|
|
/* Dummy value used in computing PCR value below */
|
|
|
|
#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
|
|
|
|
|
2015-05-22 14:25:02 +07:00
|
|
|
static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
|
2013-09-21 11:35:02 +07:00
|
|
|
{
|
2016-11-14 07:35:08 +07:00
|
|
|
unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
|
2013-09-21 11:35:02 +07:00
|
|
|
struct kvmppc_vcore *vc = vcpu->arch.vcore;
|
|
|
|
|
2016-11-14 07:35:08 +07:00
|
|
|
/* We can (emulate) our own architecture version and anything older */
|
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
host_pcr_bit = PCR_ARCH_300;
|
|
|
|
else if (cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
|
|
host_pcr_bit = PCR_ARCH_207;
|
|
|
|
else if (cpu_has_feature(CPU_FTR_ARCH_206))
|
|
|
|
host_pcr_bit = PCR_ARCH_206;
|
|
|
|
else
|
|
|
|
host_pcr_bit = PCR_ARCH_205;
|
|
|
|
|
|
|
|
/* Determine lowest PCR bit needed to run guest in given PVR level */
|
|
|
|
guest_pcr_bit = host_pcr_bit;
|
2013-09-21 11:35:02 +07:00
|
|
|
if (arch_compat) {
|
|
|
|
switch (arch_compat) {
|
|
|
|
case PVR_ARCH_205:
|
2016-11-14 07:35:08 +07:00
|
|
|
guest_pcr_bit = PCR_ARCH_205;
|
2013-09-21 11:35:02 +07:00
|
|
|
break;
|
|
|
|
case PVR_ARCH_206:
|
|
|
|
case PVR_ARCH_206p:
|
2016-11-14 07:35:08 +07:00
|
|
|
guest_pcr_bit = PCR_ARCH_206;
|
2014-01-08 17:25:24 +07:00
|
|
|
break;
|
|
|
|
case PVR_ARCH_207:
|
2016-11-14 07:35:08 +07:00
|
|
|
guest_pcr_bit = PCR_ARCH_207;
|
|
|
|
break;
|
|
|
|
case PVR_ARCH_300:
|
|
|
|
guest_pcr_bit = PCR_ARCH_300;
|
2013-09-21 11:35:02 +07:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-11-14 07:35:08 +07:00
|
|
|
/* Check requested PCR bits don't exceed our capabilities */
|
|
|
|
if (guest_pcr_bit > host_pcr_bit)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2013-09-21 11:35:02 +07:00
|
|
|
spin_lock(&vc->lock);
|
|
|
|
vc->arch_compat = arch_compat;
|
2016-11-14 07:35:08 +07:00
|
|
|
/* Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit */
|
|
|
|
vc->pcr = host_pcr_bit - guest_pcr_bit;
|
2013-09-21 11:35:02 +07:00
|
|
|
spin_unlock(&vc->lock);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-05-22 14:25:02 +07:00
|
|
|
static void kvmppc_dump_regs(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
|
|
|
{
|
|
|
|
int r;
|
|
|
|
|
|
|
|
pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id);
|
|
|
|
pr_err("pc = %.16lx msr = %.16llx trap = %x\n",
|
|
|
|
vcpu->arch.pc, vcpu->arch.shregs.msr, vcpu->arch.trap);
|
|
|
|
for (r = 0; r < 16; ++r)
|
|
|
|
pr_err("r%2d = %.16lx r%d = %.16lx\n",
|
|
|
|
r, kvmppc_get_gpr(vcpu, r),
|
|
|
|
r+16, kvmppc_get_gpr(vcpu, r+16));
|
|
|
|
pr_err("ctr = %.16lx lr = %.16lx\n",
|
|
|
|
vcpu->arch.ctr, vcpu->arch.lr);
|
|
|
|
pr_err("srr0 = %.16llx srr1 = %.16llx\n",
|
|
|
|
vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1);
|
|
|
|
pr_err("sprg0 = %.16llx sprg1 = %.16llx\n",
|
|
|
|
vcpu->arch.shregs.sprg0, vcpu->arch.shregs.sprg1);
|
|
|
|
pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
|
|
|
|
vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
|
|
|
|
pr_err("cr = %.8x xer = %.16lx dsisr = %.8x\n",
|
|
|
|
vcpu->arch.cr, vcpu->arch.xer, vcpu->arch.shregs.dsisr);
|
|
|
|
pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
|
|
|
|
pr_err("fault dar = %.16lx dsisr = %.8x\n",
|
|
|
|
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
|
|
|
|
pr_err("SLB (%d entries):\n", vcpu->arch.slb_max);
|
|
|
|
for (r = 0; r < vcpu->arch.slb_max; ++r)
|
|
|
|
pr_err(" ESID = %.16llx VSID = %.16llx\n",
|
|
|
|
vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
|
|
|
|
pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
|
2013-09-20 11:52:38 +07:00
|
|
|
vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
|
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
|
|
|
vcpu->arch.last_inst);
|
|
|
|
}
|
|
|
|
|
2015-05-22 14:25:02 +07:00
|
|
|
static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
|
2011-06-29 07:22:05 +07:00
|
|
|
{
|
2015-11-05 15:03:50 +07:00
|
|
|
struct kvm_vcpu *ret;
|
2011-06-29 07:22:05 +07:00
|
|
|
|
|
|
|
mutex_lock(&kvm->lock);
|
2015-11-05 15:03:50 +07:00
|
|
|
ret = kvm_get_vcpu_by_id(kvm, id);
|
2011-06-29 07:22:05 +07:00
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
|
|
|
|
{
|
2013-08-06 23:01:26 +07:00
|
|
|
vpa->__old_status |= LPPACA_OLD_SHARED_PROC;
|
2014-06-11 15:34:19 +07:00
|
|
|
vpa->yield_count = cpu_to_be32(1);
|
2011-06-29 07:22:05 +07:00
|
|
|
}
|
|
|
|
|
2012-09-26 03:33:06 +07:00
|
|
|
static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v,
|
|
|
|
unsigned long addr, unsigned long len)
|
|
|
|
{
|
|
|
|
/* check address is cacheline aligned */
|
|
|
|
if (addr & (L1_CACHE_BYTES - 1))
|
|
|
|
return -EINVAL;
|
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
if (v->next_gpa != addr || v->len != len) {
|
|
|
|
v->next_gpa = addr;
|
|
|
|
v->len = addr ? len : 0;
|
|
|
|
v->update_pending = 1;
|
|
|
|
}
|
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
|
|
|
|
struct reg_vpa {
|
|
|
|
u32 dummy;
|
|
|
|
union {
|
2014-06-11 15:34:19 +07:00
|
|
|
__be16 hword;
|
|
|
|
__be32 word;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
} length;
|
|
|
|
};
|
|
|
|
|
|
|
|
static int vpa_is_registered(struct kvmppc_vpa *vpap)
|
|
|
|
{
|
|
|
|
if (vpap->update_pending)
|
|
|
|
return vpap->next_gpa != 0;
|
|
|
|
return vpap->pinned_addr != NULL;
|
|
|
|
}
|
|
|
|
|
2011-06-29 07:22:05 +07:00
|
|
|
static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
|
|
|
|
unsigned long flags,
|
|
|
|
unsigned long vcpuid, unsigned long vpa)
|
|
|
|
{
|
|
|
|
struct kvm *kvm = vcpu->kvm;
|
2011-12-12 19:28:55 +07:00
|
|
|
unsigned long len, nb;
|
2011-06-29 07:22:05 +07:00
|
|
|
void *va;
|
|
|
|
struct kvm_vcpu *tvcpu;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
int err;
|
|
|
|
int subfunc;
|
|
|
|
struct kvmppc_vpa *vpap;
|
2011-06-29 07:22:05 +07:00
|
|
|
|
|
|
|
tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
|
|
|
|
if (!tvcpu)
|
|
|
|
return H_PARAMETER;
|
|
|
|
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
subfunc = (flags >> H_VPA_FUNC_SHIFT) & H_VPA_FUNC_MASK;
|
|
|
|
if (subfunc == H_VPA_REG_VPA || subfunc == H_VPA_REG_DTL ||
|
|
|
|
subfunc == H_VPA_REG_SLB) {
|
|
|
|
/* Registering new area - address must be cache-line aligned */
|
|
|
|
if ((vpa & (L1_CACHE_BYTES - 1)) || !vpa)
|
2011-06-29 07:22:05 +07:00
|
|
|
return H_PARAMETER;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
|
|
|
|
/* convert logical addr to kernel addr and read length */
|
2011-12-12 19:28:55 +07:00
|
|
|
va = kvmppc_pin_guest_page(kvm, vpa, &nb);
|
|
|
|
if (va == NULL)
|
2011-12-12 19:28:21 +07:00
|
|
|
return H_PARAMETER;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
if (subfunc == H_VPA_REG_VPA)
|
2014-06-11 15:34:19 +07:00
|
|
|
len = be16_to_cpu(((struct reg_vpa *)va)->length.hword);
|
2011-06-29 07:22:05 +07:00
|
|
|
else
|
2014-06-11 15:34:19 +07:00
|
|
|
len = be32_to_cpu(((struct reg_vpa *)va)->length.word);
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
kvmppc_unpin_guest_page(kvm, va, vpa, false);
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
|
|
|
|
/* Check length */
|
|
|
|
if (len > nb || len < sizeof(struct reg_vpa))
|
|
|
|
return H_PARAMETER;
|
|
|
|
} else {
|
|
|
|
vpa = 0;
|
|
|
|
len = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = H_PARAMETER;
|
|
|
|
vpap = NULL;
|
|
|
|
spin_lock(&tvcpu->arch.vpa_update_lock);
|
|
|
|
|
|
|
|
switch (subfunc) {
|
|
|
|
case H_VPA_REG_VPA: /* register VPA */
|
|
|
|
if (len < sizeof(struct lppaca))
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
vpap = &tvcpu->arch.vpa;
|
|
|
|
err = 0;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case H_VPA_REG_DTL: /* register DTL */
|
|
|
|
if (len < sizeof(struct dtl_entry))
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
len -= len % sizeof(struct dtl_entry);
|
|
|
|
|
|
|
|
/* Check that they have previously registered a VPA */
|
|
|
|
err = H_RESOURCE;
|
|
|
|
if (!vpa_is_registered(&tvcpu->arch.vpa))
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
|
|
|
|
vpap = &tvcpu->arch.dtl;
|
|
|
|
err = 0;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case H_VPA_REG_SLB: /* register SLB shadow buffer */
|
|
|
|
/* Check that they have previously registered a VPA */
|
|
|
|
err = H_RESOURCE;
|
|
|
|
if (!vpa_is_registered(&tvcpu->arch.vpa))
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
|
|
|
|
vpap = &tvcpu->arch.slb_shadow;
|
|
|
|
err = 0;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case H_VPA_DEREG_VPA: /* deregister VPA */
|
|
|
|
/* Check they don't still have a DTL or SLB buf registered */
|
|
|
|
err = H_RESOURCE;
|
|
|
|
if (vpa_is_registered(&tvcpu->arch.dtl) ||
|
|
|
|
vpa_is_registered(&tvcpu->arch.slb_shadow))
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
|
|
|
|
vpap = &tvcpu->arch.vpa;
|
|
|
|
err = 0;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case H_VPA_DEREG_DTL: /* deregister DTL */
|
|
|
|
vpap = &tvcpu->arch.dtl;
|
|
|
|
err = 0;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case H_VPA_DEREG_SLB: /* deregister SLB shadow buffer */
|
|
|
|
vpap = &tvcpu->arch.slb_shadow;
|
|
|
|
err = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (vpap) {
|
|
|
|
vpap->next_gpa = vpa;
|
|
|
|
vpap->len = len;
|
|
|
|
vpap->update_pending = 1;
|
2011-06-29 07:22:05 +07:00
|
|
|
}
|
2011-12-12 19:28:55 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
spin_unlock(&tvcpu->arch.vpa_update_lock);
|
|
|
|
|
2011-12-12 19:28:55 +07:00
|
|
|
return err;
|
2011-06-29 07:22:05 +07:00
|
|
|
}
|
|
|
|
|
2012-06-01 17:20:24 +07:00
|
|
|
static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
{
|
2012-06-01 17:20:24 +07:00
|
|
|
struct kvm *kvm = vcpu->kvm;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
void *va;
|
|
|
|
unsigned long nb;
|
2012-06-01 17:20:24 +07:00
|
|
|
unsigned long gpa;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
|
2012-06-01 17:20:24 +07:00
|
|
|
/*
|
|
|
|
* We need to pin the page pointed to by vpap->next_gpa,
|
|
|
|
* but we can't call kvmppc_pin_guest_page under the lock
|
|
|
|
* as it does get_user_pages() and down_read(). So we
|
|
|
|
* have to drop the lock, pin the page, then get the lock
|
|
|
|
* again and check that a new area didn't get registered
|
|
|
|
* in the meantime.
|
|
|
|
*/
|
|
|
|
for (;;) {
|
|
|
|
gpa = vpap->next_gpa;
|
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
va = NULL;
|
|
|
|
nb = 0;
|
|
|
|
if (gpa)
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
va = kvmppc_pin_guest_page(kvm, gpa, &nb);
|
2012-06-01 17:20:24 +07:00
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
if (gpa == vpap->next_gpa)
|
|
|
|
break;
|
|
|
|
/* sigh... unpin that one and try again */
|
|
|
|
if (va)
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
kvmppc_unpin_guest_page(kvm, va, gpa, false);
|
2012-06-01 17:20:24 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
vpap->update_pending = 0;
|
|
|
|
if (va && nb < vpap->len) {
|
|
|
|
/*
|
|
|
|
* If it's now too short, it must be that userspace
|
|
|
|
* has changed the mappings underlying guest memory,
|
|
|
|
* so unregister the region.
|
|
|
|
*/
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
kvmppc_unpin_guest_page(kvm, va, gpa, false);
|
2012-06-01 17:20:24 +07:00
|
|
|
va = NULL;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
}
|
|
|
|
if (vpap->pinned_addr)
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
|
|
|
|
vpap->dirty);
|
|
|
|
vpap->gpa = gpa;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
vpap->pinned_addr = va;
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
vpap->dirty = false;
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
if (va)
|
|
|
|
vpap->pinned_end = va + vpap->len;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
|
|
|
|
{
|
2012-10-15 08:17:17 +07:00
|
|
|
if (!(vcpu->arch.vpa.update_pending ||
|
|
|
|
vcpu->arch.slb_shadow.update_pending ||
|
|
|
|
vcpu->arch.dtl.update_pending))
|
|
|
|
return;
|
|
|
|
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
if (vcpu->arch.vpa.update_pending) {
|
2012-06-01 17:20:24 +07:00
|
|
|
kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
|
2012-09-26 03:33:06 +07:00
|
|
|
if (vcpu->arch.vpa.pinned_addr)
|
|
|
|
init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
}
|
|
|
|
if (vcpu->arch.dtl.update_pending) {
|
2012-06-01 17:20:24 +07:00
|
|
|
kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
|
|
|
|
vcpu->arch.dtl_index = 0;
|
|
|
|
}
|
|
|
|
if (vcpu->arch.slb_shadow.update_pending)
|
2012-06-01 17:20:24 +07:00
|
|
|
kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
/*
|
|
|
|
* Return the accumulated stolen time for the vcore up until `now'.
|
|
|
|
* The caller should hold the vcore lock.
|
|
|
|
*/
|
|
|
|
static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
|
|
|
|
{
|
|
|
|
u64 p;
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
unsigned long flags;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
spin_lock_irqsave(&vc->stoltb_lock, flags);
|
|
|
|
p = vc->stolen_tb;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
if (vc->vcore_state != VCORE_INACTIVE &&
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
vc->preempt_tb != TB_NIL)
|
|
|
|
p += now - vc->preempt_tb;
|
|
|
|
spin_unlock_irqrestore(&vc->stoltb_lock, flags);
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
return p;
|
|
|
|
}
|
|
|
|
|
2012-02-03 07:56:21 +07:00
|
|
|
static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
|
|
|
|
struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
struct dtl_entry *dt;
|
|
|
|
struct lppaca *vpa;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
unsigned long stolen;
|
|
|
|
unsigned long core_stolen;
|
|
|
|
u64 now;
|
2012-02-03 07:56:21 +07:00
|
|
|
|
|
|
|
dt = vcpu->arch.dtl_ptr;
|
|
|
|
vpa = vcpu->arch.vpa.pinned_addr;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
now = mftb();
|
|
|
|
core_stolen = vcore_stolen_time(vc, now);
|
|
|
|
stolen = core_stolen - vcpu->arch.stolen_logged;
|
|
|
|
vcpu->arch.stolen_logged = core_stolen;
|
2013-11-16 13:46:04 +07:00
|
|
|
spin_lock_irq(&vcpu->arch.tbacct_lock);
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
stolen += vcpu->arch.busy_stolen;
|
|
|
|
vcpu->arch.busy_stolen = 0;
|
2013-11-16 13:46:04 +07:00
|
|
|
spin_unlock_irq(&vcpu->arch.tbacct_lock);
|
2012-02-03 07:56:21 +07:00
|
|
|
if (!dt || !vpa)
|
|
|
|
return;
|
|
|
|
memset(dt, 0, sizeof(struct dtl_entry));
|
|
|
|
dt->dispatch_reason = 7;
|
2014-06-11 15:34:19 +07:00
|
|
|
dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid);
|
|
|
|
dt->timebase = cpu_to_be64(now + vc->tb_offset);
|
|
|
|
dt->enqueue_to_dispatch_time = cpu_to_be32(stolen);
|
|
|
|
dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu));
|
|
|
|
dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr);
|
2012-02-03 07:56:21 +07:00
|
|
|
++dt;
|
|
|
|
if (dt == vcpu->arch.dtl.pinned_end)
|
|
|
|
dt = vcpu->arch.dtl.pinned_addr;
|
|
|
|
vcpu->arch.dtl_ptr = dt;
|
|
|
|
/* order writing *dt vs. writing vpa->dtl_idx */
|
|
|
|
smp_wmb();
|
2014-06-11 15:34:19 +07:00
|
|
|
vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index);
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
vcpu->arch.dtl.dirty = true;
|
2012-02-03 07:56:21 +07:00
|
|
|
}
|
|
|
|
|
2014-06-02 08:03:01 +07:00
|
|
|
static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207)
|
|
|
|
return true;
|
|
|
|
if ((!vcpu->arch.vcore->arch_compat) &&
|
|
|
|
cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
|
|
return true;
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
|
|
|
|
unsigned long resource, unsigned long value1,
|
|
|
|
unsigned long value2)
|
|
|
|
{
|
|
|
|
switch (resource) {
|
|
|
|
case H_SET_MODE_RESOURCE_SET_CIABR:
|
|
|
|
if (!kvmppc_power8_compatible(vcpu))
|
|
|
|
return H_P2;
|
|
|
|
if (value2)
|
|
|
|
return H_P4;
|
|
|
|
if (mflags)
|
|
|
|
return H_UNSUPPORTED_FLAG_START;
|
|
|
|
/* Guests can't breakpoint the hypervisor */
|
|
|
|
if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER)
|
|
|
|
return H_P3;
|
|
|
|
vcpu->arch.ciabr = value1;
|
|
|
|
return H_SUCCESS;
|
|
|
|
case H_SET_MODE_RESOURCE_SET_DAWR:
|
|
|
|
if (!kvmppc_power8_compatible(vcpu))
|
|
|
|
return H_P2;
|
|
|
|
if (mflags)
|
|
|
|
return H_UNSUPPORTED_FLAG_START;
|
|
|
|
if (value2 & DABRX_HYP)
|
|
|
|
return H_P4;
|
|
|
|
vcpu->arch.dawr = value1;
|
|
|
|
vcpu->arch.dawrx = value2;
|
|
|
|
return H_SUCCESS;
|
|
|
|
default:
|
|
|
|
return H_TOO_HARD;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-12-03 09:30:40 +07:00
|
|
|
static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
|
|
|
|
{
|
|
|
|
struct kvmppc_vcore *vcore = target->arch.vcore;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We expect to have been called by the real mode handler
|
|
|
|
* (kvmppc_rm_h_confer()) which would have directly returned
|
|
|
|
* H_SUCCESS if the source vcore wasn't idle (e.g. if it may
|
|
|
|
* have useful work to do and should not confer) so we don't
|
|
|
|
* recheck that here.
|
|
|
|
*/
|
|
|
|
|
|
|
|
spin_lock(&vcore->lock);
|
|
|
|
if (target->arch.state == KVMPPC_VCPU_RUNNABLE &&
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
vcore->vcore_state != VCORE_INACTIVE &&
|
|
|
|
vcore->runner)
|
2014-12-03 09:30:40 +07:00
|
|
|
target = vcore->runner;
|
|
|
|
spin_unlock(&vcore->lock);
|
|
|
|
|
|
|
|
return kvm_vcpu_yield_to(target);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
int yield_count = 0;
|
|
|
|
struct lppaca *lppaca;
|
|
|
|
|
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr;
|
|
|
|
if (lppaca)
|
2015-03-20 16:39:39 +07:00
|
|
|
yield_count = be32_to_cpu(lppaca->yield_count);
|
2014-12-03 09:30:40 +07:00
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
return yield_count;
|
|
|
|
}
|
|
|
|
|
2011-06-29 07:22:05 +07:00
|
|
|
int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
unsigned long req = kvmppc_get_gpr(vcpu, 3);
|
|
|
|
unsigned long target, ret = H_SUCCESS;
|
2014-12-03 09:30:40 +07:00
|
|
|
int yield_count;
|
2011-06-29 07:22:05 +07:00
|
|
|
struct kvm_vcpu *tvcpu;
|
2013-04-18 03:30:00 +07:00
|
|
|
int idx, rc;
|
2011-06-29 07:22:05 +07:00
|
|
|
|
2014-06-02 08:02:59 +07:00
|
|
|
if (req <= MAX_HCALL_OPCODE &&
|
|
|
|
!test_bit(req/4, vcpu->kvm->arch.enabled_hcalls))
|
|
|
|
return RESUME_HOST;
|
|
|
|
|
2011-06-29 07:22:05 +07:00
|
|
|
switch (req) {
|
|
|
|
case H_CEDE:
|
|
|
|
break;
|
|
|
|
case H_PROD:
|
|
|
|
target = kvmppc_get_gpr(vcpu, 4);
|
|
|
|
tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
|
|
|
|
if (!tvcpu) {
|
|
|
|
ret = H_PARAMETER;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
tvcpu->arch.prodded = 1;
|
|
|
|
smp_mb();
|
2016-12-06 16:42:05 +07:00
|
|
|
if (tvcpu->arch.ceded)
|
|
|
|
kvmppc_fast_vcpu_kick_hv(tvcpu);
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
|
|
|
case H_CONFER:
|
2013-09-06 10:23:21 +07:00
|
|
|
target = kvmppc_get_gpr(vcpu, 4);
|
|
|
|
if (target == -1)
|
|
|
|
break;
|
|
|
|
tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
|
|
|
|
if (!tvcpu) {
|
|
|
|
ret = H_PARAMETER;
|
|
|
|
break;
|
|
|
|
}
|
2014-12-03 09:30:40 +07:00
|
|
|
yield_count = kvmppc_get_gpr(vcpu, 5);
|
|
|
|
if (kvmppc_get_yield_count(tvcpu) != yield_count)
|
|
|
|
break;
|
|
|
|
kvm_arch_vcpu_yield_to(tvcpu);
|
2011-06-29 07:22:05 +07:00
|
|
|
break;
|
|
|
|
case H_REGISTER_VPA:
|
|
|
|
ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
|
|
|
|
kvmppc_get_gpr(vcpu, 5),
|
|
|
|
kvmppc_get_gpr(vcpu, 6));
|
|
|
|
break;
|
2013-04-18 03:30:00 +07:00
|
|
|
case H_RTAS:
|
|
|
|
if (list_empty(&vcpu->kvm->arch.rtas_tokens))
|
|
|
|
return RESUME_HOST;
|
|
|
|
|
2013-11-16 13:46:05 +07:00
|
|
|
idx = srcu_read_lock(&vcpu->kvm->srcu);
|
2013-04-18 03:30:00 +07:00
|
|
|
rc = kvmppc_rtas_hcall(vcpu);
|
2013-11-16 13:46:05 +07:00
|
|
|
srcu_read_unlock(&vcpu->kvm->srcu, idx);
|
2013-04-18 03:30:00 +07:00
|
|
|
|
|
|
|
if (rc == -ENOENT)
|
|
|
|
return RESUME_HOST;
|
|
|
|
else if (rc == 0)
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* Send the error out to userspace via KVM_RUN */
|
|
|
|
return rc;
|
kvmppc: Implement H_LOGICAL_CI_{LOAD,STORE} in KVM
On POWER, storage caching is usually configured via the MMU - attributes
such as cache-inhibited are stored in the TLB and the hashed page table.
This makes correctly performing cache inhibited IO accesses awkward when
the MMU is turned off (real mode). Some CPU models provide special
registers to control the cache attributes of real mode load and stores but
this is not at all consistent. This is a problem in particular for SLOF,
the firmware used on KVM guests, which runs entirely in real mode, but
which needs to do IO to load the kernel.
To simplify this qemu implements two special hypercalls, H_LOGICAL_CI_LOAD
and H_LOGICAL_CI_STORE which simulate a cache-inhibited load or store to
a logical address (aka guest physical address). SLOF uses these for IO.
However, because these are implemented within qemu, not the host kernel,
these bypass any IO devices emulated within KVM itself. The simplest way
to see this problem is to attempt to boot a KVM guest from a virtio-blk
device with iothread / dataplane enabled. The iothread code relies on an
in kernel implementation of the virtio queue notification, which is not
triggered by the IO hcalls, and so the guest will stall in SLOF unable to
load the guest OS.
This patch addresses this by providing in-kernel implementations of the
2 hypercalls, which correctly scan the KVM IO bus. Any access to an
address not handled by the KVM IO bus will cause a VM exit, hitting the
qemu implementation as before.
Note that a userspace change is also required, in order to enable these
new hcall implementations with KVM_CAP_PPC_ENABLE_HCALL.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
[agraf: fix compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-02-05 07:53:25 +07:00
|
|
|
case H_LOGICAL_CI_LOAD:
|
|
|
|
ret = kvmppc_h_logical_ci_load(vcpu);
|
|
|
|
if (ret == H_TOO_HARD)
|
|
|
|
return RESUME_HOST;
|
|
|
|
break;
|
|
|
|
case H_LOGICAL_CI_STORE:
|
|
|
|
ret = kvmppc_h_logical_ci_store(vcpu);
|
|
|
|
if (ret == H_TOO_HARD)
|
|
|
|
return RESUME_HOST;
|
|
|
|
break;
|
2014-06-02 08:03:01 +07:00
|
|
|
case H_SET_MODE:
|
|
|
|
ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4),
|
|
|
|
kvmppc_get_gpr(vcpu, 5),
|
|
|
|
kvmppc_get_gpr(vcpu, 6),
|
|
|
|
kvmppc_get_gpr(vcpu, 7));
|
|
|
|
if (ret == H_TOO_HARD)
|
|
|
|
return RESUME_HOST;
|
|
|
|
break;
|
2013-04-18 03:30:26 +07:00
|
|
|
case H_XIRR:
|
|
|
|
case H_CPPR:
|
|
|
|
case H_EOI:
|
|
|
|
case H_IPI:
|
2013-05-23 22:42:21 +07:00
|
|
|
case H_IPOLL:
|
|
|
|
case H_XIRR_X:
|
2013-04-18 03:30:26 +07:00
|
|
|
if (kvmppc_xics_enabled(vcpu)) {
|
|
|
|
ret = kvmppc_xics_hcall(vcpu, req);
|
|
|
|
break;
|
2016-02-15 08:55:09 +07:00
|
|
|
}
|
|
|
|
return RESUME_HOST;
|
|
|
|
case H_PUT_TCE:
|
|
|
|
ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
|
|
|
|
kvmppc_get_gpr(vcpu, 5),
|
|
|
|
kvmppc_get_gpr(vcpu, 6));
|
|
|
|
if (ret == H_TOO_HARD)
|
|
|
|
return RESUME_HOST;
|
|
|
|
break;
|
|
|
|
case H_PUT_TCE_INDIRECT:
|
|
|
|
ret = kvmppc_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
|
|
|
|
kvmppc_get_gpr(vcpu, 5),
|
|
|
|
kvmppc_get_gpr(vcpu, 6),
|
|
|
|
kvmppc_get_gpr(vcpu, 7));
|
|
|
|
if (ret == H_TOO_HARD)
|
|
|
|
return RESUME_HOST;
|
|
|
|
break;
|
|
|
|
case H_STUFF_TCE:
|
|
|
|
ret = kvmppc_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
|
|
|
|
kvmppc_get_gpr(vcpu, 5),
|
|
|
|
kvmppc_get_gpr(vcpu, 6),
|
|
|
|
kvmppc_get_gpr(vcpu, 7));
|
|
|
|
if (ret == H_TOO_HARD)
|
|
|
|
return RESUME_HOST;
|
|
|
|
break;
|
2011-06-29 07:22:05 +07:00
|
|
|
default:
|
|
|
|
return RESUME_HOST;
|
|
|
|
}
|
|
|
|
kvmppc_set_gpr(vcpu, 3, ret);
|
|
|
|
vcpu->arch.hcall_needed = 0;
|
|
|
|
return RESUME_GUEST;
|
|
|
|
}
|
|
|
|
|
2014-06-02 08:03:00 +07:00
|
|
|
static int kvmppc_hcall_impl_hv(unsigned long cmd)
|
|
|
|
{
|
|
|
|
switch (cmd) {
|
|
|
|
case H_CEDE:
|
|
|
|
case H_PROD:
|
|
|
|
case H_CONFER:
|
|
|
|
case H_REGISTER_VPA:
|
2014-06-02 08:03:01 +07:00
|
|
|
case H_SET_MODE:
|
kvmppc: Implement H_LOGICAL_CI_{LOAD,STORE} in KVM
On POWER, storage caching is usually configured via the MMU - attributes
such as cache-inhibited are stored in the TLB and the hashed page table.
This makes correctly performing cache inhibited IO accesses awkward when
the MMU is turned off (real mode). Some CPU models provide special
registers to control the cache attributes of real mode load and stores but
this is not at all consistent. This is a problem in particular for SLOF,
the firmware used on KVM guests, which runs entirely in real mode, but
which needs to do IO to load the kernel.
To simplify this qemu implements two special hypercalls, H_LOGICAL_CI_LOAD
and H_LOGICAL_CI_STORE which simulate a cache-inhibited load or store to
a logical address (aka guest physical address). SLOF uses these for IO.
However, because these are implemented within qemu, not the host kernel,
these bypass any IO devices emulated within KVM itself. The simplest way
to see this problem is to attempt to boot a KVM guest from a virtio-blk
device with iothread / dataplane enabled. The iothread code relies on an
in kernel implementation of the virtio queue notification, which is not
triggered by the IO hcalls, and so the guest will stall in SLOF unable to
load the guest OS.
This patch addresses this by providing in-kernel implementations of the
2 hypercalls, which correctly scan the KVM IO bus. Any access to an
address not handled by the KVM IO bus will cause a VM exit, hitting the
qemu implementation as before.
Note that a userspace change is also required, in order to enable these
new hcall implementations with KVM_CAP_PPC_ENABLE_HCALL.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
[agraf: fix compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-02-05 07:53:25 +07:00
|
|
|
case H_LOGICAL_CI_LOAD:
|
|
|
|
case H_LOGICAL_CI_STORE:
|
2014-06-02 08:03:00 +07:00
|
|
|
#ifdef CONFIG_KVM_XICS
|
|
|
|
case H_XIRR:
|
|
|
|
case H_CPPR:
|
|
|
|
case H_EOI:
|
|
|
|
case H_IPI:
|
|
|
|
case H_IPOLL:
|
|
|
|
case H_XIRR_X:
|
|
|
|
#endif
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* See if it's in the real-mode table */
|
|
|
|
return kvmppc_hcall_impl_hv_realmode(cmd);
|
|
|
|
}
|
|
|
|
|
2014-09-10 00:07:35 +07:00
|
|
|
static int kvmppc_emulate_debug_inst(struct kvm_run *run,
|
|
|
|
struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
u32 last_inst;
|
|
|
|
|
|
|
|
if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
|
|
|
|
EMULATE_DONE) {
|
|
|
|
/*
|
|
|
|
* Fetch failed, so return to guest and
|
|
|
|
* try executing it again.
|
|
|
|
*/
|
|
|
|
return RESUME_GUEST;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (last_inst == KVMPPC_INST_SW_BREAKPOINT) {
|
|
|
|
run->exit_reason = KVM_EXIT_DEBUG;
|
|
|
|
run->debug.arch.address = kvmppc_get_pc(vcpu);
|
|
|
|
return RESUME_HOST;
|
|
|
|
} else {
|
|
|
|
kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
|
|
|
|
return RESUME_GUEST;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
|
|
|
|
struct task_struct *tsk)
|
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
|
|
|
{
|
|
|
|
int r = RESUME_HOST;
|
|
|
|
|
|
|
|
vcpu->stat.sum_exits++;
|
|
|
|
|
2015-11-12 12:43:48 +07:00
|
|
|
/*
|
|
|
|
* This can happen if an interrupt occurs in the last stages
|
|
|
|
* of guest entry or the first stages of guest exit (i.e. after
|
|
|
|
* setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
|
|
|
|
* and before setting it to KVM_GUEST_MODE_HOST_HV).
|
|
|
|
* That can happen due to a bug, or due to a machine check
|
|
|
|
* occurring at just the wrong time.
|
|
|
|
*/
|
|
|
|
if (vcpu->arch.shregs.msr & MSR_HV) {
|
|
|
|
printk(KERN_EMERG "KVM trap in HV mode!\n");
|
|
|
|
printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
|
|
|
|
vcpu->arch.trap, kvmppc_get_pc(vcpu),
|
|
|
|
vcpu->arch.shregs.msr);
|
|
|
|
kvmppc_dump_regs(vcpu);
|
|
|
|
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
|
|
|
|
run->hw.hardware_exit_reason = vcpu->arch.trap;
|
|
|
|
return RESUME_HOST;
|
|
|
|
}
|
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
|
|
|
run->exit_reason = KVM_EXIT_UNKNOWN;
|
|
|
|
run->ready_for_interrupt_injection = 1;
|
|
|
|
switch (vcpu->arch.trap) {
|
|
|
|
/* We're good on these - the host merely wanted to get our attention */
|
|
|
|
case BOOK3S_INTERRUPT_HV_DECREMENTER:
|
|
|
|
vcpu->stat.dec_exits++;
|
|
|
|
r = RESUME_GUEST;
|
|
|
|
break;
|
|
|
|
case BOOK3S_INTERRUPT_EXTERNAL:
|
2014-01-08 17:25:28 +07:00
|
|
|
case BOOK3S_INTERRUPT_H_DOORBELL:
|
2016-11-22 10:30:14 +07:00
|
|
|
case BOOK3S_INTERRUPT_H_VIRT:
|
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
|
|
|
vcpu->stat.ext_intr_exits++;
|
|
|
|
r = RESUME_GUEST;
|
|
|
|
break;
|
2014-11-03 11:51:57 +07:00
|
|
|
/* HMI is hypervisor interrupt and host has handled it. Resume guest.*/
|
|
|
|
case BOOK3S_INTERRUPT_HMI:
|
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
|
|
|
case BOOK3S_INTERRUPT_PERFMON:
|
|
|
|
r = RESUME_GUEST;
|
|
|
|
break;
|
KVM: PPC: Book3S HV: Handle guest-caused machine checks on POWER7 without panicking
Currently, if a machine check interrupt happens while we are in the
guest, we exit the guest and call the host's machine check handler,
which tends to cause the host to panic. Some machine checks can be
triggered by the guest; for example, if the guest creates two entries
in the SLB that map the same effective address, and then accesses that
effective address, the CPU will take a machine check interrupt.
To handle this better, when a machine check happens inside the guest,
we call a new function, kvmppc_realmode_machine_check(), while still in
real mode before exiting the guest. On POWER7, it handles the cases
that the guest can trigger, either by flushing and reloading the SLB,
or by flushing the TLB, and then it delivers the machine check interrupt
directly to the guest without going back to the host. On POWER7, the
OPAL firmware patches the machine check interrupt vector so that it
gets control first, and it leaves behind its analysis of the situation
in a structure pointed to by the opal_mc_evt field of the paca. The
kvmppc_realmode_machine_check() function looks at this, and if OPAL
reports that there was no error, or that it has handled the error, we
also go straight back to the guest with a machine check. We have to
deliver a machine check to the guest since the machine check interrupt
might have trashed valid values in SRR0/1.
If the machine check is one we can't handle in real mode, and one that
OPAL hasn't already handled, or on PPC970, we exit the guest and call
the host's machine check handler. We do this by jumping to the
machine_check_fwnmi label, rather than absolute address 0x200, because
we don't want to re-execute OPAL's handler on POWER7. On PPC970, the
two are equivalent because address 0x200 just contains a branch.
Then, if the host machine check handler decides that the system can
continue executing, kvmppc_handle_exit() delivers a machine check
interrupt to the guest -- once again to let the guest know that SRR0/1
have been modified.
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix checkpatch warnings]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-24 05:37:50 +07:00
|
|
|
case BOOK3S_INTERRUPT_MACHINE_CHECK:
|
|
|
|
/*
|
|
|
|
* Deliver a machine check interrupt to the guest.
|
|
|
|
* We have to do this, even if the host has handled the
|
|
|
|
* machine check, because machine checks use SRR0/1 and
|
|
|
|
* the interrupt might have trashed guest state in them.
|
|
|
|
*/
|
|
|
|
kvmppc_book3s_queue_irqprio(vcpu,
|
|
|
|
BOOK3S_INTERRUPT_MACHINE_CHECK);
|
|
|
|
r = RESUME_GUEST;
|
|
|
|
break;
|
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
|
|
|
case BOOK3S_INTERRUPT_PROGRAM:
|
|
|
|
{
|
|
|
|
ulong flags;
|
|
|
|
/*
|
|
|
|
* Normally program interrupts are delivered directly
|
|
|
|
* to the guest by the hardware, but we can get here
|
|
|
|
* as a result of a hypervisor emulation interrupt
|
|
|
|
* (e40) getting turned into a 700 by BML RTAS.
|
|
|
|
*/
|
|
|
|
flags = vcpu->arch.shregs.msr & 0x1f0000ull;
|
|
|
|
kvmppc_core_queue_program(vcpu, flags);
|
|
|
|
r = RESUME_GUEST;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case BOOK3S_INTERRUPT_SYSCALL:
|
|
|
|
{
|
|
|
|
/* hcall - punt to userspace */
|
|
|
|
int i;
|
|
|
|
|
2013-11-19 13:12:48 +07:00
|
|
|
/* hypercall with MSR_PR has already been handled in rmode,
|
|
|
|
* and never reaches here.
|
|
|
|
*/
|
|
|
|
|
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
|
|
|
run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
|
|
|
|
for (i = 0; i < 9; ++i)
|
|
|
|
run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
|
|
|
|
run->exit_reason = KVM_EXIT_PAPR_HCALL;
|
|
|
|
vcpu->arch.hcall_needed = 1;
|
|
|
|
r = RESUME_HOST;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/*
|
KVM: PPC: Implement MMU notifiers for Book3S HV guests
This adds the infrastructure to enable us to page out pages underneath
a Book3S HV guest, on processors that support virtualized partition
memory, that is, POWER7. Instead of pinning all the guest's pages,
we now look in the host userspace Linux page tables to find the
mapping for a given guest page. Then, if the userspace Linux PTE
gets invalidated, kvm_unmap_hva() gets called for that address, and
we replace all the guest HPTEs that refer to that page with absent
HPTEs, i.e. ones with the valid bit clear and the HPTE_V_ABSENT bit
set, which will cause an HDSI when the guest tries to access them.
Finally, the page fault handler is extended to reinstantiate the
guest HPTE when the guest tries to access a page which has been paged
out.
Since we can't intercept the guest DSI and ISI interrupts on PPC970,
we still have to pin all the guest pages on PPC970. We have a new flag,
kvm->arch.using_mmu_notifiers, that indicates whether we can page
guest pages out. If it is not set, the MMU notifier callbacks do
nothing and everything operates as before.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:38:05 +07:00
|
|
|
* We get these next two if the guest accesses a page which it thinks
|
|
|
|
* it has mapped but which is not actually present, either because
|
|
|
|
* it is for an emulated I/O device or because the corresonding
|
|
|
|
* host page has been paged out. Any other HDSI/HISI interrupts
|
|
|
|
* have been handled already.
|
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
|
|
|
*/
|
|
|
|
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
|
2012-10-15 08:16:48 +07:00
|
|
|
r = RESUME_PAGE_FAULT;
|
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
|
|
|
break;
|
|
|
|
case BOOK3S_INTERRUPT_H_INST_STORAGE:
|
2012-10-15 08:16:48 +07:00
|
|
|
vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
|
|
|
|
vcpu->arch.fault_dsisr = 0;
|
|
|
|
r = RESUME_PAGE_FAULT;
|
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
|
|
|
break;
|
|
|
|
/*
|
|
|
|
* This occurs if the guest executes an illegal instruction.
|
2014-09-10 00:07:35 +07:00
|
|
|
* If the guest debug is disabled, generate a program interrupt
|
|
|
|
* to the guest. If guest debug is enabled, we need to check
|
|
|
|
* whether the instruction is a software breakpoint instruction.
|
|
|
|
* Accordingly return to Guest or Host.
|
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
|
|
|
*/
|
|
|
|
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
|
KVM: PPC: Book3S HV: Fix endianness of instruction obtained from HEIR register
There are two ways in which a guest instruction can be obtained from
the guest in the guest exit code in book3s_hv_rmhandlers.S. If the
exit was caused by a Hypervisor Emulation interrupt (i.e. an illegal
instruction), the offending instruction is in the HEIR register
(Hypervisor Emulation Instruction Register). If the exit was caused
by a load or store to an emulated MMIO device, we load the instruction
from the guest by turning data relocation on and loading the instruction
with an lwz instruction.
Unfortunately, in the case where the guest has opposite endianness to
the host, these two methods give results of different endianness, but
both get put into vcpu->arch.last_inst. The HEIR value has been loaded
using guest endianness, whereas the lwz will load the instruction using
host endianness. The rest of the code that uses vcpu->arch.last_inst
assumes it was loaded using host endianness.
To fix this, we define a new vcpu field to store the HEIR value. Then,
in kvmppc_handle_exit_hv(), we transfer the value from this new field to
vcpu->arch.last_inst, doing a byte-swap if the guest and host endianness
differ.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-03 09:30:39 +07:00
|
|
|
if (vcpu->arch.emul_inst != KVM_INST_FETCH_FAILED)
|
|
|
|
vcpu->arch.last_inst = kvmppc_need_byteswap(vcpu) ?
|
|
|
|
swab32(vcpu->arch.emul_inst) :
|
|
|
|
vcpu->arch.emul_inst;
|
2014-09-10 00:07:35 +07:00
|
|
|
if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
|
|
|
|
r = kvmppc_emulate_debug_inst(run, vcpu);
|
|
|
|
} else {
|
|
|
|
kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
|
|
|
|
r = RESUME_GUEST;
|
|
|
|
}
|
2014-01-08 17:25:23 +07:00
|
|
|
break;
|
|
|
|
/*
|
|
|
|
* This occurs if the guest (kernel or userspace), does something that
|
|
|
|
* is prohibited by HFSCR. We just generate a program interrupt to
|
|
|
|
* the guest.
|
|
|
|
*/
|
|
|
|
case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
|
|
|
|
kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
|
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
|
|
|
r = RESUME_GUEST;
|
|
|
|
break;
|
2016-08-19 12:35:52 +07:00
|
|
|
case BOOK3S_INTERRUPT_HV_RM_HARD:
|
|
|
|
r = RESUME_PASSTHROUGH;
|
|
|
|
break;
|
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
|
|
|
default:
|
|
|
|
kvmppc_dump_regs(vcpu);
|
|
|
|
printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
|
|
|
|
vcpu->arch.trap, kvmppc_get_pc(vcpu),
|
|
|
|
vcpu->arch.shregs.msr);
|
2013-09-20 11:52:41 +07:00
|
|
|
run->hw.hardware_exit_reason = vcpu->arch.trap;
|
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
|
|
|
r = RESUME_HOST;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
|
|
|
|
struct kvm_sregs *sregs)
|
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
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
memset(sregs, 0, sizeof(struct kvm_sregs));
|
2013-08-22 18:38:39 +07:00
|
|
|
sregs->pvr = vcpu->arch.pvr;
|
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
|
|
|
for (i = 0; i < vcpu->arch.slb_max; i++) {
|
|
|
|
sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
|
|
|
|
sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
|
|
|
|
struct kvm_sregs *sregs)
|
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
|
|
|
{
|
|
|
|
int i, j;
|
|
|
|
|
2014-09-02 13:14:43 +07:00
|
|
|
/* Only accept the same PVR as the host's, since we can't spoof it */
|
|
|
|
if (sregs->pvr != vcpu->arch.pvr)
|
|
|
|
return -EINVAL;
|
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
|
|
|
|
|
|
|
j = 0;
|
|
|
|
for (i = 0; i < vcpu->arch.slb_nr; i++) {
|
|
|
|
if (sregs->u.s.ppc64.slb[i].slbe & SLB_ESID_V) {
|
|
|
|
vcpu->arch.slb[j].orige = sregs->u.s.ppc64.slb[i].slbe;
|
|
|
|
vcpu->arch.slb[j].origv = sregs->u.s.ppc64.slb[i].slbv;
|
|
|
|
++j;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
vcpu->arch.slb_max = j;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-07-19 14:59:34 +07:00
|
|
|
static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
|
|
|
|
bool preserve_top32)
|
2013-09-20 11:52:38 +07:00
|
|
|
{
|
2015-03-20 16:39:38 +07:00
|
|
|
struct kvm *kvm = vcpu->kvm;
|
2013-09-20 11:52:38 +07:00
|
|
|
struct kvmppc_vcore *vc = vcpu->arch.vcore;
|
|
|
|
u64 mask;
|
|
|
|
|
2015-03-20 16:39:38 +07:00
|
|
|
mutex_lock(&kvm->lock);
|
2013-09-20 11:52:38 +07:00
|
|
|
spin_lock(&vc->lock);
|
2014-01-08 17:25:30 +07:00
|
|
|
/*
|
|
|
|
* If ILE (interrupt little-endian) has changed, update the
|
|
|
|
* MSR_LE bit in the intr_msr for each vcpu in this vcore.
|
|
|
|
*/
|
|
|
|
if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
|
|
|
|
struct kvm_vcpu *vcpu;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
kvm_for_each_vcpu(i, vcpu, kvm) {
|
|
|
|
if (vcpu->arch.vcore != vc)
|
|
|
|
continue;
|
|
|
|
if (new_lpcr & LPCR_ILE)
|
|
|
|
vcpu->arch.intr_msr |= MSR_LE;
|
|
|
|
else
|
|
|
|
vcpu->arch.intr_msr &= ~MSR_LE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-09-20 11:52:38 +07:00
|
|
|
/*
|
|
|
|
* Userspace can only modify DPFD (default prefetch depth),
|
|
|
|
* ILE (interrupt little-endian) and TC (translation control).
|
2017-01-30 17:21:53 +07:00
|
|
|
* On POWER8 and POWER9 userspace can also modify AIL (alt. interrupt loc.).
|
2013-09-20 11:52:38 +07:00
|
|
|
*/
|
|
|
|
mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
|
2014-01-08 17:25:27 +07:00
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
|
|
mask |= LPCR_AIL;
|
2014-07-19 14:59:34 +07:00
|
|
|
|
|
|
|
/* Broken 32-bit version of LPCR must not clear top bits */
|
|
|
|
if (preserve_top32)
|
|
|
|
mask &= 0xFFFFFFFF;
|
2013-09-20 11:52:38 +07:00
|
|
|
vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
|
|
|
|
spin_unlock(&vc->lock);
|
2015-03-20 16:39:38 +07:00
|
|
|
mutex_unlock(&kvm->lock);
|
2013-09-20 11:52:38 +07:00
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
|
|
|
|
union kvmppc_one_reg *val)
|
2011-12-12 19:26:50 +07:00
|
|
|
{
|
2012-09-26 03:31:56 +07:00
|
|
|
int r = 0;
|
|
|
|
long int i;
|
2011-12-12 19:26:50 +07:00
|
|
|
|
2012-09-26 03:31:56 +07:00
|
|
|
switch (id) {
|
2014-09-10 00:07:35 +07:00
|
|
|
case KVM_REG_PPC_DEBUG_INST:
|
|
|
|
*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
|
|
|
|
break;
|
2011-12-12 19:26:50 +07:00
|
|
|
case KVM_REG_PPC_HIOR:
|
2012-09-26 03:31:56 +07:00
|
|
|
*val = get_reg_val(id, 0);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_DABR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.dabr);
|
|
|
|
break;
|
KVM: PPC: Book3S HV: Add support for DABRX register on POWER7
The DABRX (DABR extension) register on POWER7 processors provides finer
control over which accesses cause a data breakpoint interrupt. It
contains 3 bits which indicate whether to enable accesses in user,
kernel and hypervisor modes respectively to cause data breakpoint
interrupts, plus one bit that enables both real mode and virtual mode
accesses to cause interrupts. Currently, KVM sets DABRX to allow
both kernel and user accesses to cause interrupts while in the guest.
This adds support for the guest to specify other values for DABRX.
PAPR defines a H_SET_XDABR hcall to allow the guest to set both DABR
and DABRX with one call. This adds a real-mode implementation of
H_SET_XDABR, which shares most of its code with the existing H_SET_DABR
implementation. To support this, we add a per-vcpu field to store the
DABRX value plus code to get and set it via the ONE_REG interface.
For Linux guests to use this new hcall, userspace needs to add
"hcall-xdabr" to the set of strings in the /chosen/hypertas-functions
property in the device tree. If userspace does this and then migrates
the guest to a host where the kernel doesn't include this patch, then
userspace will need to implement H_SET_XDABR by writing the specified
DABR value to the DABR using the ONE_REG interface. In that case, the
old kernel will set DABRX to DABRX_USER | DABRX_KERNEL. That should
still work correctly, at least for Linux guests, since Linux guests
cope with getting data breakpoint interrupts in modes that weren't
requested by just ignoring the interrupt, and Linux guests never set
DABRX_BTI.
The other thing this does is to make H_SET_DABR and H_SET_XDABR work
on POWER8, which has the DAWR and DAWRX instead of DABR/X. Guests that
know about POWER8 should use H_SET_MODE rather than H_SET_[X]DABR, but
guests running in POWER7 compatibility mode will still use H_SET_[X]DABR.
For them, this adds the logic to convert DABR/X values into DAWR/X values
on POWER8.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:29 +07:00
|
|
|
case KVM_REG_PPC_DABRX:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.dabrx);
|
|
|
|
break;
|
2012-09-26 03:31:56 +07:00
|
|
|
case KVM_REG_PPC_DSCR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.dscr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PURR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.purr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_SPURR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.spurr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_AMR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.amr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_UAMOR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.uamor);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
|
2012-09-26 03:31:56 +07:00
|
|
|
i = id - KVM_REG_PPC_MMCR0;
|
|
|
|
*val = get_reg_val(id, vcpu->arch.mmcr[i]);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
|
|
|
|
i = id - KVM_REG_PPC_PMC1;
|
|
|
|
*val = get_reg_val(id, vcpu->arch.pmc[i]);
|
2011-12-12 19:26:50 +07:00
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
|
|
|
|
i = id - KVM_REG_PPC_SPMC1;
|
|
|
|
*val = get_reg_val(id, vcpu->arch.spmc[i]);
|
|
|
|
break;
|
2013-09-06 10:11:18 +07:00
|
|
|
case KVM_REG_PPC_SIAR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.siar);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_SDAR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.sdar);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_SIER:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.sier);
|
2012-09-26 03:32:30 +07:00
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_IAMR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.iamr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PSPB:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.pspb);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_DPDES:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
|
|
|
|
break;
|
2016-09-15 10:42:52 +07:00
|
|
|
case KVM_REG_PPC_VTB:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vcore->vtb);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_DAWR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.dawr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_DAWRX:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.dawrx);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_CIABR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.ciabr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_CSIGR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.csigr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TACR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.tacr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TCSCR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.tcscr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PID:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.pid);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_ACOP:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.acop);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_WORT:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.wort);
|
2012-09-26 03:32:30 +07:00
|
|
|
break;
|
2016-11-18 09:11:42 +07:00
|
|
|
case KVM_REG_PPC_TIDR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.tid);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PSSCR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.psscr);
|
|
|
|
break;
|
2012-09-26 03:33:06 +07:00
|
|
|
case KVM_REG_PPC_VPA_ADDR:
|
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
|
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_VPA_SLB:
|
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
val->vpaval.addr = vcpu->arch.slb_shadow.next_gpa;
|
|
|
|
val->vpaval.length = vcpu->arch.slb_shadow.len;
|
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_VPA_DTL:
|
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
val->vpaval.addr = vcpu->arch.dtl.next_gpa;
|
|
|
|
val->vpaval.length = vcpu->arch.dtl.len;
|
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
break;
|
KVM: PPC: Book3S HV: Implement timebase offset for guests
This allows guests to have a different timebase origin from the host.
This is needed for migration, where a guest can migrate from one host
to another and the two hosts might have a different timebase origin.
However, the timebase seen by the guest must not go backwards, and
should go forwards only by a small amount corresponding to the time
taken for the migration.
Therefore this provides a new per-vcpu value accessed via the one_reg
interface using the new KVM_REG_PPC_TB_OFFSET identifier. This value
defaults to 0 and is not modified by KVM. On entering the guest, this
value is added onto the timebase, and on exiting the guest, it is
subtracted from the timebase.
This is only supported for recent POWER hardware which has the TBU40
(timebase upper 40 bits) register. Writing to the TBU40 register only
alters the upper 40 bits of the timebase, leaving the lower 24 bits
unchanged. This provides a way to modify the timebase for guest
migration without disturbing the synchronization of the timebase
registers across CPU cores. The kernel rounds up the value given
to a multiple of 2^24.
Timebase values stored in KVM structures (struct kvm_vcpu, struct
kvmppc_vcore, etc.) are stored as host timebase values. The timebase
values in the dispatch trace log need to be guest timebase values,
however, since that is read directly by the guest. This moves the
setting of vcpu->arch.dec_expires on guest exit to a point after we
have restored the host timebase so that vcpu->arch.dec_expires is a
host timebase value.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-06 10:17:46 +07:00
|
|
|
case KVM_REG_PPC_TB_OFFSET:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
|
|
|
|
break;
|
2013-09-20 11:52:38 +07:00
|
|
|
case KVM_REG_PPC_LPCR:
|
2014-07-19 14:59:34 +07:00
|
|
|
case KVM_REG_PPC_LPCR_64:
|
2013-09-20 11:52:38 +07:00
|
|
|
*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
|
|
|
|
break;
|
2013-09-20 11:52:39 +07:00
|
|
|
case KVM_REG_PPC_PPR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.ppr);
|
|
|
|
break;
|
2014-03-25 06:47:03 +07:00
|
|
|
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
|
|
|
|
case KVM_REG_PPC_TFHAR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.tfhar);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TFIAR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.tfiar);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TEXASR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.texasr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
|
|
|
|
i = id - KVM_REG_PPC_TM_GPR0;
|
|
|
|
*val = get_reg_val(id, vcpu->arch.gpr_tm[i]);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
|
|
|
|
{
|
|
|
|
int j;
|
|
|
|
i = id - KVM_REG_PPC_TM_VSR0;
|
|
|
|
if (i < 32)
|
|
|
|
for (j = 0; j < TS_FPRWIDTH; j++)
|
|
|
|
val->vsxval[j] = vcpu->arch.fp_tm.fpr[i][j];
|
|
|
|
else {
|
|
|
|
if (cpu_has_feature(CPU_FTR_ALTIVEC))
|
|
|
|
val->vval = vcpu->arch.vr_tm.vr[i-32];
|
|
|
|
else
|
|
|
|
r = -ENXIO;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case KVM_REG_PPC_TM_CR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.cr_tm);
|
|
|
|
break;
|
2016-11-07 11:09:58 +07:00
|
|
|
case KVM_REG_PPC_TM_XER:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.xer_tm);
|
|
|
|
break;
|
2014-03-25 06:47:03 +07:00
|
|
|
case KVM_REG_PPC_TM_LR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.lr_tm);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_CTR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.ctr_tm);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_FPSCR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.fp_tm.fpscr);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_AMR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.amr_tm);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_PPR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.ppr_tm);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_VRSAVE:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vrsave_tm);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_VSCR:
|
|
|
|
if (cpu_has_feature(CPU_FTR_ALTIVEC))
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vr_tm.vscr.u[3]);
|
|
|
|
else
|
|
|
|
r = -ENXIO;
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_DSCR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.dscr_tm);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_TAR:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.tar_tm);
|
|
|
|
break;
|
|
|
|
#endif
|
2013-09-21 11:35:02 +07:00
|
|
|
case KVM_REG_PPC_ARCH_COMPAT:
|
|
|
|
*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
|
|
|
|
break;
|
2011-12-12 19:26:50 +07:00
|
|
|
default:
|
2012-09-26 03:31:56 +07:00
|
|
|
r = -EINVAL;
|
2011-12-12 19:26:50 +07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
|
|
|
|
union kvmppc_one_reg *val)
|
2011-12-12 19:26:50 +07:00
|
|
|
{
|
2012-09-26 03:31:56 +07:00
|
|
|
int r = 0;
|
|
|
|
long int i;
|
2012-09-26 03:33:06 +07:00
|
|
|
unsigned long addr, len;
|
2011-12-12 19:26:50 +07:00
|
|
|
|
2012-09-26 03:31:56 +07:00
|
|
|
switch (id) {
|
2011-12-12 19:26:50 +07:00
|
|
|
case KVM_REG_PPC_HIOR:
|
|
|
|
/* Only allow this to be set to zero */
|
2012-09-26 03:31:56 +07:00
|
|
|
if (set_reg_val(id, *val))
|
2011-12-12 19:26:50 +07:00
|
|
|
r = -EINVAL;
|
|
|
|
break;
|
2012-09-26 03:31:56 +07:00
|
|
|
case KVM_REG_PPC_DABR:
|
|
|
|
vcpu->arch.dabr = set_reg_val(id, *val);
|
|
|
|
break;
|
KVM: PPC: Book3S HV: Add support for DABRX register on POWER7
The DABRX (DABR extension) register on POWER7 processors provides finer
control over which accesses cause a data breakpoint interrupt. It
contains 3 bits which indicate whether to enable accesses in user,
kernel and hypervisor modes respectively to cause data breakpoint
interrupts, plus one bit that enables both real mode and virtual mode
accesses to cause interrupts. Currently, KVM sets DABRX to allow
both kernel and user accesses to cause interrupts while in the guest.
This adds support for the guest to specify other values for DABRX.
PAPR defines a H_SET_XDABR hcall to allow the guest to set both DABR
and DABRX with one call. This adds a real-mode implementation of
H_SET_XDABR, which shares most of its code with the existing H_SET_DABR
implementation. To support this, we add a per-vcpu field to store the
DABRX value plus code to get and set it via the ONE_REG interface.
For Linux guests to use this new hcall, userspace needs to add
"hcall-xdabr" to the set of strings in the /chosen/hypertas-functions
property in the device tree. If userspace does this and then migrates
the guest to a host where the kernel doesn't include this patch, then
userspace will need to implement H_SET_XDABR by writing the specified
DABR value to the DABR using the ONE_REG interface. In that case, the
old kernel will set DABRX to DABRX_USER | DABRX_KERNEL. That should
still work correctly, at least for Linux guests, since Linux guests
cope with getting data breakpoint interrupts in modes that weren't
requested by just ignoring the interrupt, and Linux guests never set
DABRX_BTI.
The other thing this does is to make H_SET_DABR and H_SET_XDABR work
on POWER8, which has the DAWR and DAWRX instead of DABR/X. Guests that
know about POWER8 should use H_SET_MODE rather than H_SET_[X]DABR, but
guests running in POWER7 compatibility mode will still use H_SET_[X]DABR.
For them, this adds the logic to convert DABR/X values into DAWR/X values
on POWER8.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:29 +07:00
|
|
|
case KVM_REG_PPC_DABRX:
|
|
|
|
vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
|
|
|
|
break;
|
2012-09-26 03:31:56 +07:00
|
|
|
case KVM_REG_PPC_DSCR:
|
|
|
|
vcpu->arch.dscr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PURR:
|
|
|
|
vcpu->arch.purr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_SPURR:
|
|
|
|
vcpu->arch.spurr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_AMR:
|
|
|
|
vcpu->arch.amr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_UAMOR:
|
|
|
|
vcpu->arch.uamor = set_reg_val(id, *val);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
|
2012-09-26 03:31:56 +07:00
|
|
|
i = id - KVM_REG_PPC_MMCR0;
|
|
|
|
vcpu->arch.mmcr[i] = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
|
|
|
|
i = id - KVM_REG_PPC_PMC1;
|
|
|
|
vcpu->arch.pmc[i] = set_reg_val(id, *val);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
|
|
|
|
i = id - KVM_REG_PPC_SPMC1;
|
|
|
|
vcpu->arch.spmc[i] = set_reg_val(id, *val);
|
|
|
|
break;
|
2013-09-06 10:11:18 +07:00
|
|
|
case KVM_REG_PPC_SIAR:
|
|
|
|
vcpu->arch.siar = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_SDAR:
|
|
|
|
vcpu->arch.sdar = set_reg_val(id, *val);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_SIER:
|
|
|
|
vcpu->arch.sier = set_reg_val(id, *val);
|
2012-09-26 03:32:30 +07:00
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_IAMR:
|
|
|
|
vcpu->arch.iamr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PSPB:
|
|
|
|
vcpu->arch.pspb = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_DPDES:
|
|
|
|
vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
|
|
|
|
break;
|
2016-09-15 10:42:52 +07:00
|
|
|
case KVM_REG_PPC_VTB:
|
|
|
|
vcpu->arch.vcore->vtb = set_reg_val(id, *val);
|
|
|
|
break;
|
2014-01-08 17:25:21 +07:00
|
|
|
case KVM_REG_PPC_DAWR:
|
|
|
|
vcpu->arch.dawr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_DAWRX:
|
|
|
|
vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_CIABR:
|
|
|
|
vcpu->arch.ciabr = set_reg_val(id, *val);
|
|
|
|
/* Don't allow setting breakpoints in hypervisor code */
|
|
|
|
if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
|
|
|
|
vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_CSIGR:
|
|
|
|
vcpu->arch.csigr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TACR:
|
|
|
|
vcpu->arch.tacr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TCSCR:
|
|
|
|
vcpu->arch.tcscr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PID:
|
|
|
|
vcpu->arch.pid = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_ACOP:
|
|
|
|
vcpu->arch.acop = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_WORT:
|
|
|
|
vcpu->arch.wort = set_reg_val(id, *val);
|
2012-09-26 03:32:30 +07:00
|
|
|
break;
|
2016-11-18 09:11:42 +07:00
|
|
|
case KVM_REG_PPC_TIDR:
|
|
|
|
vcpu->arch.tid = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_PSSCR:
|
|
|
|
vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
|
|
|
|
break;
|
2012-09-26 03:33:06 +07:00
|
|
|
case KVM_REG_PPC_VPA_ADDR:
|
|
|
|
addr = set_reg_val(id, *val);
|
|
|
|
r = -EINVAL;
|
|
|
|
if (!addr && (vcpu->arch.slb_shadow.next_gpa ||
|
|
|
|
vcpu->arch.dtl.next_gpa))
|
|
|
|
break;
|
|
|
|
r = set_vpa(vcpu, &vcpu->arch.vpa, addr, sizeof(struct lppaca));
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_VPA_SLB:
|
|
|
|
addr = val->vpaval.addr;
|
|
|
|
len = val->vpaval.length;
|
|
|
|
r = -EINVAL;
|
|
|
|
if (addr && !vcpu->arch.vpa.next_gpa)
|
|
|
|
break;
|
|
|
|
r = set_vpa(vcpu, &vcpu->arch.slb_shadow, addr, len);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_VPA_DTL:
|
|
|
|
addr = val->vpaval.addr;
|
|
|
|
len = val->vpaval.length;
|
|
|
|
r = -EINVAL;
|
2012-10-15 08:18:37 +07:00
|
|
|
if (addr && (len < sizeof(struct dtl_entry) ||
|
|
|
|
!vcpu->arch.vpa.next_gpa))
|
2012-09-26 03:33:06 +07:00
|
|
|
break;
|
|
|
|
len -= len % sizeof(struct dtl_entry);
|
|
|
|
r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
|
|
|
|
break;
|
KVM: PPC: Book3S HV: Implement timebase offset for guests
This allows guests to have a different timebase origin from the host.
This is needed for migration, where a guest can migrate from one host
to another and the two hosts might have a different timebase origin.
However, the timebase seen by the guest must not go backwards, and
should go forwards only by a small amount corresponding to the time
taken for the migration.
Therefore this provides a new per-vcpu value accessed via the one_reg
interface using the new KVM_REG_PPC_TB_OFFSET identifier. This value
defaults to 0 and is not modified by KVM. On entering the guest, this
value is added onto the timebase, and on exiting the guest, it is
subtracted from the timebase.
This is only supported for recent POWER hardware which has the TBU40
(timebase upper 40 bits) register. Writing to the TBU40 register only
alters the upper 40 bits of the timebase, leaving the lower 24 bits
unchanged. This provides a way to modify the timebase for guest
migration without disturbing the synchronization of the timebase
registers across CPU cores. The kernel rounds up the value given
to a multiple of 2^24.
Timebase values stored in KVM structures (struct kvm_vcpu, struct
kvmppc_vcore, etc.) are stored as host timebase values. The timebase
values in the dispatch trace log need to be guest timebase values,
however, since that is read directly by the guest. This moves the
setting of vcpu->arch.dec_expires on guest exit to a point after we
have restored the host timebase so that vcpu->arch.dec_expires is a
host timebase value.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-06 10:17:46 +07:00
|
|
|
case KVM_REG_PPC_TB_OFFSET:
|
|
|
|
/* round up to multiple of 2^24 */
|
|
|
|
vcpu->arch.vcore->tb_offset =
|
|
|
|
ALIGN(set_reg_val(id, *val), 1UL << 24);
|
|
|
|
break;
|
2013-09-20 11:52:38 +07:00
|
|
|
case KVM_REG_PPC_LPCR:
|
2014-07-19 14:59:34 +07:00
|
|
|
kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), true);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_LPCR_64:
|
|
|
|
kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false);
|
2013-09-20 11:52:38 +07:00
|
|
|
break;
|
2013-09-20 11:52:39 +07:00
|
|
|
case KVM_REG_PPC_PPR:
|
|
|
|
vcpu->arch.ppr = set_reg_val(id, *val);
|
|
|
|
break;
|
2014-03-25 06:47:03 +07:00
|
|
|
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
|
|
|
|
case KVM_REG_PPC_TFHAR:
|
|
|
|
vcpu->arch.tfhar = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TFIAR:
|
|
|
|
vcpu->arch.tfiar = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TEXASR:
|
|
|
|
vcpu->arch.texasr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
|
|
|
|
i = id - KVM_REG_PPC_TM_GPR0;
|
|
|
|
vcpu->arch.gpr_tm[i] = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
|
|
|
|
{
|
|
|
|
int j;
|
|
|
|
i = id - KVM_REG_PPC_TM_VSR0;
|
|
|
|
if (i < 32)
|
|
|
|
for (j = 0; j < TS_FPRWIDTH; j++)
|
|
|
|
vcpu->arch.fp_tm.fpr[i][j] = val->vsxval[j];
|
|
|
|
else
|
|
|
|
if (cpu_has_feature(CPU_FTR_ALTIVEC))
|
|
|
|
vcpu->arch.vr_tm.vr[i-32] = val->vval;
|
|
|
|
else
|
|
|
|
r = -ENXIO;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case KVM_REG_PPC_TM_CR:
|
|
|
|
vcpu->arch.cr_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
2016-11-07 11:09:58 +07:00
|
|
|
case KVM_REG_PPC_TM_XER:
|
|
|
|
vcpu->arch.xer_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
2014-03-25 06:47:03 +07:00
|
|
|
case KVM_REG_PPC_TM_LR:
|
|
|
|
vcpu->arch.lr_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_CTR:
|
|
|
|
vcpu->arch.ctr_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_FPSCR:
|
|
|
|
vcpu->arch.fp_tm.fpscr = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_AMR:
|
|
|
|
vcpu->arch.amr_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_PPR:
|
|
|
|
vcpu->arch.ppr_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_VRSAVE:
|
|
|
|
vcpu->arch.vrsave_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_VSCR:
|
|
|
|
if (cpu_has_feature(CPU_FTR_ALTIVEC))
|
|
|
|
vcpu->arch.vr.vscr.u[3] = set_reg_val(id, *val);
|
|
|
|
else
|
|
|
|
r = - ENXIO;
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_DSCR:
|
|
|
|
vcpu->arch.dscr_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
case KVM_REG_PPC_TM_TAR:
|
|
|
|
vcpu->arch.tar_tm = set_reg_val(id, *val);
|
|
|
|
break;
|
|
|
|
#endif
|
2013-09-21 11:35:02 +07:00
|
|
|
case KVM_REG_PPC_ARCH_COMPAT:
|
|
|
|
r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
|
|
|
|
break;
|
2011-12-12 19:26:50 +07:00
|
|
|
default:
|
2012-09-26 03:31:56 +07:00
|
|
|
r = -EINVAL;
|
2011-12-12 19:26:50 +07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
/*
|
|
|
|
* On POWER9, threads are independent and can be in different partitions.
|
|
|
|
* Therefore we consider each thread to be a subcore.
|
|
|
|
* There is a restriction that all threads have to be in the same
|
|
|
|
* MMU mode (radix or HPT), unfortunately, but since we only support
|
|
|
|
* HPT guests on a HPT host so far, that isn't an impediment yet.
|
|
|
|
*/
|
|
|
|
static int threads_per_vcore(void)
|
|
|
|
{
|
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
return 1;
|
|
|
|
return threads_per_subcore;
|
|
|
|
}
|
|
|
|
|
2014-07-18 11:18:42 +07:00
|
|
|
static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
|
|
|
|
{
|
|
|
|
struct kvmppc_vcore *vcore;
|
|
|
|
|
|
|
|
vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL);
|
|
|
|
|
|
|
|
if (vcore == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
spin_lock_init(&vcore->lock);
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
spin_lock_init(&vcore->stoltb_lock);
|
2016-02-19 15:46:39 +07:00
|
|
|
init_swait_queue_head(&vcore->wq);
|
2014-07-18 11:18:42 +07:00
|
|
|
vcore->preempt_tb = TB_NIL;
|
|
|
|
vcore->lpcr = kvm->arch.lpcr;
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
vcore->first_vcpuid = core * threads_per_vcore();
|
2014-07-18 11:18:42 +07:00
|
|
|
vcore->kvm = kvm;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
INIT_LIST_HEAD(&vcore->preempt_list);
|
2014-07-18 11:18:42 +07:00
|
|
|
|
|
|
|
return vcore;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code. Currently these
times are accumulated per vcpu in 5 parts of the code:
* rm_entry - time taken from the start of kvmppc_hv_entry() until
just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
guest until we either re-enter the guest or decide to exit to the
host. This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
while other threads in the same vcore are active.
These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings". This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.
The overhead of the extra code amounts to about 30ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since
production environments may not wish to incur this overhead, the new
code is conditional on a new config symbol,
CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:02 +07:00
|
|
|
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
|
|
|
|
static struct debugfs_timings_element {
|
|
|
|
const char *name;
|
|
|
|
size_t offset;
|
|
|
|
} timings[] = {
|
|
|
|
{"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
|
|
|
|
{"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
|
|
|
|
{"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
|
|
|
|
{"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
|
|
|
|
{"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
|
|
|
|
};
|
|
|
|
|
|
|
|
#define N_TIMINGS (sizeof(timings) / sizeof(timings[0]))
|
|
|
|
|
|
|
|
struct debugfs_timings_state {
|
|
|
|
struct kvm_vcpu *vcpu;
|
|
|
|
unsigned int buflen;
|
|
|
|
char buf[N_TIMINGS * 100];
|
|
|
|
};
|
|
|
|
|
|
|
|
static int debugfs_timings_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
struct kvm_vcpu *vcpu = inode->i_private;
|
|
|
|
struct debugfs_timings_state *p;
|
|
|
|
|
|
|
|
p = kzalloc(sizeof(*p), GFP_KERNEL);
|
|
|
|
if (!p)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
kvm_get_kvm(vcpu->kvm);
|
|
|
|
p->vcpu = vcpu;
|
|
|
|
file->private_data = p;
|
|
|
|
|
|
|
|
return nonseekable_open(inode, file);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int debugfs_timings_release(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
struct debugfs_timings_state *p = file->private_data;
|
|
|
|
|
|
|
|
kvm_put_kvm(p->vcpu->kvm);
|
|
|
|
kfree(p);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
|
|
|
|
size_t len, loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct debugfs_timings_state *p = file->private_data;
|
|
|
|
struct kvm_vcpu *vcpu = p->vcpu;
|
|
|
|
char *s, *buf_end;
|
|
|
|
struct kvmhv_tb_accumulator tb;
|
|
|
|
u64 count;
|
|
|
|
loff_t pos;
|
|
|
|
ssize_t n;
|
|
|
|
int i, loops;
|
|
|
|
bool ok;
|
|
|
|
|
|
|
|
if (!p->buflen) {
|
|
|
|
s = p->buf;
|
|
|
|
buf_end = s + sizeof(p->buf);
|
|
|
|
for (i = 0; i < N_TIMINGS; ++i) {
|
|
|
|
struct kvmhv_tb_accumulator *acc;
|
|
|
|
|
|
|
|
acc = (struct kvmhv_tb_accumulator *)
|
|
|
|
((unsigned long)vcpu + timings[i].offset);
|
|
|
|
ok = false;
|
|
|
|
for (loops = 0; loops < 1000; ++loops) {
|
|
|
|
count = acc->seqcount;
|
|
|
|
if (!(count & 1)) {
|
|
|
|
smp_rmb();
|
|
|
|
tb = *acc;
|
|
|
|
smp_rmb();
|
|
|
|
if (count == acc->seqcount) {
|
|
|
|
ok = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
udelay(1);
|
|
|
|
}
|
|
|
|
if (!ok)
|
|
|
|
snprintf(s, buf_end - s, "%s: stuck\n",
|
|
|
|
timings[i].name);
|
|
|
|
else
|
|
|
|
snprintf(s, buf_end - s,
|
|
|
|
"%s: %llu %llu %llu %llu\n",
|
|
|
|
timings[i].name, count / 2,
|
|
|
|
tb_to_ns(tb.tb_total),
|
|
|
|
tb_to_ns(tb.tb_min),
|
|
|
|
tb_to_ns(tb.tb_max));
|
|
|
|
s += strlen(s);
|
|
|
|
}
|
|
|
|
p->buflen = s - p->buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
pos = *ppos;
|
|
|
|
if (pos >= p->buflen)
|
|
|
|
return 0;
|
|
|
|
if (len > p->buflen - pos)
|
|
|
|
len = p->buflen - pos;
|
|
|
|
n = copy_to_user(buf, p->buf + pos, len);
|
|
|
|
if (n) {
|
|
|
|
if (n == len)
|
|
|
|
return -EFAULT;
|
|
|
|
len -= n;
|
|
|
|
}
|
|
|
|
*ppos = pos + len;
|
|
|
|
return len;
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
|
|
|
|
size_t len, loff_t *ppos)
|
|
|
|
{
|
|
|
|
return -EACCES;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations debugfs_timings_ops = {
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.open = debugfs_timings_open,
|
|
|
|
.release = debugfs_timings_release,
|
|
|
|
.read = debugfs_timings_read,
|
|
|
|
.write = debugfs_timings_write,
|
|
|
|
.llseek = generic_file_llseek,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Create a debugfs directory for the vcpu */
|
|
|
|
static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
|
|
|
|
{
|
|
|
|
char buf[16];
|
|
|
|
struct kvm *kvm = vcpu->kvm;
|
|
|
|
|
|
|
|
snprintf(buf, sizeof(buf), "vcpu%u", id);
|
|
|
|
if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
|
|
|
|
return;
|
|
|
|
vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
|
|
|
|
if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
|
|
|
|
return;
|
|
|
|
vcpu->arch.debugfs_timings =
|
|
|
|
debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
|
|
|
|
vcpu, &debugfs_timings_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
|
|
|
|
static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
|
|
|
|
unsigned int id)
|
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
|
|
|
{
|
|
|
|
struct kvm_vcpu *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 07:23:08 +07:00
|
|
|
int err = -EINVAL;
|
|
|
|
int core;
|
|
|
|
struct kvmppc_vcore *vcore;
|
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
|
|
|
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
core = id / threads_per_vcore();
|
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 07:23:08 +07:00
|
|
|
if (core >= KVM_MAX_VCORES)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = -ENOMEM;
|
2011-12-07 15:24:56 +07:00
|
|
|
vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
|
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
|
|
|
if (!vcpu)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = kvm_vcpu_init(vcpu, kvm, id);
|
|
|
|
if (err)
|
|
|
|
goto free_vcpu;
|
|
|
|
|
|
|
|
vcpu->arch.shared = &vcpu->arch.shregs;
|
2014-04-24 18:46:24 +07:00
|
|
|
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
|
|
|
|
/*
|
|
|
|
* The shared struct is never shared on HV,
|
|
|
|
* so we can always use host endianness
|
|
|
|
*/
|
|
|
|
#ifdef __BIG_ENDIAN__
|
|
|
|
vcpu->arch.shared_big_endian = true;
|
|
|
|
#else
|
|
|
|
vcpu->arch.shared_big_endian = false;
|
|
|
|
#endif
|
|
|
|
#endif
|
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
|
|
|
vcpu->arch.mmcr[0] = MMCR0_FC;
|
|
|
|
vcpu->arch.ctrl = CTRL_RUNLATCH;
|
|
|
|
/* default to host PVR, since we can't spoof it */
|
2013-10-07 23:47:53 +07:00
|
|
|
kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
spin_lock_init(&vcpu->arch.vpa_update_lock);
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
spin_lock_init(&vcpu->arch.tbacct_lock);
|
|
|
|
vcpu->arch.busy_preempt = TB_NIL;
|
2014-01-08 17:25:30 +07:00
|
|
|
vcpu->arch.intr_msr = MSR_SF | MSR_ME;
|
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
|
|
|
|
|
|
|
kvmppc_mmu_book3s_hv_init(vcpu);
|
|
|
|
|
2012-10-15 08:17:42 +07:00
|
|
|
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
|
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 07:23:08 +07:00
|
|
|
|
|
|
|
init_waitqueue_head(&vcpu->arch.cpu_run);
|
|
|
|
|
|
|
|
mutex_lock(&kvm->lock);
|
|
|
|
vcore = kvm->arch.vcores[core];
|
|
|
|
if (!vcore) {
|
2014-07-18 11:18:42 +07:00
|
|
|
vcore = kvmppc_vcore_create(kvm, core);
|
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 07:23:08 +07:00
|
|
|
kvm->arch.vcores[core] = vcore;
|
KVM: PPC: Book3S HV: Improve handling of local vs. global TLB invalidations
When we change or remove a HPT (hashed page table) entry, we can do
either a global TLB invalidation (tlbie) that works across the whole
machine, or a local invalidation (tlbiel) that only affects this core.
Currently we do local invalidations if the VM has only one vcpu or if
the guest requests it with the H_LOCAL flag, though the guest Linux
kernel currently doesn't ever use H_LOCAL. Then, to cope with the
possibility that vcpus moving around to different physical cores might
expose stale TLB entries, there is some code in kvmppc_hv_entry to
flush the whole TLB of entries for this VM if either this vcpu is now
running on a different physical core from where it last ran, or if this
physical core last ran a different vcpu.
There are a number of problems on POWER7 with this as it stands:
- The TLB invalidation is done per thread, whereas it only needs to be
done per core, since the TLB is shared between the threads.
- With the possibility of the host paging out guest pages, the use of
H_LOCAL by an SMP guest is dangerous since the guest could possibly
retain and use a stale TLB entry pointing to a page that had been
removed from the guest.
- The TLB invalidations that we do when a vcpu moves from one physical
core to another are unnecessary in the case of an SMP guest that isn't
using H_LOCAL.
- The optimization of using local invalidations rather than global should
apply to guests with one virtual core, not just one vcpu.
(None of this applies on PPC970, since there we always have to
invalidate the whole TLB when entering and leaving the guest, and we
can't support paging out guest memory.)
To fix these problems and simplify the code, we now maintain a simple
cpumask of which cpus need to flush the TLB on entry to the guest.
(This is indexed by cpu, though we only ever use the bits for thread
0 of each core.) Whenever we do a local TLB invalidation, we set the
bits for every cpu except the bit for thread 0 of the core that we're
currently running on. Whenever we enter a guest, we test and clear the
bit for our core, and flush the TLB if it was set.
On initial startup of the VM, and when resetting the HPT, we set all the
bits in the need_tlb_flush cpumask, since any core could potentially have
stale TLB entries from the previous VM to use the same LPID, or the
previous contents of the HPT.
Then, we maintain a count of the number of online virtual cores, and use
that when deciding whether to use a local invalidation rather than the
number of online vcpus. The code to make that decision is extracted out
into a new function, global_invalidates(). For multi-core guests on
POWER7 (i.e. when we are using mmu notifiers), we now never do local
invalidations regardless of the H_LOCAL flag.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-22 06:28:08 +07:00
|
|
|
kvm->arch.online_vcores++;
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
|
|
|
|
if (!vcore)
|
|
|
|
goto free_vcpu;
|
|
|
|
|
|
|
|
spin_lock(&vcore->lock);
|
|
|
|
++vcore->num_threads;
|
|
|
|
spin_unlock(&vcore->lock);
|
|
|
|
vcpu->arch.vcore = vcore;
|
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers
On a threaded processor such as POWER7, we group VCPUs into virtual
cores and arrange that the VCPUs in a virtual core run on the same
physical core. Currently we don't enforce any correspondence between
virtual thread numbers within a virtual core and physical thread
numbers. Physical threads are allocated starting at 0 on a first-come
first-served basis to runnable virtual threads (VCPUs).
POWER8 implements a new "msgsndp" instruction which guest kernels can
use to interrupt other threads in the same core or sub-core. Since
the instruction takes the destination physical thread ID as a parameter,
it becomes necessary to align the physical thread IDs with the virtual
thread IDs, that is, to make sure virtual thread N within a virtual
core always runs on physical thread N.
This means that it's possible that thread 0, which is where we call
__kvmppc_vcore_entry, may end up running some other vcpu than the
one whose task called kvmppc_run_core(), or it may end up running
no vcpu at all, if for example thread 0 of the virtual core is
currently executing in userspace. However, we do need thread 0
to be responsible for switching the MMU -- a previous version of
this patch that had other threads switching the MMU was found to
be responsible for occasional memory corruption and machine check
interrupts in the guest on POWER7 machines.
To accommodate this, we no longer pass the vcpu pointer to
__kvmppc_vcore_entry, but instead let the assembly code load it from
the PACA. Since the assembly code will need to know the kvm pointer
and the thread ID for threads which don't have a vcpu, we move the
thread ID into the PACA and we add a kvm pointer to the virtual core
structure.
In the case where thread 0 has no vcpu to run, it still calls into
kvmppc_hv_entry in order to do the MMU switch, and then naps until
either its vcpu is ready to run in the guest, or some other thread
needs to exit the guest. In the latter case, thread 0 jumps to the
code that switches the MMU back to the host. This control flow means
that now we switch the MMU before loading any guest vcpu state.
Similarly, on guest exit we now save all the guest vcpu state before
switching the MMU back to the host. This has required substantial
code movement, making the diff rather large.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:20 +07:00
|
|
|
vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
vcpu->arch.thread_cpu = -1;
|
KVM: PPC: Book3S HV: Invalidate TLB on radix guest vcpu movement
With radix, the guest can do TLB invalidations itself using the tlbie
(global) and tlbiel (local) TLB invalidation instructions. Linux guests
use local TLB invalidations for translations that have only ever been
accessed on one vcpu. However, that doesn't mean that the translations
have only been accessed on one physical cpu (pcpu) since vcpus can move
around from one pcpu to another. Thus a tlbiel might leave behind stale
TLB entries on a pcpu where the vcpu previously ran, and if that task
then moves back to that previous pcpu, it could see those stale TLB
entries and thus access memory incorrectly. The usual symptom of this
is random segfaults in userspace programs in the guest.
To cope with this, we detect when a vcpu is about to start executing on
a thread in a core that is a different core from the last time it
executed. If that is the case, then we mark the core as needing a
TLB flush and then send an interrupt to any thread in the core that is
currently running a vcpu from the same guest. This will get those vcpus
out of the guest, and the first one to re-enter the guest will do the
TLB flush. The reason for interrupting the vcpus executing on the old
core is to cope with the following scenario:
CPU 0 CPU 1 CPU 4
(core 0) (core 0) (core 1)
VCPU 0 runs task X VCPU 1 runs
core 0 TLB gets
entries from task X
VCPU 0 moves to CPU 4
VCPU 0 runs task X
Unmap pages of task X
tlbiel
(still VCPU 1) task X moves to VCPU 1
task X runs
task X sees stale TLB
entries
That is, as soon as the VCPU starts executing on the new core, it
could unmap and tlbiel some page table entries, and then the task
could migrate to one of the VCPUs running on the old core and
potentially see stale TLB entries.
Since the TLB is shared between all the threads in a core, we only
use the bit of kvm->arch.need_tlb_flush corresponding to the first
thread in the core. To ensure that we don't have a window where we
can miss a flush, this moves the clearing of the bit from before the
actual flush to after it. This way, two threads might both do the
flush, but we prevent the situation where one thread can enter the
guest before the flush is finished.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-30 17:21:50 +07:00
|
|
|
vcpu->arch.prev_cpu = -1;
|
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 07:23:08 +07:00
|
|
|
|
2011-08-10 18:57:08 +07:00
|
|
|
vcpu->arch.cpu_type = KVM_CPU_3S_64;
|
|
|
|
kvmppc_sanity_check(vcpu);
|
|
|
|
|
KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code. Currently these
times are accumulated per vcpu in 5 parts of the code:
* rm_entry - time taken from the start of kvmppc_hv_entry() until
just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
guest until we either re-enter the guest or decide to exit to the
host. This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
while other threads in the same vcore are active.
These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings". This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.
The overhead of the extra code amounts to about 30ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since
production environments may not wish to incur this overhead, the new
code is conditional on a new config symbol,
CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:02 +07:00
|
|
|
debugfs_vcpu_init(vcpu, id);
|
|
|
|
|
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
|
|
|
return vcpu;
|
|
|
|
|
|
|
|
free_vcpu:
|
2011-12-07 15:24:56 +07:00
|
|
|
kmem_cache_free(kvm_vcpu_cache, 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
|
|
|
out:
|
|
|
|
return ERR_PTR(err);
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
|
|
|
|
{
|
|
|
|
if (vpa->pinned_addr)
|
|
|
|
kvmppc_unpin_guest_page(kvm, vpa->pinned_addr, vpa->gpa,
|
|
|
|
vpa->dirty);
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_core_vcpu_free_hv(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
|
|
|
{
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 02:51:04 +07:00
|
|
|
unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
|
|
|
|
unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
|
|
|
|
unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
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
|
|
|
kvm_vcpu_uninit(vcpu);
|
2011-12-07 15:24:56 +07:00
|
|
|
kmem_cache_free(kvm_vcpu_cache, 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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
/* Indicate we want to get back into the guest */
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
static void kvmppc_set_timer(struct kvm_vcpu *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 07:23:08 +07:00
|
|
|
{
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
unsigned long dec_nsec, now;
|
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 07:23:08 +07:00
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
now = get_tb();
|
|
|
|
if (now > vcpu->arch.dec_expires) {
|
|
|
|
/* decrementer has already gone negative */
|
|
|
|
kvmppc_core_queue_dec(vcpu);
|
2011-11-09 07:23:20 +07:00
|
|
|
kvmppc_core_prepare_to_enter(vcpu);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
return;
|
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 07:23:08 +07:00
|
|
|
}
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
|
|
|
|
/ tb_ticks_per_sec;
|
2016-12-25 18:30:41 +07:00
|
|
|
hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vcpu->arch.timer_running = 1;
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
static void kvmppc_end_cede(struct kvm_vcpu *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 07:23:08 +07:00
|
|
|
{
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vcpu->arch.ceded = 0;
|
|
|
|
if (vcpu->arch.timer_running) {
|
|
|
|
hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
|
|
|
|
vcpu->arch.timer_running = 0;
|
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers
On a threaded processor such as POWER7, we group VCPUs into virtual
cores and arrange that the VCPUs in a virtual core run on the same
physical core. Currently we don't enforce any correspondence between
virtual thread numbers within a virtual core and physical thread
numbers. Physical threads are allocated starting at 0 on a first-come
first-served basis to runnable virtual threads (VCPUs).
POWER8 implements a new "msgsndp" instruction which guest kernels can
use to interrupt other threads in the same core or sub-core. Since
the instruction takes the destination physical thread ID as a parameter,
it becomes necessary to align the physical thread IDs with the virtual
thread IDs, that is, to make sure virtual thread N within a virtual
core always runs on physical thread N.
This means that it's possible that thread 0, which is where we call
__kvmppc_vcore_entry, may end up running some other vcpu than the
one whose task called kvmppc_run_core(), or it may end up running
no vcpu at all, if for example thread 0 of the virtual core is
currently executing in userspace. However, we do need thread 0
to be responsible for switching the MMU -- a previous version of
this patch that had other threads switching the MMU was found to
be responsible for occasional memory corruption and machine check
interrupts in the guest on POWER7 machines.
To accommodate this, we no longer pass the vcpu pointer to
__kvmppc_vcore_entry, but instead let the assembly code load it from
the PACA. Since the assembly code will need to know the kvm pointer
and the thread ID for threads which don't have a vcpu, we move the
thread ID into the PACA and we add a kvm pointer to the virtual core
structure.
In the case where thread 0 has no vcpu to run, it still calls into
kvmppc_hv_entry in order to do the MMU switch, and then naps until
either its vcpu is ready to run in the guest, or some other thread
needs to exit the guest. In the latter case, thread 0 jumps to the
code that switches the MMU back to the host. This control flow means
that now we switch the MMU before loading any guest vcpu state.
Similarly, on guest exit we now save all the guest vcpu state before
switching the MMU back to the host. This has required substantial
code movement, making the diff rather large.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:20 +07:00
|
|
|
extern void __kvmppc_vcore_entry(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
|
|
|
|
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 07:23:08 +07:00
|
|
|
static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
|
|
|
|
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
|
|
|
{
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
u64 now;
|
|
|
|
|
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 07:23:08 +07:00
|
|
|
if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
|
|
|
|
return;
|
2013-11-16 13:46:04 +07:00
|
|
|
spin_lock_irq(&vcpu->arch.tbacct_lock);
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
now = mftb();
|
|
|
|
vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
|
|
|
|
vcpu->arch.stolen_logged;
|
|
|
|
vcpu->arch.busy_preempt = now;
|
|
|
|
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
|
2013-11-16 13:46:04 +07:00
|
|
|
spin_unlock_irq(&vcpu->arch.tbacct_lock);
|
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 07:23:08 +07:00
|
|
|
--vc->n_runnable;
|
2016-08-02 11:03:20 +07:00
|
|
|
WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], NULL);
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
2012-02-03 07:54:17 +07:00
|
|
|
static int kvmppc_grab_hwthread(int cpu)
|
|
|
|
{
|
|
|
|
struct paca_struct *tpaca;
|
2014-09-02 13:14:42 +07:00
|
|
|
long timeout = 10000;
|
2012-02-03 07:54:17 +07:00
|
|
|
|
|
|
|
tpaca = &paca[cpu];
|
|
|
|
|
|
|
|
/* Ensure the thread won't go into the kernel if it wakes */
|
2012-10-15 08:16:14 +07:00
|
|
|
tpaca->kvm_hstate.kvm_vcpu = NULL;
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
tpaca->kvm_hstate.kvm_vcore = NULL;
|
2015-03-28 10:21:06 +07:00
|
|
|
tpaca->kvm_hstate.napping = 0;
|
|
|
|
smp_wmb();
|
|
|
|
tpaca->kvm_hstate.hwthread_req = 1;
|
2012-02-03 07:54:17 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If the thread is already executing in the kernel (e.g. handling
|
|
|
|
* a stray interrupt), wait for it to get back to nap mode.
|
|
|
|
* The smp_mb() is to ensure that our setting of hwthread_req
|
|
|
|
* is visible before we look at hwthread_state, so if this
|
|
|
|
* races with the code at system_reset_pSeries and the thread
|
|
|
|
* misses our setting of hwthread_req, we are sure to see its
|
|
|
|
* setting of hwthread_state, and vice versa.
|
|
|
|
*/
|
|
|
|
smp_mb();
|
|
|
|
while (tpaca->kvm_hstate.hwthread_state == KVM_HWTHREAD_IN_KERNEL) {
|
|
|
|
if (--timeout <= 0) {
|
|
|
|
pr_err("KVM: couldn't grab cpu %d\n", cpu);
|
|
|
|
return -EBUSY;
|
|
|
|
}
|
|
|
|
udelay(1);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void kvmppc_release_hwthread(int cpu)
|
|
|
|
{
|
|
|
|
struct paca_struct *tpaca;
|
|
|
|
|
|
|
|
tpaca = &paca[cpu];
|
|
|
|
tpaca->kvm_hstate.hwthread_req = 0;
|
|
|
|
tpaca->kvm_hstate.kvm_vcpu = NULL;
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
tpaca->kvm_hstate.kvm_vcore = NULL;
|
|
|
|
tpaca->kvm_hstate.kvm_split_mode = NULL;
|
2012-02-03 07:54:17 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Invalidate TLB on radix guest vcpu movement
With radix, the guest can do TLB invalidations itself using the tlbie
(global) and tlbiel (local) TLB invalidation instructions. Linux guests
use local TLB invalidations for translations that have only ever been
accessed on one vcpu. However, that doesn't mean that the translations
have only been accessed on one physical cpu (pcpu) since vcpus can move
around from one pcpu to another. Thus a tlbiel might leave behind stale
TLB entries on a pcpu where the vcpu previously ran, and if that task
then moves back to that previous pcpu, it could see those stale TLB
entries and thus access memory incorrectly. The usual symptom of this
is random segfaults in userspace programs in the guest.
To cope with this, we detect when a vcpu is about to start executing on
a thread in a core that is a different core from the last time it
executed. If that is the case, then we mark the core as needing a
TLB flush and then send an interrupt to any thread in the core that is
currently running a vcpu from the same guest. This will get those vcpus
out of the guest, and the first one to re-enter the guest will do the
TLB flush. The reason for interrupting the vcpus executing on the old
core is to cope with the following scenario:
CPU 0 CPU 1 CPU 4
(core 0) (core 0) (core 1)
VCPU 0 runs task X VCPU 1 runs
core 0 TLB gets
entries from task X
VCPU 0 moves to CPU 4
VCPU 0 runs task X
Unmap pages of task X
tlbiel
(still VCPU 1) task X moves to VCPU 1
task X runs
task X sees stale TLB
entries
That is, as soon as the VCPU starts executing on the new core, it
could unmap and tlbiel some page table entries, and then the task
could migrate to one of the VCPUs running on the old core and
potentially see stale TLB entries.
Since the TLB is shared between all the threads in a core, we only
use the bit of kvm->arch.need_tlb_flush corresponding to the first
thread in the core. To ensure that we don't have a window where we
can miss a flush, this moves the clearing of the bit from before the
actual flush to after it. This way, two threads might both do the
flush, but we prevent the situation where one thread can enter the
guest before the flush is finished.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-30 17:21:50 +07:00
|
|
|
static void do_nothing(void *x)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
cpu = cpu_first_thread_sibling(cpu);
|
|
|
|
cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush);
|
|
|
|
/*
|
|
|
|
* Make sure setting of bit in need_tlb_flush precedes
|
|
|
|
* testing of cpu_in_guest bits. The matching barrier on
|
|
|
|
* the other side is the first smp_mb() in kvmppc_run_core().
|
|
|
|
*/
|
|
|
|
smp_mb();
|
|
|
|
for (i = 0; i < threads_per_core; ++i)
|
|
|
|
if (cpumask_test_cpu(cpu + i, &kvm->arch.cpu_in_guest))
|
|
|
|
smp_call_function_single(cpu + i, do_nothing, NULL, 1);
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
|
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 07:23:08 +07:00
|
|
|
{
|
|
|
|
int cpu;
|
|
|
|
struct paca_struct *tpaca;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
struct kvmppc_vcore *mvc = vc->master_vcore;
|
KVM: PPC: Book3S HV: Invalidate TLB on radix guest vcpu movement
With radix, the guest can do TLB invalidations itself using the tlbie
(global) and tlbiel (local) TLB invalidation instructions. Linux guests
use local TLB invalidations for translations that have only ever been
accessed on one vcpu. However, that doesn't mean that the translations
have only been accessed on one physical cpu (pcpu) since vcpus can move
around from one pcpu to another. Thus a tlbiel might leave behind stale
TLB entries on a pcpu where the vcpu previously ran, and if that task
then moves back to that previous pcpu, it could see those stale TLB
entries and thus access memory incorrectly. The usual symptom of this
is random segfaults in userspace programs in the guest.
To cope with this, we detect when a vcpu is about to start executing on
a thread in a core that is a different core from the last time it
executed. If that is the case, then we mark the core as needing a
TLB flush and then send an interrupt to any thread in the core that is
currently running a vcpu from the same guest. This will get those vcpus
out of the guest, and the first one to re-enter the guest will do the
TLB flush. The reason for interrupting the vcpus executing on the old
core is to cope with the following scenario:
CPU 0 CPU 1 CPU 4
(core 0) (core 0) (core 1)
VCPU 0 runs task X VCPU 1 runs
core 0 TLB gets
entries from task X
VCPU 0 moves to CPU 4
VCPU 0 runs task X
Unmap pages of task X
tlbiel
(still VCPU 1) task X moves to VCPU 1
task X runs
task X sees stale TLB
entries
That is, as soon as the VCPU starts executing on the new core, it
could unmap and tlbiel some page table entries, and then the task
could migrate to one of the VCPUs running on the old core and
potentially see stale TLB entries.
Since the TLB is shared between all the threads in a core, we only
use the bit of kvm->arch.need_tlb_flush corresponding to the first
thread in the core. To ensure that we don't have a window where we
can miss a flush, this moves the clearing of the bit from before the
actual flush to after it. This way, two threads might both do the
flush, but we prevent the situation where one thread can enter the
guest before the flush is finished.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-30 17:21:50 +07:00
|
|
|
struct kvm *kvm = vc->kvm;
|
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 07:23:08 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
cpu = vc->pcpu;
|
|
|
|
if (vcpu) {
|
|
|
|
if (vcpu->arch.timer_running) {
|
|
|
|
hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
|
|
|
|
vcpu->arch.timer_running = 0;
|
|
|
|
}
|
|
|
|
cpu += vcpu->arch.ptid;
|
|
|
|
vcpu->cpu = mvc->pcpu;
|
|
|
|
vcpu->arch.thread_cpu = cpu;
|
KVM: PPC: Book3S HV: Invalidate TLB on radix guest vcpu movement
With radix, the guest can do TLB invalidations itself using the tlbie
(global) and tlbiel (local) TLB invalidation instructions. Linux guests
use local TLB invalidations for translations that have only ever been
accessed on one vcpu. However, that doesn't mean that the translations
have only been accessed on one physical cpu (pcpu) since vcpus can move
around from one pcpu to another. Thus a tlbiel might leave behind stale
TLB entries on a pcpu where the vcpu previously ran, and if that task
then moves back to that previous pcpu, it could see those stale TLB
entries and thus access memory incorrectly. The usual symptom of this
is random segfaults in userspace programs in the guest.
To cope with this, we detect when a vcpu is about to start executing on
a thread in a core that is a different core from the last time it
executed. If that is the case, then we mark the core as needing a
TLB flush and then send an interrupt to any thread in the core that is
currently running a vcpu from the same guest. This will get those vcpus
out of the guest, and the first one to re-enter the guest will do the
TLB flush. The reason for interrupting the vcpus executing on the old
core is to cope with the following scenario:
CPU 0 CPU 1 CPU 4
(core 0) (core 0) (core 1)
VCPU 0 runs task X VCPU 1 runs
core 0 TLB gets
entries from task X
VCPU 0 moves to CPU 4
VCPU 0 runs task X
Unmap pages of task X
tlbiel
(still VCPU 1) task X moves to VCPU 1
task X runs
task X sees stale TLB
entries
That is, as soon as the VCPU starts executing on the new core, it
could unmap and tlbiel some page table entries, and then the task
could migrate to one of the VCPUs running on the old core and
potentially see stale TLB entries.
Since the TLB is shared between all the threads in a core, we only
use the bit of kvm->arch.need_tlb_flush corresponding to the first
thread in the core. To ensure that we don't have a window where we
can miss a flush, this moves the clearing of the bit from before the
actual flush to after it. This way, two threads might both do the
flush, but we prevent the situation where one thread can enter the
guest before the flush is finished.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-30 17:21:50 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* With radix, the guest can do TLB invalidations itself,
|
|
|
|
* and it could choose to use the local form (tlbiel) if
|
|
|
|
* it is invalidating a translation that has only ever been
|
|
|
|
* used on one vcpu. However, that doesn't mean it has
|
|
|
|
* only ever been used on one physical cpu, since vcpus
|
|
|
|
* can move around between pcpus. To cope with this, when
|
|
|
|
* a vcpu moves from one pcpu to another, we need to tell
|
|
|
|
* any vcpus running on the same core as this vcpu previously
|
|
|
|
* ran to flush the TLB. The TLB is shared between threads,
|
|
|
|
* so we use a single bit in .need_tlb_flush for all 4 threads.
|
|
|
|
*/
|
|
|
|
if (kvm_is_radix(kvm) && vcpu->arch.prev_cpu != cpu) {
|
|
|
|
if (vcpu->arch.prev_cpu >= 0 &&
|
|
|
|
cpu_first_thread_sibling(vcpu->arch.prev_cpu) !=
|
|
|
|
cpu_first_thread_sibling(cpu))
|
|
|
|
radix_flush_cpu(kvm, vcpu->arch.prev_cpu, vcpu);
|
|
|
|
vcpu->arch.prev_cpu = cpu;
|
|
|
|
}
|
|
|
|
cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
tpaca = &paca[cpu];
|
2015-03-28 10:21:06 +07:00
|
|
|
tpaca->kvm_hstate.kvm_vcpu = vcpu;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
tpaca->kvm_hstate.ptid = cpu - mvc->pcpu;
|
|
|
|
/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
|
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 07:23:08 +07:00
|
|
|
smp_wmb();
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
tpaca->kvm_hstate.kvm_vcore = mvc;
|
2015-03-28 10:21:06 +07:00
|
|
|
if (cpu != smp_processor_id())
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
kvmppc_ipi_thread(cpu);
|
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 07:23:08 +07:00
|
|
|
}
|
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
|
|
|
|
2015-03-28 10:21:06 +07:00
|
|
|
static void kvmppc_wait_for_nap(void)
|
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 07:23:08 +07:00
|
|
|
{
|
2015-03-28 10:21:06 +07:00
|
|
|
int cpu = smp_processor_id();
|
|
|
|
int i, loops;
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
int n_threads = threads_per_vcore();
|
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 07:23:08 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
if (n_threads <= 1)
|
|
|
|
return;
|
2015-03-28 10:21:06 +07:00
|
|
|
for (loops = 0; loops < 1000000; ++loops) {
|
|
|
|
/*
|
|
|
|
* Check if all threads are finished.
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
* We set the vcore pointer when starting a thread
|
2015-03-28 10:21:06 +07:00
|
|
|
* and the thread clears it when finished, so we look
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
* for any threads that still have a non-NULL vcore ptr.
|
2015-03-28 10:21:06 +07:00
|
|
|
*/
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
for (i = 1; i < n_threads; ++i)
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
if (paca[cpu + i].kvm_hstate.kvm_vcore)
|
2015-03-28 10:21:06 +07:00
|
|
|
break;
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
if (i == n_threads) {
|
2015-03-28 10:21:06 +07:00
|
|
|
HMT_medium();
|
|
|
|
return;
|
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 07:23:08 +07:00
|
|
|
}
|
2015-03-28 10:21:06 +07:00
|
|
|
HMT_low();
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
HMT_medium();
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
for (i = 1; i < n_threads; ++i)
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
if (paca[cpu + i].kvm_hstate.kvm_vcore)
|
2015-03-28 10:21:06 +07:00
|
|
|
pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check that we are on thread 0 and that any other threads in
|
2012-10-15 08:16:14 +07:00
|
|
|
* this core are off-line. Then grab the threads so they can't
|
|
|
|
* enter the kernel.
|
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 07:23:08 +07:00
|
|
|
*/
|
|
|
|
static int on_primary_thread(void)
|
|
|
|
{
|
|
|
|
int cpu = smp_processor_id();
|
2014-05-23 15:15:29 +07:00
|
|
|
int thr;
|
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 07:23:08 +07:00
|
|
|
|
2014-05-23 15:15:29 +07:00
|
|
|
/* Are we on a primary subcore? */
|
|
|
|
if (cpu_thread_in_subcore(cpu))
|
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 07:23:08 +07:00
|
|
|
return 0;
|
2014-05-23 15:15:29 +07:00
|
|
|
|
|
|
|
thr = 0;
|
|
|
|
while (++thr < threads_per_subcore)
|
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 07:23:08 +07:00
|
|
|
if (cpu_online(cpu + thr))
|
|
|
|
return 0;
|
2012-10-15 08:16:14 +07:00
|
|
|
|
|
|
|
/* Grab all hw threads so they can't go into the kernel */
|
2014-05-23 15:15:29 +07:00
|
|
|
for (thr = 1; thr < threads_per_subcore; ++thr) {
|
2012-10-15 08:16:14 +07:00
|
|
|
if (kvmppc_grab_hwthread(cpu + thr)) {
|
|
|
|
/* Couldn't grab one; let the others go */
|
|
|
|
do {
|
|
|
|
kvmppc_release_hwthread(cpu + thr);
|
|
|
|
} while (--thr > 0);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
/*
|
|
|
|
* A list of virtual cores for each physical CPU.
|
|
|
|
* These are vcores that could run but their runner VCPU tasks are
|
|
|
|
* (or may be) preempted.
|
|
|
|
*/
|
|
|
|
struct preempted_vcore_list {
|
|
|
|
struct list_head list;
|
|
|
|
spinlock_t lock;
|
|
|
|
};
|
|
|
|
|
|
|
|
static DEFINE_PER_CPU(struct preempted_vcore_list, preempted_vcores);
|
|
|
|
|
|
|
|
static void init_vcore_lists(void)
|
|
|
|
{
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
struct preempted_vcore_list *lp = &per_cpu(preempted_vcores, cpu);
|
|
|
|
spin_lock_init(&lp->lock);
|
|
|
|
INIT_LIST_HEAD(&lp->list);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores);
|
|
|
|
|
|
|
|
vc->vcore_state = VCORE_PREEMPT;
|
|
|
|
vc->pcpu = smp_processor_id();
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
if (vc->num_threads < threads_per_vcore()) {
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
spin_lock(&lp->lock);
|
|
|
|
list_add_tail(&vc->preempt_list, &lp->list);
|
|
|
|
spin_unlock(&lp->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Start accumulating stolen time */
|
|
|
|
kvmppc_core_start_stolen(vc);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc)
|
|
|
|
{
|
2015-07-16 14:11:13 +07:00
|
|
|
struct preempted_vcore_list *lp;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
|
|
|
|
kvmppc_core_end_stolen(vc);
|
|
|
|
if (!list_empty(&vc->preempt_list)) {
|
2015-07-16 14:11:13 +07:00
|
|
|
lp = &per_cpu(preempted_vcores, vc->pcpu);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
spin_lock(&lp->lock);
|
|
|
|
list_del_init(&vc->preempt_list);
|
|
|
|
spin_unlock(&lp->lock);
|
|
|
|
}
|
|
|
|
vc->vcore_state = VCORE_INACTIVE;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
/*
|
|
|
|
* This stores information about the virtual cores currently
|
|
|
|
* assigned to a physical core.
|
|
|
|
*/
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
struct core_info {
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
int n_subcores;
|
|
|
|
int max_subcore_threads;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
int total_threads;
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
int subcore_threads[MAX_SUBCORES];
|
|
|
|
struct kvm *subcore_vm[MAX_SUBCORES];
|
|
|
|
struct list_head vcs[MAX_SUBCORES];
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
};
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
/*
|
|
|
|
* This mapping means subcores 0 and 1 can use threads 0-3 and 4-7
|
|
|
|
* respectively in 2-way micro-threading (split-core) mode.
|
|
|
|
*/
|
|
|
|
static int subcore_thread_map[MAX_SUBCORES] = { 0, 4, 2, 6 };
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc)
|
|
|
|
{
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
int sub;
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
memset(cip, 0, sizeof(*cip));
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
cip->n_subcores = 1;
|
|
|
|
cip->max_subcore_threads = vc->num_threads;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
cip->total_threads = vc->num_threads;
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
cip->subcore_threads[0] = vc->num_threads;
|
|
|
|
cip->subcore_vm[0] = vc->kvm;
|
|
|
|
for (sub = 0; sub < MAX_SUBCORES; ++sub)
|
|
|
|
INIT_LIST_HEAD(&cip->vcs[sub]);
|
|
|
|
list_add_tail(&vc->preempt_list, &cip->vcs[0]);
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool subcore_config_ok(int n_subcores, int n_threads)
|
|
|
|
{
|
|
|
|
/* Can only dynamically split if unsplit to begin with */
|
|
|
|
if (n_subcores > 1 && threads_per_subcore < MAX_SMT_THREADS)
|
|
|
|
return false;
|
|
|
|
if (n_subcores > MAX_SUBCORES)
|
|
|
|
return false;
|
|
|
|
if (n_subcores > 1) {
|
|
|
|
if (!(dynamic_mt_modes & 2))
|
|
|
|
n_subcores = 4;
|
|
|
|
if (n_subcores > 2 && !(dynamic_mt_modes & 4))
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
return n_subcores * roundup_pow_of_two(n_threads) <= MAX_SMT_THREADS;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static void init_master_vcore(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
vc->master_vcore = vc;
|
|
|
|
vc->entry_exit_map = 0;
|
|
|
|
vc->in_guest = 0;
|
|
|
|
vc->napping_threads = 0;
|
|
|
|
vc->conferring_threads = 0;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
|
|
|
|
{
|
|
|
|
int n_threads = vc->num_threads;
|
|
|
|
int sub;
|
|
|
|
|
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (n_threads < cip->max_subcore_threads)
|
|
|
|
n_threads = cip->max_subcore_threads;
|
2016-09-15 13:27:41 +07:00
|
|
|
if (!subcore_config_ok(cip->n_subcores + 1, n_threads))
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
return false;
|
2016-09-15 13:27:41 +07:00
|
|
|
cip->max_subcore_threads = n_threads;
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
|
|
|
|
sub = cip->n_subcores;
|
|
|
|
++cip->n_subcores;
|
|
|
|
cip->total_threads += vc->num_threads;
|
|
|
|
cip->subcore_threads[sub] = vc->num_threads;
|
|
|
|
cip->subcore_vm[sub] = vc->kvm;
|
|
|
|
init_master_vcore(vc);
|
2016-10-17 22:15:50 +07:00
|
|
|
list_move_tail(&vc->preempt_list, &cip->vcs[sub]);
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Work out whether it is possible to piggyback the execution of
|
|
|
|
* vcore *pvc onto the execution of the other vcores described in *cip.
|
|
|
|
*/
|
|
|
|
static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
|
|
|
|
int target_threads)
|
|
|
|
{
|
|
|
|
if (cip->total_threads + pvc->num_threads > target_threads)
|
|
|
|
return false;
|
|
|
|
|
2016-09-15 13:27:41 +07:00
|
|
|
return can_dynamic_split(pvc, cip);
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
}
|
|
|
|
|
2015-03-28 10:21:03 +07:00
|
|
|
static void prepare_threads(struct kvmppc_vcore *vc)
|
|
|
|
{
|
2016-08-02 11:03:20 +07:00
|
|
|
int i;
|
|
|
|
struct kvm_vcpu *vcpu;
|
2015-03-28 10:21:03 +07:00
|
|
|
|
2016-08-02 11:03:20 +07:00
|
|
|
for_each_runnable_thread(i, vcpu, vc) {
|
2015-03-28 10:21:03 +07:00
|
|
|
if (signal_pending(vcpu->arch.run_task))
|
|
|
|
vcpu->arch.ret = -EINTR;
|
|
|
|
else if (vcpu->arch.vpa.update_pending ||
|
|
|
|
vcpu->arch.slb_shadow.update_pending ||
|
|
|
|
vcpu->arch.dtl.update_pending)
|
|
|
|
vcpu->arch.ret = RESUME_GUEST;
|
|
|
|
else
|
|
|
|
continue;
|
|
|
|
kvmppc_remove_runnable(vc, vcpu);
|
|
|
|
wake_up(&vcpu->arch.cpu_run);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
static void collect_piggybacks(struct core_info *cip, int target_threads)
|
|
|
|
{
|
|
|
|
struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores);
|
|
|
|
struct kvmppc_vcore *pvc, *vcnext;
|
|
|
|
|
|
|
|
spin_lock(&lp->lock);
|
|
|
|
list_for_each_entry_safe(pvc, vcnext, &lp->list, preempt_list) {
|
|
|
|
if (!spin_trylock(&pvc->lock))
|
|
|
|
continue;
|
|
|
|
prepare_threads(pvc);
|
|
|
|
if (!pvc->n_runnable) {
|
|
|
|
list_del_init(&pvc->preempt_list);
|
|
|
|
if (pvc->runner == NULL) {
|
|
|
|
pvc->vcore_state = VCORE_INACTIVE;
|
|
|
|
kvmppc_core_end_stolen(pvc);
|
|
|
|
}
|
|
|
|
spin_unlock(&pvc->lock);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (!can_piggyback(pvc, cip, target_threads)) {
|
|
|
|
spin_unlock(&pvc->lock);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
kvmppc_core_end_stolen(pvc);
|
|
|
|
pvc->vcore_state = VCORE_PIGGYBACK;
|
|
|
|
if (cip->total_threads >= target_threads)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
spin_unlock(&lp->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
{
|
2016-08-02 11:03:20 +07:00
|
|
|
int still_running = 0, i;
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
u64 now;
|
|
|
|
long ret;
|
2016-08-02 11:03:20 +07:00
|
|
|
struct kvm_vcpu *vcpu;
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
spin_lock(&vc->lock);
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
now = get_tb();
|
2016-08-02 11:03:20 +07:00
|
|
|
for_each_runnable_thread(i, vcpu, vc) {
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
/* cancel pending dec exception if dec is positive */
|
|
|
|
if (now < vcpu->arch.dec_expires &&
|
|
|
|
kvmppc_core_pending_dec(vcpu))
|
|
|
|
kvmppc_core_dequeue_dec(vcpu);
|
|
|
|
|
|
|
|
trace_kvm_guest_exit(vcpu);
|
|
|
|
|
|
|
|
ret = RESUME_GUEST;
|
|
|
|
if (vcpu->arch.trap)
|
|
|
|
ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
|
|
|
|
vcpu->arch.run_task);
|
|
|
|
|
|
|
|
vcpu->arch.ret = ret;
|
|
|
|
vcpu->arch.trap = 0;
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (is_kvmppc_resume_guest(vcpu->arch.ret)) {
|
|
|
|
if (vcpu->arch.pending_exceptions)
|
|
|
|
kvmppc_core_prepare_to_enter(vcpu);
|
|
|
|
if (vcpu->arch.ceded)
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
kvmppc_set_timer(vcpu);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
else
|
|
|
|
++still_running;
|
|
|
|
} else {
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
kvmppc_remove_runnable(vc, vcpu);
|
|
|
|
wake_up(&vcpu->arch.cpu_run);
|
|
|
|
}
|
|
|
|
}
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
list_del_init(&vc->preempt_list);
|
|
|
|
if (!is_master) {
|
2015-07-16 14:11:14 +07:00
|
|
|
if (still_running > 0) {
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
kvmppc_vcore_preempt(vc);
|
2015-07-16 14:11:14 +07:00
|
|
|
} else if (vc->runner) {
|
|
|
|
vc->vcore_state = VCORE_PREEMPT;
|
|
|
|
kvmppc_core_start_stolen(vc);
|
|
|
|
} else {
|
|
|
|
vc->vcore_state = VCORE_INACTIVE;
|
|
|
|
}
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vc->n_runnable > 0 && vc->runner == NULL) {
|
|
|
|
/* make sure there's a candidate runner awake */
|
2016-08-02 11:03:20 +07:00
|
|
|
i = -1;
|
|
|
|
vcpu = next_runnable_thread(vc, &i);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
wake_up(&vcpu->arch.cpu_run);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
spin_unlock(&vc->lock);
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
}
|
|
|
|
|
2015-12-18 03:59:07 +07:00
|
|
|
/*
|
|
|
|
* Clear core from the list of active host cores as we are about to
|
|
|
|
* enter the guest. Only do this if it is the primary thread of the
|
|
|
|
* core (not if a subcore) that is entering the guest.
|
|
|
|
*/
|
2016-11-27 06:13:45 +07:00
|
|
|
static inline int kvmppc_clear_host_core(unsigned int cpu)
|
2015-12-18 03:59:07 +07:00
|
|
|
{
|
|
|
|
int core;
|
|
|
|
|
|
|
|
if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
|
2016-11-27 06:13:45 +07:00
|
|
|
return 0;
|
2015-12-18 03:59:07 +07:00
|
|
|
/*
|
|
|
|
* Memory barrier can be omitted here as we will do a smp_wmb()
|
|
|
|
* later in kvmppc_start_thread and we need ensure that state is
|
|
|
|
* visible to other CPUs only after we enter guest.
|
|
|
|
*/
|
|
|
|
core = cpu >> threads_shift;
|
|
|
|
kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
|
2016-11-27 06:13:45 +07:00
|
|
|
return 0;
|
2015-12-18 03:59:07 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Advertise this core as an active host core since we exited the guest
|
|
|
|
* Only need to do this if it is the primary thread of the core that is
|
|
|
|
* exiting.
|
|
|
|
*/
|
2016-11-27 06:13:45 +07:00
|
|
|
static inline int kvmppc_set_host_core(unsigned int cpu)
|
2015-12-18 03:59:07 +07:00
|
|
|
{
|
|
|
|
int core;
|
|
|
|
|
|
|
|
if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
|
2016-11-27 06:13:45 +07:00
|
|
|
return 0;
|
2015-12-18 03:59:07 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Memory barrier can be omitted here because we do a spin_unlock
|
|
|
|
* immediately after this which provides the memory barrier.
|
|
|
|
*/
|
|
|
|
core = cpu >> threads_shift;
|
|
|
|
kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
|
2016-11-27 06:13:45 +07:00
|
|
|
return 0;
|
2015-12-18 03:59:07 +07:00
|
|
|
}
|
|
|
|
|
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 07:23:08 +07:00
|
|
|
/*
|
|
|
|
* Run a set of guest threads on a physical core.
|
|
|
|
* Called with vc->lock held.
|
|
|
|
*/
|
KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:12 +07:00
|
|
|
static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
|
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 07:23:08 +07:00
|
|
|
{
|
2016-08-02 11:03:20 +07:00
|
|
|
struct kvm_vcpu *vcpu;
|
2015-03-28 10:21:03 +07:00
|
|
|
int i;
|
2012-09-11 20:27:01 +07:00
|
|
|
int srcu_idx;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
struct core_info core_info;
|
|
|
|
struct kvmppc_vcore *pvc, *vcnext;
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
struct kvm_split_mode split_info, *sip;
|
|
|
|
int split, subcore_size, active;
|
|
|
|
int sub;
|
|
|
|
bool thr0_done;
|
|
|
|
unsigned long cmd_bit, stat_bit;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
int pcpu, thr;
|
|
|
|
int target_threads;
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
int controlled_threads;
|
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 07:23:08 +07:00
|
|
|
|
2015-03-28 10:21:03 +07:00
|
|
|
/*
|
|
|
|
* Remove from the list any threads that have a signal pending
|
|
|
|
* or need a VPA update done
|
|
|
|
*/
|
|
|
|
prepare_threads(vc);
|
|
|
|
|
|
|
|
/* if the runner is no longer runnable, let the caller pick a new one */
|
|
|
|
if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
|
|
|
|
return;
|
2012-06-01 17:20:24 +07:00
|
|
|
|
|
|
|
/*
|
2015-03-28 10:21:03 +07:00
|
|
|
* Initialize *vc.
|
2012-06-01 17:20:24 +07:00
|
|
|
*/
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
init_master_vcore(vc);
|
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
Currently the calculations of stolen time for PPC Book3S HV guests
uses fields in both the vcpu struct and the kvmppc_vcore struct. The
fields in the kvmppc_vcore struct are protected by the
vcpu->arch.tbacct_lock of the vcpu that has taken responsibility for
running the virtual core. This works correctly but confuses lockdep,
because it sees that the code takes the tbacct_lock for a vcpu in
kvmppc_remove_runnable() and then takes another vcpu's tbacct_lock in
vcore_stolen_time(), and it thinks there is a possibility of deadlock,
causing it to print reports like this:
=============================================
[ INFO: possible recursive locking detected ]
3.18.0-rc7-kvm-00016-g8db4bc6 #89 Not tainted
---------------------------------------------
qemu-system-ppc/6188 is trying to acquire lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb1fe8>] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
but task is already holding lock:
(&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&vcpu->arch.tbacct_lock)->rlock);
lock(&(&vcpu->arch.tbacct_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by qemu-system-ppc/6188:
#0: (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f98>] .vcpu_load+0x28/0xe0 [kvm]
#1: (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecb41b0>] .kvmppc_vcpu_run_hv+0x530/0x1530 [kvm_hv]
#2: (&(&vcpu->arch.tbacct_lock)->rlock){......}, at: [<d00000000ecb25a0>] .kvmppc_remove_runnable.part.3+0x30/0xd0 [kvm_hv]
stack backtrace:
CPU: 40 PID: 6188 Comm: qemu-system-ppc Not tainted 3.18.0-rc7-kvm-00016-g8db4bc6 #89
Call Trace:
[c000000b2754f3f0] [c000000000b31b6c] .dump_stack+0x88/0xb4 (unreliable)
[c000000b2754f470] [c0000000000faeb8] .__lock_acquire+0x1878/0x2190
[c000000b2754f600] [c0000000000fbf0c] .lock_acquire+0xcc/0x1a0
[c000000b2754f6d0] [c000000000b2954c] ._raw_spin_lock_irq+0x4c/0x70
[c000000b2754f760] [d00000000ecb1fe8] .vcore_stolen_time+0x48/0xd0 [kvm_hv]
[c000000b2754f7f0] [d00000000ecb25b4] .kvmppc_remove_runnable.part.3+0x44/0xd0 [kvm_hv]
[c000000b2754f880] [d00000000ecb43ec] .kvmppc_vcpu_run_hv+0x76c/0x1530 [kvm_hv]
[c000000b2754f9f0] [d00000000eb9f46c] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
[c000000b2754fa60] [d00000000eb9c9a4] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
[c000000b2754faf0] [d00000000eb94538] .kvm_vcpu_ioctl+0x498/0x760 [kvm]
[c000000b2754fcb0] [c000000000267eb4] .do_vfs_ioctl+0x444/0x770
[c000000b2754fd90] [c0000000002682a4] .SyS_ioctl+0xc4/0xe0
[c000000b2754fe30] [c0000000000092e4] syscall_exit+0x0/0x98
In order to make the locking easier to analyse, we change the code to
use a spinlock in the kvmppc_vcore struct to protect the stolen_tb and
preempt_tb fields. This lock needs to be an irq-safe lock since it is
used in the kvmppc_core_vcpu_load_hv() and kvmppc_core_vcpu_put_hv()
functions, which are called with the scheduler rq lock held, which is
an irq-safe lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-12-04 12:43:28 +07:00
|
|
|
vc->preempt_tb = TB_NIL;
|
2012-06-01 17:20:24 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
/*
|
|
|
|
* Number of threads that we will be controlling: the same as
|
|
|
|
* the number of threads per subcore, except on POWER9,
|
|
|
|
* where it's 1 because the threads are (mostly) independent.
|
|
|
|
*/
|
|
|
|
controlled_threads = threads_per_vcore();
|
|
|
|
|
2012-10-15 08:16:14 +07:00
|
|
|
/*
|
2014-05-23 15:15:29 +07:00
|
|
|
* Make sure we are running on primary threads, and that secondary
|
|
|
|
* threads are offline. Also check if the number of threads in this
|
|
|
|
* guest are greater than the current system threads per guest.
|
2012-10-15 08:16:14 +07:00
|
|
|
*/
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
if ((controlled_threads > 1) &&
|
2014-05-23 15:15:29 +07:00
|
|
|
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
|
2016-08-02 11:03:20 +07:00
|
|
|
for_each_runnable_thread(i, vcpu, vc) {
|
2012-10-15 08:16:14 +07:00
|
|
|
vcpu->arch.ret = -EBUSY;
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
kvmppc_remove_runnable(vc, vcpu);
|
|
|
|
wake_up(&vcpu->arch.cpu_run);
|
|
|
|
}
|
2012-10-15 08:16:14 +07:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
/*
|
|
|
|
* See if we could run any other vcores on the physical core
|
|
|
|
* along with this one.
|
|
|
|
*/
|
|
|
|
init_core_info(&core_info, vc);
|
|
|
|
pcpu = smp_processor_id();
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
target_threads = controlled_threads;
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (target_smt_mode && target_smt_mode < target_threads)
|
|
|
|
target_threads = target_smt_mode;
|
|
|
|
if (vc->num_threads < target_threads)
|
|
|
|
collect_piggybacks(&core_info, target_threads);
|
2014-05-23 15:15:29 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
/* Decide on micro-threading (split-core) mode */
|
|
|
|
subcore_size = threads_per_subcore;
|
|
|
|
cmd_bit = stat_bit = 0;
|
|
|
|
split = core_info.n_subcores;
|
|
|
|
sip = NULL;
|
|
|
|
if (split > 1) {
|
|
|
|
/* threads_per_subcore must be MAX_SMT_THREADS (8) here */
|
|
|
|
if (split == 2 && (dynamic_mt_modes & 2)) {
|
|
|
|
cmd_bit = HID0_POWER8_1TO2LPAR;
|
|
|
|
stat_bit = HID0_POWER8_2LPARMODE;
|
|
|
|
} else {
|
|
|
|
split = 4;
|
|
|
|
cmd_bit = HID0_POWER8_1TO4LPAR;
|
|
|
|
stat_bit = HID0_POWER8_4LPARMODE;
|
|
|
|
}
|
|
|
|
subcore_size = MAX_SMT_THREADS / split;
|
|
|
|
sip = &split_info;
|
|
|
|
memset(&split_info, 0, sizeof(split_info));
|
|
|
|
split_info.rpr = mfspr(SPRN_RPR);
|
|
|
|
split_info.pmmar = mfspr(SPRN_PMMAR);
|
|
|
|
split_info.ldbar = mfspr(SPRN_LDBAR);
|
|
|
|
split_info.subcore_size = subcore_size;
|
|
|
|
for (sub = 0; sub < core_info.n_subcores; ++sub)
|
|
|
|
split_info.master_vcs[sub] =
|
|
|
|
list_first_entry(&core_info.vcs[sub],
|
|
|
|
struct kvmppc_vcore, preempt_list);
|
|
|
|
/* order writes to split_info before kvm_split_mode pointer */
|
|
|
|
smp_wmb();
|
|
|
|
}
|
|
|
|
pcpu = smp_processor_id();
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
for (thr = 0; thr < controlled_threads; ++thr)
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
|
|
|
|
|
|
|
|
/* Initiate micro-threading (split-core) if required */
|
|
|
|
if (cmd_bit) {
|
|
|
|
unsigned long hid0 = mfspr(SPRN_HID0);
|
|
|
|
|
|
|
|
hid0 |= cmd_bit | HID0_POWER8_DYNLPARDIS;
|
|
|
|
mb();
|
|
|
|
mtspr(SPRN_HID0, hid0);
|
|
|
|
isync();
|
|
|
|
for (;;) {
|
|
|
|
hid0 = mfspr(SPRN_HID0);
|
|
|
|
if (hid0 & stat_bit)
|
|
|
|
break;
|
|
|
|
cpu_relax();
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
}
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
}
|
2014-05-23 15:15:29 +07:00
|
|
|
|
2015-12-18 03:59:07 +07:00
|
|
|
kvmppc_clear_host_core(pcpu);
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
/* Start all the threads */
|
|
|
|
active = 0;
|
|
|
|
for (sub = 0; sub < core_info.n_subcores; ++sub) {
|
|
|
|
thr = subcore_thread_map[sub];
|
|
|
|
thr0_done = false;
|
|
|
|
active |= 1 << thr;
|
|
|
|
list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) {
|
|
|
|
pvc->pcpu = pcpu + thr;
|
2016-08-02 11:03:20 +07:00
|
|
|
for_each_runnable_thread(i, vcpu, pvc) {
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
kvmppc_start_thread(vcpu, pvc);
|
|
|
|
kvmppc_create_dtl_entry(vcpu, pvc);
|
|
|
|
trace_kvm_guest_enter(vcpu);
|
|
|
|
if (!vcpu->arch.ptid)
|
|
|
|
thr0_done = true;
|
|
|
|
active |= 1 << (thr + vcpu->arch.ptid);
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* We need to start the first thread of each subcore
|
|
|
|
* even if it doesn't have a vcpu.
|
|
|
|
*/
|
|
|
|
if (pvc->master_vcore == pvc && !thr0_done)
|
|
|
|
kvmppc_start_thread(NULL, pvc);
|
|
|
|
thr += pvc->num_threads;
|
|
|
|
}
|
KVM: PPC: Book3S HV: Make virtual processor area registration more robust
The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU. Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration. If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.
This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used. Each area now has a struct kvmppc_vpa which is
used to manage these updates. There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields. (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)
This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.
Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-20 00:46:32 +07:00
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
|
2015-09-02 23:18:58 +07:00
|
|
|
/*
|
|
|
|
* Ensure that split_info.do_nap is set after setting
|
|
|
|
* the vcore pointer in the PACA of the secondaries.
|
|
|
|
*/
|
|
|
|
smp_mb();
|
|
|
|
if (cmd_bit)
|
|
|
|
split_info.do_nap = 1; /* ask secondaries to nap when done */
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
/*
|
|
|
|
* When doing micro-threading, poke the inactive threads as well.
|
|
|
|
* This gets them to the nap instruction after kvm_do_nap,
|
|
|
|
* which reduces the time taken to unsplit later.
|
|
|
|
*/
|
|
|
|
if (split > 1)
|
|
|
|
for (thr = 1; thr < threads_per_subcore; ++thr)
|
|
|
|
if (!(active & (1 << thr)))
|
|
|
|
kvmppc_ipi_thread(pcpu + thr);
|
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers
On a threaded processor such as POWER7, we group VCPUs into virtual
cores and arrange that the VCPUs in a virtual core run on the same
physical core. Currently we don't enforce any correspondence between
virtual thread numbers within a virtual core and physical thread
numbers. Physical threads are allocated starting at 0 on a first-come
first-served basis to runnable virtual threads (VCPUs).
POWER8 implements a new "msgsndp" instruction which guest kernels can
use to interrupt other threads in the same core or sub-core. Since
the instruction takes the destination physical thread ID as a parameter,
it becomes necessary to align the physical thread IDs with the virtual
thread IDs, that is, to make sure virtual thread N within a virtual
core always runs on physical thread N.
This means that it's possible that thread 0, which is where we call
__kvmppc_vcore_entry, may end up running some other vcpu than the
one whose task called kvmppc_run_core(), or it may end up running
no vcpu at all, if for example thread 0 of the virtual core is
currently executing in userspace. However, we do need thread 0
to be responsible for switching the MMU -- a previous version of
this patch that had other threads switching the MMU was found to
be responsible for occasional memory corruption and machine check
interrupts in the guest on POWER7 machines.
To accommodate this, we no longer pass the vcpu pointer to
__kvmppc_vcore_entry, but instead let the assembly code load it from
the PACA. Since the assembly code will need to know the kvm pointer
and the thread ID for threads which don't have a vcpu, we move the
thread ID into the PACA and we add a kvm pointer to the virtual core
structure.
In the case where thread 0 has no vcpu to run, it still calls into
kvmppc_hv_entry in order to do the MMU switch, and then naps until
either its vcpu is ready to run in the guest, or some other thread
needs to exit the guest. In the latter case, thread 0 jumps to the
code that switches the MMU back to the host. This control flow means
that now we switch the MMU before loading any guest vcpu state.
Similarly, on guest exit we now save all the guest vcpu state before
switching the MMU back to the host. This has required substantial
code movement, making the diff rather large.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:20 +07:00
|
|
|
|
2012-10-15 08:17:17 +07:00
|
|
|
vc->vcore_state = VCORE_RUNNING;
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
preempt_disable();
|
2014-12-04 07:48:10 +07:00
|
|
|
|
|
|
|
trace_kvmppc_run_core(vc, 0);
|
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
for (sub = 0; sub < core_info.n_subcores; ++sub)
|
|
|
|
list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list)
|
|
|
|
spin_unlock(&pvc->lock);
|
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
|
|
|
|
2016-06-15 20:18:26 +07:00
|
|
|
guest_enter();
|
2012-09-11 20:27:01 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers
On a threaded processor such as POWER7, we group VCPUs into virtual
cores and arrange that the VCPUs in a virtual core run on the same
physical core. Currently we don't enforce any correspondence between
virtual thread numbers within a virtual core and physical thread
numbers. Physical threads are allocated starting at 0 on a first-come
first-served basis to runnable virtual threads (VCPUs).
POWER8 implements a new "msgsndp" instruction which guest kernels can
use to interrupt other threads in the same core or sub-core. Since
the instruction takes the destination physical thread ID as a parameter,
it becomes necessary to align the physical thread IDs with the virtual
thread IDs, that is, to make sure virtual thread N within a virtual
core always runs on physical thread N.
This means that it's possible that thread 0, which is where we call
__kvmppc_vcore_entry, may end up running some other vcpu than the
one whose task called kvmppc_run_core(), or it may end up running
no vcpu at all, if for example thread 0 of the virtual core is
currently executing in userspace. However, we do need thread 0
to be responsible for switching the MMU -- a previous version of
this patch that had other threads switching the MMU was found to
be responsible for occasional memory corruption and machine check
interrupts in the guest on POWER7 machines.
To accommodate this, we no longer pass the vcpu pointer to
__kvmppc_vcore_entry, but instead let the assembly code load it from
the PACA. Since the assembly code will need to know the kvm pointer
and the thread ID for threads which don't have a vcpu, we move the
thread ID into the PACA and we add a kvm pointer to the virtual core
structure.
In the case where thread 0 has no vcpu to run, it still calls into
kvmppc_hv_entry in order to do the MMU switch, and then naps until
either its vcpu is ready to run in the guest, or some other thread
needs to exit the guest. In the latter case, thread 0 jumps to the
code that switches the MMU back to the host. This control flow means
that now we switch the MMU before loading any guest vcpu state.
Similarly, on guest exit we now save all the guest vcpu state before
switching the MMU back to the host. This has required substantial
code movement, making the diff rather large.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:20 +07:00
|
|
|
srcu_idx = srcu_read_lock(&vc->kvm->srcu);
|
2012-09-11 20:27:01 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers
On a threaded processor such as POWER7, we group VCPUs into virtual
cores and arrange that the VCPUs in a virtual core run on the same
physical core. Currently we don't enforce any correspondence between
virtual thread numbers within a virtual core and physical thread
numbers. Physical threads are allocated starting at 0 on a first-come
first-served basis to runnable virtual threads (VCPUs).
POWER8 implements a new "msgsndp" instruction which guest kernels can
use to interrupt other threads in the same core or sub-core. Since
the instruction takes the destination physical thread ID as a parameter,
it becomes necessary to align the physical thread IDs with the virtual
thread IDs, that is, to make sure virtual thread N within a virtual
core always runs on physical thread N.
This means that it's possible that thread 0, which is where we call
__kvmppc_vcore_entry, may end up running some other vcpu than the
one whose task called kvmppc_run_core(), or it may end up running
no vcpu at all, if for example thread 0 of the virtual core is
currently executing in userspace. However, we do need thread 0
to be responsible for switching the MMU -- a previous version of
this patch that had other threads switching the MMU was found to
be responsible for occasional memory corruption and machine check
interrupts in the guest on POWER7 machines.
To accommodate this, we no longer pass the vcpu pointer to
__kvmppc_vcore_entry, but instead let the assembly code load it from
the PACA. Since the assembly code will need to know the kvm pointer
and the thread ID for threads which don't have a vcpu, we move the
thread ID into the PACA and we add a kvm pointer to the virtual core
structure.
In the case where thread 0 has no vcpu to run, it still calls into
kvmppc_hv_entry in order to do the MMU switch, and then naps until
either its vcpu is ready to run in the guest, or some other thread
needs to exit the guest. In the latter case, thread 0 jumps to the
code that switches the MMU back to the host. This control flow means
that now we switch the MMU before loading any guest vcpu state.
Similarly, on guest exit we now save all the guest vcpu state before
switching the MMU back to the host. This has required substantial
code movement, making the diff rather large.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 17:25:20 +07:00
|
|
|
__kvmppc_vcore_entry();
|
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
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
|
|
|
|
|
|
|
|
spin_lock(&vc->lock);
|
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 07:23:08 +07:00
|
|
|
/* prevent other vcpu threads from doing kvmppc_start_thread() now */
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vc->vcore_state = VCORE_EXITING;
|
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 07:23:08 +07:00
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
/* wait for secondary threads to finish writing their state to memory */
|
2015-03-28 10:21:06 +07:00
|
|
|
kvmppc_wait_for_nap();
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
|
|
|
|
/* Return to whole-core mode if we split the core earlier */
|
|
|
|
if (split > 1) {
|
|
|
|
unsigned long hid0 = mfspr(SPRN_HID0);
|
|
|
|
unsigned long loops = 0;
|
|
|
|
|
|
|
|
hid0 &= ~HID0_POWER8_DYNLPARDIS;
|
|
|
|
stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
|
|
|
|
mb();
|
|
|
|
mtspr(SPRN_HID0, hid0);
|
|
|
|
isync();
|
|
|
|
for (;;) {
|
|
|
|
hid0 = mfspr(SPRN_HID0);
|
|
|
|
if (!(hid0 & stat_bit))
|
|
|
|
break;
|
|
|
|
cpu_relax();
|
|
|
|
++loops;
|
|
|
|
}
|
|
|
|
split_info.do_nap = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Let secondaries go back to the offline loop */
|
KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 13:43:30 +07:00
|
|
|
for (i = 0; i < controlled_threads; ++i) {
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
kvmppc_release_hwthread(pcpu + i);
|
|
|
|
if (sip && sip->napped[i])
|
|
|
|
kvmppc_ipi_thread(pcpu + i);
|
KVM: PPC: Book3S HV: Invalidate TLB on radix guest vcpu movement
With radix, the guest can do TLB invalidations itself using the tlbie
(global) and tlbiel (local) TLB invalidation instructions. Linux guests
use local TLB invalidations for translations that have only ever been
accessed on one vcpu. However, that doesn't mean that the translations
have only been accessed on one physical cpu (pcpu) since vcpus can move
around from one pcpu to another. Thus a tlbiel might leave behind stale
TLB entries on a pcpu where the vcpu previously ran, and if that task
then moves back to that previous pcpu, it could see those stale TLB
entries and thus access memory incorrectly. The usual symptom of this
is random segfaults in userspace programs in the guest.
To cope with this, we detect when a vcpu is about to start executing on
a thread in a core that is a different core from the last time it
executed. If that is the case, then we mark the core as needing a
TLB flush and then send an interrupt to any thread in the core that is
currently running a vcpu from the same guest. This will get those vcpus
out of the guest, and the first one to re-enter the guest will do the
TLB flush. The reason for interrupting the vcpus executing on the old
core is to cope with the following scenario:
CPU 0 CPU 1 CPU 4
(core 0) (core 0) (core 1)
VCPU 0 runs task X VCPU 1 runs
core 0 TLB gets
entries from task X
VCPU 0 moves to CPU 4
VCPU 0 runs task X
Unmap pages of task X
tlbiel
(still VCPU 1) task X moves to VCPU 1
task X runs
task X sees stale TLB
entries
That is, as soon as the VCPU starts executing on the new core, it
could unmap and tlbiel some page table entries, and then the task
could migrate to one of the VCPUs running on the old core and
potentially see stale TLB entries.
Since the TLB is shared between all the threads in a core, we only
use the bit of kvm->arch.need_tlb_flush corresponding to the first
thread in the core. To ensure that we don't have a window where we
can miss a flush, this moves the clearing of the bit from before the
actual flush to after it. This way, two threads might both do the
flush, but we prevent the situation where one thread can enter the
guest before the flush is finished.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-30 17:21:50 +07:00
|
|
|
cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest);
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
}
|
|
|
|
|
2015-12-18 03:59:07 +07:00
|
|
|
kvmppc_set_host_core(pcpu);
|
|
|
|
|
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 07:23:08 +07:00
|
|
|
spin_unlock(&vc->lock);
|
2012-09-11 20:27:01 +07:00
|
|
|
|
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 07:23:08 +07:00
|
|
|
/* make sure updates to secondary vcpu structs are visible now */
|
|
|
|
smp_mb();
|
2016-06-15 20:18:26 +07:00
|
|
|
guest_exit();
|
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
|
|
|
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
for (sub = 0; sub < core_info.n_subcores; ++sub)
|
|
|
|
list_for_each_entry_safe(pvc, vcnext, &core_info.vcs[sub],
|
|
|
|
preempt_list)
|
|
|
|
post_guest_process(pvc, pvc == vc);
|
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
|
|
|
|
2012-10-15 08:16:48 +07:00
|
|
|
spin_lock(&vc->lock);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
preempt_enable();
|
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
|
|
|
|
|
|
|
out:
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vc->vcore_state = VCORE_INACTIVE;
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvmppc_run_core(vc, 1);
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
/*
|
|
|
|
* Wait for some other vcpu thread to execute us, and
|
|
|
|
* wake us up when we need to handle something in the host.
|
|
|
|
*/
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc,
|
|
|
|
struct kvm_vcpu *vcpu, int wait_state)
|
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 07:23:08 +07:00
|
|
|
{
|
|
|
|
DEFINE_WAIT(wait);
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
|
|
|
|
spin_unlock(&vc->lock);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
schedule();
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
spin_lock(&vc->lock);
|
|
|
|
}
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
finish_wait(&vcpu->arch.cpu_run, &wait);
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
static void grow_halt_poll_ns(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
/* 10us base */
|
|
|
|
if (vc->halt_poll_ns == 0 && halt_poll_ns_grow)
|
|
|
|
vc->halt_poll_ns = 10000;
|
|
|
|
else
|
|
|
|
vc->halt_poll_ns *= halt_poll_ns_grow;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void shrink_halt_poll_ns(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
if (halt_poll_ns_shrink == 0)
|
|
|
|
vc->halt_poll_ns = 0;
|
|
|
|
else
|
|
|
|
vc->halt_poll_ns /= halt_poll_ns_shrink;
|
|
|
|
}
|
|
|
|
|
2016-10-14 07:53:23 +07:00
|
|
|
/*
|
|
|
|
* Check to see if any of the runnable vcpus on the vcore have pending
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
* exceptions or are no longer ceded
|
|
|
|
*/
|
|
|
|
static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc)
|
|
|
|
{
|
|
|
|
struct kvm_vcpu *vcpu;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_runnable_thread(i, vcpu, vc) {
|
2016-12-06 16:42:05 +07:00
|
|
|
if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded ||
|
|
|
|
vcpu->arch.prodded)
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
/*
|
|
|
|
* All the vcpus in this vcore are idle, so wait for a decrementer
|
|
|
|
* or external interrupt to one of the vcpus. vc->lock is held.
|
|
|
|
*/
|
|
|
|
static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
|
|
|
|
{
|
2016-08-02 11:03:23 +07:00
|
|
|
ktime_t cur, start_poll, start_wait;
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
int do_sleep = 1;
|
|
|
|
u64 block_ns;
|
2016-02-19 15:46:39 +07:00
|
|
|
DECLARE_SWAITQUEUE(wait);
|
2014-11-03 11:52:00 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
/* Poll for pending exceptions and ceded state */
|
2016-08-02 11:03:23 +07:00
|
|
|
cur = start_poll = ktime_get();
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
if (vc->halt_poll_ns) {
|
2016-08-02 11:03:23 +07:00
|
|
|
ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns);
|
|
|
|
++vc->runner->stat.halt_attempted_poll;
|
2014-11-03 11:52:00 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
vc->vcore_state = VCORE_POLLING;
|
|
|
|
spin_unlock(&vc->lock);
|
|
|
|
|
|
|
|
do {
|
|
|
|
if (kvmppc_vcore_check_block(vc)) {
|
|
|
|
do_sleep = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
cur = ktime_get();
|
|
|
|
} while (single_task_running() && ktime_before(cur, stop));
|
|
|
|
|
|
|
|
spin_lock(&vc->lock);
|
|
|
|
vc->vcore_state = VCORE_INACTIVE;
|
|
|
|
|
2016-08-02 11:03:23 +07:00
|
|
|
if (!do_sleep) {
|
|
|
|
++vc->runner->stat.halt_successful_poll;
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
goto out;
|
2016-08-02 11:03:23 +07:00
|
|
|
}
|
2014-11-03 11:52:00 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
|
|
|
|
|
|
|
|
if (kvmppc_vcore_check_block(vc)) {
|
2016-02-19 15:46:39 +07:00
|
|
|
finish_swait(&vc->wq, &wait);
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
do_sleep = 0;
|
2016-08-02 11:03:23 +07:00
|
|
|
/* If we polled, count this as a successful poll */
|
|
|
|
if (vc->halt_poll_ns)
|
|
|
|
++vc->runner->stat.halt_successful_poll;
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
goto out;
|
2014-11-03 11:52:00 +07:00
|
|
|
}
|
|
|
|
|
2016-08-02 11:03:23 +07:00
|
|
|
start_wait = ktime_get();
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vc->vcore_state = VCORE_SLEEPING;
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvmppc_vcore_blocked(vc, 0);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
spin_unlock(&vc->lock);
|
2012-10-15 08:16:48 +07:00
|
|
|
schedule();
|
2016-02-19 15:46:39 +07:00
|
|
|
finish_swait(&vc->wq, &wait);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
spin_lock(&vc->lock);
|
|
|
|
vc->vcore_state = VCORE_INACTIVE;
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvmppc_vcore_blocked(vc, 1);
|
2016-08-02 11:03:23 +07:00
|
|
|
++vc->runner->stat.halt_successful_wait;
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
|
|
|
|
cur = ktime_get();
|
|
|
|
|
|
|
|
out:
|
2016-08-02 11:03:23 +07:00
|
|
|
block_ns = ktime_to_ns(cur) - ktime_to_ns(start_poll);
|
|
|
|
|
|
|
|
/* Attribute wait time */
|
|
|
|
if (do_sleep) {
|
|
|
|
vc->runner->stat.halt_wait_ns +=
|
|
|
|
ktime_to_ns(cur) - ktime_to_ns(start_wait);
|
|
|
|
/* Attribute failed poll time */
|
|
|
|
if (vc->halt_poll_ns)
|
|
|
|
vc->runner->stat.halt_poll_fail_ns +=
|
|
|
|
ktime_to_ns(start_wait) -
|
|
|
|
ktime_to_ns(start_poll);
|
|
|
|
} else {
|
|
|
|
/* Attribute successful poll time */
|
|
|
|
if (vc->halt_poll_ns)
|
|
|
|
vc->runner->stat.halt_poll_success_ns +=
|
|
|
|
ktime_to_ns(cur) -
|
|
|
|
ktime_to_ns(start_poll);
|
|
|
|
}
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
|
|
|
|
/* Adjust poll time */
|
2016-10-14 07:53:20 +07:00
|
|
|
if (halt_poll_ns) {
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
if (block_ns <= vc->halt_poll_ns)
|
|
|
|
;
|
|
|
|
/* We slept and blocked for longer than the max halt time */
|
2016-10-14 07:53:20 +07:00
|
|
|
else if (vc->halt_poll_ns && block_ns > halt_poll_ns)
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
shrink_halt_poll_ns(vc);
|
|
|
|
/* We slept and our poll time is too small */
|
2016-10-14 07:53:20 +07:00
|
|
|
else if (vc->halt_poll_ns < halt_poll_ns &&
|
|
|
|
block_ns < halt_poll_ns)
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
grow_halt_poll_ns(vc);
|
2016-10-14 07:53:21 +07:00
|
|
|
if (vc->halt_poll_ns > halt_poll_ns)
|
|
|
|
vc->halt_poll_ns = halt_poll_ns;
|
KVM: PPC: Book3S HV: Implement halt polling
This patch introduces new halt polling functionality into the kvm_hv kernel
module. When a vcore is idle it will poll for some period of time before
scheduling itself out.
When all of the runnable vcpus on a vcore have ceded (and thus the vcore is
idle) we schedule ourselves out to allow something else to run. In the
event that we need to wake up very quickly (for example an interrupt
arrives), we are required to wait until we get scheduled again.
Implement halt polling so that when a vcore is idle, and before scheduling
ourselves, we poll for vcpus in the runnable_threads list which have
pending exceptions or which leave the ceded state. If we poll successfully
then we can get back into the guest very quickly without ever scheduling
ourselves, otherwise we schedule ourselves out as before.
There exists generic halt_polling code in virt/kvm_main.c, however on
powerpc the polling conditions are different to the generic case. It would
be nice if we could just implement an arch specific kvm_check_block()
function, but there is still other arch specific things which need to be
done for kvm_hv (for example manipulating vcore states) which means that a
separate implementation is the best option.
Testing of this patch with a TCP round robin test between two guests with
virtio network interfaces has found a decrease in round trip time of ~15us
on average. A performance gain is only seen when going out of and
back into the guest often and quickly, otherwise there is no net benefit
from the polling. The polling interval is adjusted such that when we are
often scheduled out for long periods of time it is reduced, and when we
often poll successfully it is increased. The rate at which the polling
interval increases or decreases, and the maximum polling interval, can
be set through module parameters.
Based on the implementation in the generic kvm module by Wanpeng Li and
Paolo Bonzini, and on direction from Paul Mackerras.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-02 11:03:21 +07:00
|
|
|
} else
|
|
|
|
vc->halt_poll_ns = 0;
|
|
|
|
|
|
|
|
trace_kvmppc_vcore_wakeup(do_sleep, block_ns);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
|
|
|
|
{
|
2016-08-02 11:03:20 +07:00
|
|
|
int n_ceded, i;
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
struct kvmppc_vcore *vc;
|
2016-08-02 11:03:20 +07:00
|
|
|
struct kvm_vcpu *v;
|
KVM: PPC: book3s_hv: Add support for PPC970-family processors
This adds support for running KVM guests in supervisor mode on those
PPC970 processors that have a usable hypervisor mode. Unfortunately,
Apple G5 machines have supervisor mode disabled (MSR[HV] is forced to
1), but the YDL PowerStation does have a usable hypervisor mode.
There are several differences between the PPC970 and POWER7 in how
guests are managed. These differences are accommodated using the
CPU_FTR_ARCH_201 (PPC970) and CPU_FTR_ARCH_206 (POWER7) CPU feature
bits. Notably, on PPC970:
* The LPCR, LPID or RMOR registers don't exist, and the functions of
those registers are provided by bits in HID4 and one bit in HID0.
* External interrupts can be directed to the hypervisor, but unlike
POWER7 they are masked by MSR[EE] in non-hypervisor modes and use
SRR0/1 not HSRR0/1.
* There is no virtual RMA (VRMA) mode; the guest must use an RMO
(real mode offset) area.
* The TLB entries are not tagged with the LPID, so it is necessary to
flush the whole TLB on partition switch. Furthermore, when switching
partitions we have to ensure that no other CPU is executing the tlbie
or tlbsync instructions in either the old or the new partition,
otherwise undefined behaviour can occur.
* The PMU has 8 counters (PMC registers) rather than 6.
* The DSCR, PURR, SPURR, AMR, AMOR, UAMOR registers don't exist.
* The SLB has 64 entries rather than 32.
* There is no mediated external interrupt facility, so if we switch to
a guest that has a virtual external interrupt pending but the guest
has MSR[EE] = 0, we have to arrange to have an interrupt pending for
it so that we can get control back once it re-enables interrupts. We
do that by sending ourselves an IPI with smp_send_reschedule after
hard-disabling interrupts.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:40:08 +07:00
|
|
|
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvmppc_run_vcpu_enter(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 07:23:08 +07:00
|
|
|
kvm_run->exit_reason = 0;
|
|
|
|
vcpu->arch.ret = RESUME_GUEST;
|
|
|
|
vcpu->arch.trap = 0;
|
2012-10-15 08:17:17 +07:00
|
|
|
kvmppc_update_vpas(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 07:23:08 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Synchronize with other threads in this virtual core
|
|
|
|
*/
|
|
|
|
vc = vcpu->arch.vcore;
|
|
|
|
spin_lock(&vc->lock);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vcpu->arch.ceded = 0;
|
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 07:23:08 +07:00
|
|
|
vcpu->arch.run_task = current;
|
|
|
|
vcpu->arch.kvm_run = kvm_run;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
vcpu->arch.busy_preempt = TB_NIL;
|
2016-08-02 11:03:20 +07:00
|
|
|
WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], 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 07:23:08 +07:00
|
|
|
++vc->n_runnable;
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
/*
|
|
|
|
* This happens the first time this is called for a vcpu.
|
|
|
|
* If the vcore is already running, we may be able to start
|
|
|
|
* this thread straight away and have it join in.
|
|
|
|
*/
|
2012-10-15 08:17:42 +07:00
|
|
|
if (!signal_pending(current)) {
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vc->vcore_state == VCORE_PIGGYBACK) {
|
|
|
|
struct kvmppc_vcore *mvc = vc->master_vcore;
|
|
|
|
if (spin_trylock(&mvc->lock)) {
|
|
|
|
if (mvc->vcore_state == VCORE_RUNNING &&
|
|
|
|
!VCORE_IS_EXITING(mvc)) {
|
|
|
|
kvmppc_create_dtl_entry(vcpu, vc);
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
kvmppc_start_thread(vcpu, vc);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
trace_kvm_guest_enter(vcpu);
|
|
|
|
}
|
|
|
|
spin_unlock(&mvc->lock);
|
|
|
|
}
|
|
|
|
} else if (vc->vcore_state == VCORE_RUNNING &&
|
|
|
|
!VCORE_IS_EXITING(vc)) {
|
2012-10-15 08:17:17 +07:00
|
|
|
kvmppc_create_dtl_entry(vcpu, vc);
|
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 17:38:16 +07:00
|
|
|
kvmppc_start_thread(vcpu, vc);
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvm_guest_enter(vcpu);
|
2012-10-15 08:17:42 +07:00
|
|
|
} else if (vc->vcore_state == VCORE_SLEEPING) {
|
2016-02-19 15:46:39 +07:00
|
|
|
swake_up(&vc->wq);
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
2012-10-15 08:17:42 +07:00
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
|
|
|
|
!signal_pending(current)) {
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
|
|
|
|
kvmppc_vcore_end_preempt(vc);
|
|
|
|
|
2012-10-15 08:17:42 +07:00
|
|
|
if (vc->vcore_state != VCORE_INACTIVE) {
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
kvmppc_wait_for_exec(vc, vcpu, TASK_INTERRUPTIBLE);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
continue;
|
|
|
|
}
|
2016-08-02 11:03:20 +07:00
|
|
|
for_each_runnable_thread(i, v, vc) {
|
2011-11-09 07:23:20 +07:00
|
|
|
kvmppc_core_prepare_to_enter(v);
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
if (signal_pending(v->arch.run_task)) {
|
|
|
|
kvmppc_remove_runnable(vc, v);
|
|
|
|
v->stat.signal_exits++;
|
|
|
|
v->arch.kvm_run->exit_reason = KVM_EXIT_INTR;
|
|
|
|
v->arch.ret = -EINTR;
|
|
|
|
wake_up(&v->arch.cpu_run);
|
|
|
|
}
|
|
|
|
}
|
2012-10-15 08:17:42 +07:00
|
|
|
if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
|
|
|
|
break;
|
|
|
|
n_ceded = 0;
|
2016-08-02 11:03:20 +07:00
|
|
|
for_each_runnable_thread(i, v, vc) {
|
2016-12-06 16:42:05 +07:00
|
|
|
if (!v->arch.pending_exceptions && !v->arch.prodded)
|
2012-10-15 08:17:42 +07:00
|
|
|
n_ceded += v->arch.ceded;
|
2013-04-18 03:31:41 +07:00
|
|
|
else
|
|
|
|
v->arch.ceded = 0;
|
|
|
|
}
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
vc->runner = vcpu;
|
|
|
|
if (n_ceded == vc->n_runnable) {
|
2012-10-15 08:17:42 +07:00
|
|
|
kvmppc_vcore_blocked(vc);
|
2015-07-15 16:52:03 +07:00
|
|
|
} else if (need_resched()) {
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
kvmppc_vcore_preempt(vc);
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
/* Let something else run */
|
|
|
|
cond_resched_lock(&vc->lock);
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
if (vc->vcore_state == VCORE_PREEMPT)
|
|
|
|
kvmppc_vcore_end_preempt(vc);
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
} else {
|
2012-10-15 08:17:42 +07:00
|
|
|
kvmppc_run_core(vc);
|
KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 10:21:05 +07:00
|
|
|
}
|
2012-02-03 07:56:21 +07:00
|
|
|
vc->runner = NULL;
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
}
|
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 07:23:08 +07:00
|
|
|
|
2012-10-15 08:17:42 +07:00
|
|
|
while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
|
|
|
|
(vc->vcore_state == VCORE_RUNNING ||
|
2015-09-18 10:13:44 +07:00
|
|
|
vc->vcore_state == VCORE_EXITING ||
|
|
|
|
vc->vcore_state == VCORE_PIGGYBACK))
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
kvmppc_wait_for_exec(vc, vcpu, TASK_UNINTERRUPTIBLE);
|
2012-10-15 08:17:42 +07:00
|
|
|
|
2015-09-18 10:13:44 +07:00
|
|
|
if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
|
|
|
|
kvmppc_vcore_end_preempt(vc);
|
|
|
|
|
2012-10-15 08:17:42 +07:00
|
|
|
if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
|
|
|
|
kvmppc_remove_runnable(vc, vcpu);
|
|
|
|
vcpu->stat.signal_exits++;
|
|
|
|
kvm_run->exit_reason = KVM_EXIT_INTR;
|
|
|
|
vcpu->arch.ret = -EINTR;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
|
|
|
|
/* Wake up some vcpu to run the core */
|
2016-08-02 11:03:20 +07:00
|
|
|
i = -1;
|
|
|
|
v = next_runnable_thread(vc, &i);
|
2012-10-15 08:17:42 +07:00
|
|
|
wake_up(&v->arch.cpu_run);
|
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 07:23:08 +07:00
|
|
|
}
|
|
|
|
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvmppc_run_vcpu_exit(vcpu, kvm_run);
|
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 07:23:08 +07:00
|
|
|
spin_unlock(&vc->lock);
|
|
|
|
return vcpu->arch.ret;
|
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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
|
2011-06-29 07:22:05 +07:00
|
|
|
{
|
|
|
|
int r;
|
2012-10-15 08:16:48 +07:00
|
|
|
int srcu_idx;
|
2011-06-29 07:22:05 +07:00
|
|
|
|
2011-08-10 18:57:08 +07:00
|
|
|
if (!vcpu->arch.sane) {
|
|
|
|
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2011-11-09 07:23:23 +07:00
|
|
|
kvmppc_core_prepare_to_enter(vcpu);
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
/* No need to go into the guest when all we'll do is come back out */
|
|
|
|
if (signal_pending(current)) {
|
|
|
|
run->exit_reason = KVM_EXIT_INTR;
|
|
|
|
return -EINTR;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
atomic_inc(&vcpu->kvm->arch.vcpus_running);
|
2015-03-20 16:39:42 +07:00
|
|
|
/* Order vcpus_running vs. hpte_setup_done, see kvmppc_alloc_reset_hpt */
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
smp_mb();
|
|
|
|
|
2014-12-03 09:30:38 +07:00
|
|
|
/* On the first time here, set up HTAB and VRMA */
|
2017-01-30 17:21:53 +07:00
|
|
|
if (!kvm_is_radix(vcpu->kvm) && !vcpu->kvm->arch.hpte_setup_done) {
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
r = kvmppc_hv_setup_htab_rma(vcpu);
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
if (r)
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
goto out;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
}
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
|
2015-10-29 07:44:09 +07:00
|
|
|
flush_all_to_thread(current);
|
|
|
|
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
vcpu->arch.wqp = &vcpu->arch.vcore->wq;
|
KVM: PPC: Implement MMU notifiers for Book3S HV guests
This adds the infrastructure to enable us to page out pages underneath
a Book3S HV guest, on processors that support virtualized partition
memory, that is, POWER7. Instead of pinning all the guest's pages,
we now look in the host userspace Linux page tables to find the
mapping for a given guest page. Then, if the userspace Linux PTE
gets invalidated, kvm_unmap_hva() gets called for that address, and
we replace all the guest HPTEs that refer to that page with absent
HPTEs, i.e. ones with the valid bit clear and the HPTE_V_ABSENT bit
set, which will cause an HDSI when the guest tries to access them.
Finally, the page fault handler is extended to reinstantiate the
guest HPTE when the guest tries to access a page which has been paged
out.
Since we can't intercept the guest DSI and ISI interrupts on PPC970,
we still have to pin all the guest pages on PPC970. We have a new flag,
kvm->arch.using_mmu_notifiers, that indicates whether we can page
guest pages out. If it is not set, the MMU notifier callbacks do
nothing and everything operates as before.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:38:05 +07:00
|
|
|
vcpu->arch.pgdir = current->mm->pgd;
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
|
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel. This is inefficient.
This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode. When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle. Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction. When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.
This has some other ramifications. First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle. This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running. In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.
This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.
Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.
Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.
Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 14:42:46 +07:00
|
|
|
|
2011-06-29 07:22:05 +07:00
|
|
|
do {
|
|
|
|
r = kvmppc_run_vcpu(run, vcpu);
|
|
|
|
|
|
|
|
if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
|
|
|
|
!(vcpu->arch.shregs.msr & MSR_PR)) {
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvm_hcall_enter(vcpu);
|
2011-06-29 07:22:05 +07:00
|
|
|
r = kvmppc_pseries_do_hcall(vcpu);
|
2014-12-04 07:48:10 +07:00
|
|
|
trace_kvm_hcall_exit(vcpu, r);
|
2011-11-09 07:23:20 +07:00
|
|
|
kvmppc_core_prepare_to_enter(vcpu);
|
2012-10-15 08:16:48 +07:00
|
|
|
} else if (r == RESUME_PAGE_FAULT) {
|
|
|
|
srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
|
|
|
|
r = kvmppc_book3s_hv_page_fault(run, vcpu,
|
|
|
|
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
|
|
|
|
srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
|
2016-08-19 12:35:52 +07:00
|
|
|
} else if (r == RESUME_PASSTHROUGH)
|
|
|
|
r = kvmppc_xics_rm_complete(vcpu, 0);
|
2014-02-06 23:36:56 +07:00
|
|
|
} while (is_kvmppc_resume_guest(r));
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
|
|
|
|
out:
|
KVM: PPC: Book3S HV: Fix accounting of stolen time
Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.
In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis. Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.
To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state. Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock. This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.
Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped. Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-10-15 08:18:07 +07:00
|
|
|
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
atomic_dec(&vcpu->kvm->arch.vcpus_running);
|
2011-06-29 07:22:05 +07:00
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2012-04-27 02:43:42 +07:00
|
|
|
static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
|
|
|
|
int linux_psize)
|
|
|
|
{
|
|
|
|
struct mmu_psize_def *def = &mmu_psize_defs[linux_psize];
|
|
|
|
|
|
|
|
if (!def->shift)
|
|
|
|
return;
|
|
|
|
(*sps)->page_shift = def->shift;
|
|
|
|
(*sps)->slb_enc = def->sllp;
|
|
|
|
(*sps)->enc[0].page_shift = def->shift;
|
2013-04-28 16:37:35 +07:00
|
|
|
(*sps)->enc[0].pte_enc = def->penc[linux_psize];
|
KVM: PPC: BOOK3S: HV: Add mixed page-size support for guest
On recent IBM Power CPUs, while the hashed page table is looked up using
the page size from the segmentation hardware (i.e. the SLB), it is
possible to have the HPT entry indicate a larger page size. Thus for
example it is possible to put a 16MB page in a 64kB segment, but since
the hash lookup is done using a 64kB page size, it may be necessary to
put multiple entries in the HPT for a single 16MB page. This
capability is called mixed page-size segment (MPSS). With MPSS,
there are two relevant page sizes: the base page size, which is the
size used in searching the HPT, and the actual page size, which is the
size indicated in the HPT entry. [ Note that the actual page size is
always >= base page size ].
We use "ibm,segment-page-sizes" device tree node to advertise
the MPSS support to PAPR guest. The penc encoding indicates whether
we support a specific combination of base page size and actual
page size in the same segment. We also use the penc value in the
LP encoding of HPTE entry.
This patch exposes MPSS support to KVM guest by advertising the
feature via "ibm,segment-page-sizes". It also adds the necessary changes
to decode the base page size and the actual page size correctly from the
HPTE entry.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
2014-05-07 01:01:36 +07:00
|
|
|
/*
|
|
|
|
* Add 16MB MPSS support if host supports it
|
|
|
|
*/
|
|
|
|
if (linux_psize != MMU_PAGE_16M && def->penc[MMU_PAGE_16M] != -1) {
|
|
|
|
(*sps)->enc[1].page_shift = 24;
|
|
|
|
(*sps)->enc[1].pte_enc = def->penc[MMU_PAGE_16M];
|
|
|
|
}
|
2012-04-27 02:43:42 +07:00
|
|
|
(*sps)++;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
|
|
|
|
struct kvm_ppc_smmu_info *info)
|
2012-04-27 02:43:42 +07:00
|
|
|
{
|
|
|
|
struct kvm_ppc_one_seg_page_size *sps;
|
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
/*
|
|
|
|
* Since we don't yet support HPT guests on a radix host,
|
|
|
|
* return an error if the host uses radix.
|
|
|
|
*/
|
|
|
|
if (radix_enabled())
|
|
|
|
return -EINVAL;
|
|
|
|
|
2012-04-27 02:43:42 +07:00
|
|
|
info->flags = KVM_PPC_PAGE_SIZES_REAL;
|
|
|
|
if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
|
|
|
|
info->flags |= KVM_PPC_1T_SEGMENTS;
|
|
|
|
info->slb_size = mmu_slb_size;
|
|
|
|
|
|
|
|
/* We only support these sizes for now, and no muti-size segments */
|
|
|
|
sps = &info->sps[0];
|
|
|
|
kvmppc_add_seg_page_size(&sps, MMU_PAGE_4K);
|
|
|
|
kvmppc_add_seg_page_size(&sps, MMU_PAGE_64K);
|
|
|
|
kvmppc_add_seg_page_size(&sps, MMU_PAGE_16M);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-12-15 09:03:22 +07:00
|
|
|
/*
|
|
|
|
* Get (and clear) the dirty memory log for a memory slot.
|
|
|
|
*/
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
|
|
|
|
struct kvm_dirty_log *log)
|
2011-12-15 09:03:22 +07:00
|
|
|
{
|
2015-05-17 21:20:07 +07:00
|
|
|
struct kvm_memslots *slots;
|
2011-12-15 09:03:22 +07:00
|
|
|
struct kvm_memory_slot *memslot;
|
2017-01-30 17:21:48 +07:00
|
|
|
int i, r;
|
2011-12-15 09:03:22 +07:00
|
|
|
unsigned long n;
|
2017-01-30 17:21:48 +07:00
|
|
|
unsigned long *buf;
|
|
|
|
struct kvm_vcpu *vcpu;
|
2011-12-15 09:03:22 +07:00
|
|
|
|
|
|
|
mutex_lock(&kvm->slots_lock);
|
|
|
|
|
|
|
|
r = -EINVAL;
|
2012-12-11 00:33:09 +07:00
|
|
|
if (log->slot >= KVM_USER_MEM_SLOTS)
|
2011-12-15 09:03:22 +07:00
|
|
|
goto out;
|
|
|
|
|
2015-05-17 21:20:07 +07:00
|
|
|
slots = kvm_memslots(kvm);
|
|
|
|
memslot = id_to_memslot(slots, log->slot);
|
2011-12-15 09:03:22 +07:00
|
|
|
r = -ENOENT;
|
|
|
|
if (!memslot->dirty_bitmap)
|
|
|
|
goto out;
|
|
|
|
|
2017-01-30 17:21:48 +07:00
|
|
|
/*
|
|
|
|
* Use second half of bitmap area because radix accumulates
|
|
|
|
* bits in the first half.
|
|
|
|
*/
|
2011-12-15 09:03:22 +07:00
|
|
|
n = kvm_dirty_bitmap_bytes(memslot);
|
2017-01-30 17:21:48 +07:00
|
|
|
buf = memslot->dirty_bitmap + n / sizeof(long);
|
|
|
|
memset(buf, 0, n);
|
2011-12-15 09:03:22 +07:00
|
|
|
|
2017-01-30 17:21:48 +07:00
|
|
|
if (kvm_is_radix(kvm))
|
|
|
|
r = kvmppc_hv_get_dirty_log_radix(kvm, memslot, buf);
|
|
|
|
else
|
|
|
|
r = kvmppc_hv_get_dirty_log_hpt(kvm, memslot, buf);
|
2011-12-15 09:03:22 +07:00
|
|
|
if (r)
|
|
|
|
goto out;
|
|
|
|
|
2017-01-30 17:21:48 +07:00
|
|
|
/* Harvest dirty bits from VPA and DTL updates */
|
|
|
|
/* Note: we never modify the SLB shadow buffer areas */
|
|
|
|
kvm_for_each_vcpu(i, vcpu, kvm) {
|
|
|
|
spin_lock(&vcpu->arch.vpa_update_lock);
|
|
|
|
kvmppc_harvest_vpa_dirty(&vcpu->arch.vpa, memslot, buf);
|
|
|
|
kvmppc_harvest_vpa_dirty(&vcpu->arch.dtl, memslot, buf);
|
|
|
|
spin_unlock(&vcpu->arch.vpa_update_lock);
|
|
|
|
}
|
|
|
|
|
2011-12-15 09:03:22 +07:00
|
|
|
r = -EFAULT;
|
2017-01-30 17:21:48 +07:00
|
|
|
if (copy_to_user(log->dirty_bitmap, buf, n))
|
2011-12-15 09:03:22 +07:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
r = 0;
|
|
|
|
out:
|
|
|
|
mutex_unlock(&kvm->slots_lock);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
|
|
|
|
struct kvm_memory_slot *dont)
|
2012-09-11 20:27:46 +07:00
|
|
|
{
|
|
|
|
if (!dont || free->arch.rmap != dont->arch.rmap) {
|
|
|
|
vfree(free->arch.rmap);
|
|
|
|
free->arch.rmap = NULL;
|
2011-12-12 19:28:21 +07:00
|
|
|
}
|
2012-09-11 20:27:46 +07:00
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
|
|
|
|
unsigned long npages)
|
2012-09-11 20:27:46 +07:00
|
|
|
{
|
2017-01-30 17:21:53 +07:00
|
|
|
/*
|
|
|
|
* For now, if radix_enabled() then we only support radix guests,
|
|
|
|
* and in that case we don't need the rmap array.
|
|
|
|
*/
|
|
|
|
if (radix_enabled()) {
|
|
|
|
slot->arch.rmap = NULL;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-09-11 20:27:46 +07:00
|
|
|
slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
|
|
|
|
if (!slot->arch.rmap)
|
|
|
|
return -ENOMEM;
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
return 0;
|
|
|
|
}
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
|
|
|
|
struct kvm_memory_slot *memslot,
|
2015-05-18 18:59:39 +07:00
|
|
|
const struct kvm_userspace_memory_region *mem)
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
{
|
2012-09-11 20:27:46 +07:00
|
|
|
return 0;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
|
2015-05-18 18:59:39 +07:00
|
|
|
const struct kvm_userspace_memory_region *mem,
|
2015-05-18 18:20:23 +07:00
|
|
|
const struct kvm_memory_slot *old,
|
|
|
|
const struct kvm_memory_slot *new)
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
{
|
2012-09-11 20:28:18 +07:00
|
|
|
unsigned long npages = mem->memory_size >> PAGE_SHIFT;
|
2015-05-17 21:20:07 +07:00
|
|
|
struct kvm_memslots *slots;
|
2012-09-11 20:28:18 +07:00
|
|
|
struct kvm_memory_slot *memslot;
|
|
|
|
|
KVM: PPC: Book3S HV: Add a per vcpu cache for recently page faulted MMIO entries
This keeps a per vcpu cache for recently page faulted MMIO entries.
On a page fault, if the entry exists in the cache, we can avoid some
time-consuming paths, for example, looking up HPT, locking HPTE twice
and searching mmio gfn from memslots, then directly call
kvmppc_hv_emulate_mmio().
In current implenment, we limit the size of cache to four. We think
it's enough to cover the high-frequency MMIO HPTEs in most case.
For example, considering the case of using virtio device, for virtio
legacy devices, one HPTE could handle notifications from up to
1024 (64K page / 64 byte Port IO register) devices, so one cache entry
is enough; for virtio modern devices, we always need one HPTE to handle
notification for each device because modern device would use a 8M MMIO
register to notify host instead of Port IO register, typically the
system's configuration should not exceed four virtio devices per
vcpu, four cache entry is also enough in this case. Of course, if needed,
we could also modify the macro to a module parameter in the future.
Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-04 12:55:12 +07:00
|
|
|
/*
|
|
|
|
* If we are making a new memslot, it might make
|
|
|
|
* some address that was previously cached as emulated
|
|
|
|
* MMIO be no longer emulated MMIO, so invalidate
|
|
|
|
* all the caches of emulated MMIO translations.
|
|
|
|
*/
|
|
|
|
if (npages)
|
|
|
|
atomic64_inc(&kvm->arch.mmio_update);
|
|
|
|
|
2017-01-30 17:21:48 +07:00
|
|
|
if (npages && old->npages && !kvm_is_radix(kvm)) {
|
2012-09-11 20:28:18 +07:00
|
|
|
/*
|
|
|
|
* If modifying a memslot, reset all the rmap dirty bits.
|
|
|
|
* If this is a new memslot, we don't need to do anything
|
|
|
|
* since the rmap array starts out as all zeroes,
|
|
|
|
* i.e. no pages are dirty.
|
|
|
|
*/
|
2015-05-17 21:20:07 +07:00
|
|
|
slots = kvm_memslots(kvm);
|
|
|
|
memslot = id_to_memslot(slots, mem->slot);
|
2017-01-30 17:21:48 +07:00
|
|
|
kvmppc_hv_get_dirty_log_hpt(kvm, memslot, NULL);
|
2012-09-11 20:28:18 +07:00
|
|
|
}
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
}
|
|
|
|
|
2013-09-20 11:52:38 +07:00
|
|
|
/*
|
|
|
|
* Update LPCR values in kvm->arch and in vcores.
|
|
|
|
* Caller must hold kvm->lock.
|
|
|
|
*/
|
|
|
|
void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
|
|
|
|
{
|
|
|
|
long int i;
|
|
|
|
u32 cores_done = 0;
|
|
|
|
|
|
|
|
if ((kvm->arch.lpcr & mask) == lpcr)
|
|
|
|
return;
|
|
|
|
|
|
|
|
kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
|
|
|
|
|
|
|
|
for (i = 0; i < KVM_MAX_VCORES; ++i) {
|
|
|
|
struct kvmppc_vcore *vc = kvm->arch.vcores[i];
|
|
|
|
if (!vc)
|
|
|
|
continue;
|
|
|
|
spin_lock(&vc->lock);
|
|
|
|
vc->lpcr = (vc->lpcr & ~mask) | lpcr;
|
|
|
|
spin_unlock(&vc->lock);
|
|
|
|
if (++cores_done >= kvm->arch.online_vcores)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
|
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2016-11-16 18:25:20 +07:00
|
|
|
static void kvmppc_setup_partition_table(struct kvm *kvm)
|
|
|
|
{
|
|
|
|
unsigned long dw0, dw1;
|
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
if (!kvm_is_radix(kvm)) {
|
|
|
|
/* PS field - page size for VRMA */
|
|
|
|
dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) |
|
|
|
|
((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1);
|
|
|
|
/* HTABSIZE and HTABORG fields */
|
|
|
|
dw0 |= kvm->arch.sdr1;
|
2016-11-16 18:25:20 +07:00
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
/* Second dword as set by userspace */
|
|
|
|
dw1 = kvm->arch.process_table;
|
|
|
|
} else {
|
|
|
|
dw0 = PATB_HR | radix__get_tree_size() |
|
|
|
|
__pa(kvm->arch.pgtable) | RADIX_PGD_INDEX_SIZE;
|
|
|
|
dw1 = PATB_GR | kvm->arch.process_table;
|
|
|
|
}
|
2016-11-16 18:25:20 +07:00
|
|
|
|
|
|
|
mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
struct kvm *kvm = vcpu->kvm;
|
|
|
|
unsigned long hva;
|
|
|
|
struct kvm_memory_slot *memslot;
|
|
|
|
struct vm_area_struct *vma;
|
2013-09-20 11:52:38 +07:00
|
|
|
unsigned long lpcr = 0, senc;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
unsigned long psize, porder;
|
2012-09-11 20:27:01 +07:00
|
|
|
int srcu_idx;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
|
|
|
|
mutex_lock(&kvm->lock);
|
2015-03-20 16:39:42 +07:00
|
|
|
if (kvm->arch.hpte_setup_done)
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
goto out; /* another vcpu beat us to it */
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
/* Allocate hashed page table (if not done already) and reset it */
|
2016-12-20 12:49:00 +07:00
|
|
|
if (!kvm->arch.hpt.virt) {
|
KVM: PPC: Book3S HV: Split HPT allocation from activation
Currently, kvmppc_alloc_hpt() both allocates a new hashed page table (HPT)
and sets it up as the active page table for a VM. For the upcoming HPT
resize implementation we're going to want to allocate HPTs separately from
activating them.
So, split the allocation itself out into kvmppc_allocate_hpt() and perform
the activation with a new kvmppc_set_hpt() function. Likewise we split
kvmppc_free_hpt(), which just frees the HPT, from kvmppc_release_hpt()
which unsets it as an active HPT, then frees it.
We also move the logic to fall back to smaller HPT sizes if the first try
fails into the single caller which used that behaviour,
kvmppc_hv_setup_htab_rma(). This introduces a slight semantic change, in
that previously if the initial attempt at CMA allocation failed, we would
fall back to attempting smaller sizes with the page allocator. Now, we
try first CMA, then the page allocator at each size. As far as I can tell
this change should be harmless.
To match, we make kvmppc_free_hpt() just free the actual HPT itself. The
call to kvmppc_free_lpid() that was there, we move to the single caller.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-12-20 12:49:02 +07:00
|
|
|
int order = KVM_DEFAULT_HPT_ORDER;
|
|
|
|
struct kvm_hpt_info info;
|
|
|
|
|
|
|
|
err = kvmppc_allocate_hpt(&info, order);
|
|
|
|
/* If we get here, it means userspace didn't specify a
|
|
|
|
* size explicitly. So, try successively smaller
|
|
|
|
* sizes if the default failed. */
|
|
|
|
while ((err == -ENOMEM) && --order >= PPC_MIN_HPT_ORDER)
|
|
|
|
err = kvmppc_allocate_hpt(&info, order);
|
|
|
|
|
|
|
|
if (err < 0) {
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
pr_err("KVM: Couldn't alloc HPT\n");
|
|
|
|
goto out;
|
|
|
|
}
|
KVM: PPC: Book3S HV: Split HPT allocation from activation
Currently, kvmppc_alloc_hpt() both allocates a new hashed page table (HPT)
and sets it up as the active page table for a VM. For the upcoming HPT
resize implementation we're going to want to allocate HPTs separately from
activating them.
So, split the allocation itself out into kvmppc_allocate_hpt() and perform
the activation with a new kvmppc_set_hpt() function. Likewise we split
kvmppc_free_hpt(), which just frees the HPT, from kvmppc_release_hpt()
which unsets it as an active HPT, then frees it.
We also move the logic to fall back to smaller HPT sizes if the first try
fails into the single caller which used that behaviour,
kvmppc_hv_setup_htab_rma(). This introduces a slight semantic change, in
that previously if the initial attempt at CMA allocation failed, we would
fall back to attempting smaller sizes with the page allocator. Now, we
try first CMA, then the page allocator at each size. As far as I can tell
this change should be harmless.
To match, we make kvmppc_free_hpt() just free the actual HPT itself. The
call to kvmppc_free_lpid() that was there, we move to the single caller.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-12-20 12:49:02 +07:00
|
|
|
|
|
|
|
kvmppc_set_hpt(kvm, &info);
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
}
|
|
|
|
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
/* Look up the memslot for guest physical address 0 */
|
2012-09-11 20:27:01 +07:00
|
|
|
srcu_idx = srcu_read_lock(&kvm->srcu);
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
memslot = gfn_to_memslot(kvm, 0);
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
/* We must have some memory at 0 by now */
|
|
|
|
err = -EINVAL;
|
|
|
|
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
|
2012-09-11 20:27:01 +07:00
|
|
|
goto out_srcu;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
|
|
|
|
/* Look up the VMA for the start of this memory slot */
|
|
|
|
hva = memslot->userspace_addr;
|
|
|
|
down_read(¤t->mm->mmap_sem);
|
|
|
|
vma = find_vma(current->mm, hva);
|
|
|
|
if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
|
|
|
|
goto up_out;
|
|
|
|
|
|
|
|
psize = vma_kernel_pagesize(vma);
|
2011-12-12 19:31:41 +07:00
|
|
|
porder = __ilog2(psize);
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
|
|
|
|
up_read(¤t->mm->mmap_sem);
|
|
|
|
|
2014-12-03 09:30:38 +07:00
|
|
|
/* We can handle 4k, 64k or 16M pages in the VRMA */
|
|
|
|
err = -EINVAL;
|
|
|
|
if (!(psize == 0x1000 || psize == 0x10000 ||
|
|
|
|
psize == 0x1000000))
|
|
|
|
goto out_srcu;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
|
2014-12-03 09:30:38 +07:00
|
|
|
senc = slb_pgsize_encoding(psize);
|
|
|
|
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
|
|
|
|
(VRMA_VSID << SLB_VSID_SHIFT_1T);
|
|
|
|
/* Create HPTEs in the hash page table for the VRMA */
|
|
|
|
kvmppc_map_vrma(vcpu, memslot, porder);
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
2016-11-16 18:25:20 +07:00
|
|
|
/* Update VRMASD field in the LPCR */
|
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
|
|
|
|
/* the -4 is to account for senc values starting at 0x10 */
|
|
|
|
lpcr = senc << (LPCR_VRMASD_SH - 4);
|
|
|
|
kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
|
|
|
|
} else {
|
|
|
|
kvmppc_setup_partition_table(kvm);
|
|
|
|
}
|
2013-09-20 11:52:38 +07:00
|
|
|
|
2015-03-20 16:39:42 +07:00
|
|
|
/* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
smp_wmb();
|
2015-03-20 16:39:42 +07:00
|
|
|
kvm->arch.hpte_setup_done = 1;
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
err = 0;
|
2012-09-11 20:27:01 +07:00
|
|
|
out_srcu:
|
|
|
|
srcu_read_unlock(&kvm->srcu, srcu_idx);
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
out:
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return err;
|
2011-12-12 19:28:21 +07:00
|
|
|
|
KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()
This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory. We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.
Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page. Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context. That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.
When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work. Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma(). It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.
Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
2011-12-12 19:31:00 +07:00
|
|
|
up_out:
|
|
|
|
up_read(¤t->mm->mmap_sem);
|
2013-03-15 23:50:49 +07:00
|
|
|
goto out_srcu;
|
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
|
|
|
}
|
|
|
|
|
2015-12-18 03:59:06 +07:00
|
|
|
#ifdef CONFIG_KVM_XICS
|
|
|
|
/*
|
|
|
|
* Allocate a per-core structure for managing state about which cores are
|
|
|
|
* running in the host versus the guest and for exchanging data between
|
|
|
|
* real mode KVM and CPU running in the host.
|
|
|
|
* This is only done for the first VM.
|
|
|
|
* The allocated structure stays even if all VMs have stopped.
|
|
|
|
* It is only freed when the kvm-hv module is unloaded.
|
|
|
|
* It's OK for this routine to fail, we just don't support host
|
|
|
|
* core operations like redirecting H_IPI wakeups.
|
|
|
|
*/
|
|
|
|
void kvmppc_alloc_host_rm_ops(void)
|
|
|
|
{
|
|
|
|
struct kvmppc_host_rm_ops *ops;
|
|
|
|
unsigned long l_ops;
|
|
|
|
int cpu, core;
|
|
|
|
int size;
|
|
|
|
|
|
|
|
/* Not the first time here ? */
|
|
|
|
if (kvmppc_host_rm_ops_hv != NULL)
|
|
|
|
return;
|
|
|
|
|
|
|
|
ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL);
|
|
|
|
if (!ops)
|
|
|
|
return;
|
|
|
|
|
|
|
|
size = cpu_nr_cores() * sizeof(struct kvmppc_host_rm_core);
|
|
|
|
ops->rm_core = kzalloc(size, GFP_KERNEL);
|
|
|
|
|
|
|
|
if (!ops->rm_core) {
|
|
|
|
kfree(ops);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2015-12-18 03:59:08 +07:00
|
|
|
get_online_cpus();
|
|
|
|
|
2015-12-18 03:59:06 +07:00
|
|
|
for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
|
|
|
|
if (!cpu_online(cpu))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
core = cpu >> threads_shift;
|
|
|
|
ops->rm_core[core].rm_state.in_host = 1;
|
|
|
|
}
|
|
|
|
|
2015-12-18 03:59:09 +07:00
|
|
|
ops->vcpu_kick = kvmppc_fast_vcpu_kick_hv;
|
|
|
|
|
2015-12-18 03:59:06 +07:00
|
|
|
/*
|
|
|
|
* Make the contents of the kvmppc_host_rm_ops structure visible
|
|
|
|
* to other CPUs before we assign it to the global variable.
|
|
|
|
* Do an atomic assignment (no locks used here), but if someone
|
|
|
|
* beats us to it, just free our copy and return.
|
|
|
|
*/
|
|
|
|
smp_wmb();
|
|
|
|
l_ops = (unsigned long) ops;
|
|
|
|
|
|
|
|
if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
|
2015-12-18 03:59:08 +07:00
|
|
|
put_online_cpus();
|
2015-12-18 03:59:06 +07:00
|
|
|
kfree(ops->rm_core);
|
|
|
|
kfree(ops);
|
2015-12-18 03:59:08 +07:00
|
|
|
return;
|
2015-12-18 03:59:06 +07:00
|
|
|
}
|
2015-12-18 03:59:08 +07:00
|
|
|
|
2016-11-27 06:13:45 +07:00
|
|
|
cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
|
|
|
|
"ppc/kvm_book3s:prepare",
|
|
|
|
kvmppc_set_host_core,
|
|
|
|
kvmppc_clear_host_core);
|
2015-12-18 03:59:08 +07:00
|
|
|
put_online_cpus();
|
2015-12-18 03:59:06 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
void kvmppc_free_host_rm_ops(void)
|
|
|
|
{
|
|
|
|
if (kvmppc_host_rm_ops_hv) {
|
2016-11-27 06:13:45 +07:00
|
|
|
cpuhp_remove_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE);
|
2015-12-18 03:59:06 +07:00
|
|
|
kfree(kvmppc_host_rm_ops_hv->rm_core);
|
|
|
|
kfree(kvmppc_host_rm_ops_hv);
|
|
|
|
kvmppc_host_rm_ops_hv = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_init_vm_hv(struct kvm *kvm)
|
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
|
|
|
{
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
unsigned long lpcr, lpid;
|
2015-03-28 10:21:01 +07:00
|
|
|
char buf[32];
|
2017-01-30 17:21:53 +07:00
|
|
|
int ret;
|
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
|
|
|
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
/* Allocate the guest's logical partition ID */
|
|
|
|
|
|
|
|
lpid = kvmppc_alloc_lpid();
|
2013-07-22 13:32:35 +07:00
|
|
|
if ((long)lpid < 0)
|
KVM: PPC: Book3S HV: Make the guest hash table size configurable
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-05-04 09:32:53 +07:00
|
|
|
return -ENOMEM;
|
|
|
|
kvm->arch.lpid = lpid;
|
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
|
|
|
|
2015-12-18 03:59:06 +07:00
|
|
|
kvmppc_alloc_host_rm_ops();
|
|
|
|
|
KVM: PPC: Book3S HV: Improve handling of local vs. global TLB invalidations
When we change or remove a HPT (hashed page table) entry, we can do
either a global TLB invalidation (tlbie) that works across the whole
machine, or a local invalidation (tlbiel) that only affects this core.
Currently we do local invalidations if the VM has only one vcpu or if
the guest requests it with the H_LOCAL flag, though the guest Linux
kernel currently doesn't ever use H_LOCAL. Then, to cope with the
possibility that vcpus moving around to different physical cores might
expose stale TLB entries, there is some code in kvmppc_hv_entry to
flush the whole TLB of entries for this VM if either this vcpu is now
running on a different physical core from where it last ran, or if this
physical core last ran a different vcpu.
There are a number of problems on POWER7 with this as it stands:
- The TLB invalidation is done per thread, whereas it only needs to be
done per core, since the TLB is shared between the threads.
- With the possibility of the host paging out guest pages, the use of
H_LOCAL by an SMP guest is dangerous since the guest could possibly
retain and use a stale TLB entry pointing to a page that had been
removed from the guest.
- The TLB invalidations that we do when a vcpu moves from one physical
core to another are unnecessary in the case of an SMP guest that isn't
using H_LOCAL.
- The optimization of using local invalidations rather than global should
apply to guests with one virtual core, not just one vcpu.
(None of this applies on PPC970, since there we always have to
invalidate the whole TLB when entering and leaving the guest, and we
can't support paging out guest memory.)
To fix these problems and simplify the code, we now maintain a simple
cpumask of which cpus need to flush the TLB on entry to the guest.
(This is indexed by cpu, though we only ever use the bits for thread
0 of each core.) Whenever we do a local TLB invalidation, we set the
bits for every cpu except the bit for thread 0 of the core that we're
currently running on. Whenever we enter a guest, we test and clear the
bit for our core, and flush the TLB if it was set.
On initial startup of the VM, and when resetting the HPT, we set all the
bits in the need_tlb_flush cpumask, since any core could potentially have
stale TLB entries from the previous VM to use the same LPID, or the
previous contents of the HPT.
Then, we maintain a count of the number of online virtual cores, and use
that when deciding whether to use a local invalidation rather than the
number of online vcpus. The code to make that decision is extracted out
into a new function, global_invalidates(). For multi-core guests on
POWER7 (i.e. when we are using mmu notifiers), we now never do local
invalidations regardless of the H_LOCAL flag.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-22 06:28:08 +07:00
|
|
|
/*
|
|
|
|
* Since we don't flush the TLB when tearing down a VM,
|
|
|
|
* and this lpid might have previously been used,
|
|
|
|
* make sure we flush on each core before running the new VM.
|
2016-11-18 04:28:51 +07:00
|
|
|
* On POWER9, the tlbie in mmu_partition_table_set_entry()
|
|
|
|
* does this flush for us.
|
KVM: PPC: Book3S HV: Improve handling of local vs. global TLB invalidations
When we change or remove a HPT (hashed page table) entry, we can do
either a global TLB invalidation (tlbie) that works across the whole
machine, or a local invalidation (tlbiel) that only affects this core.
Currently we do local invalidations if the VM has only one vcpu or if
the guest requests it with the H_LOCAL flag, though the guest Linux
kernel currently doesn't ever use H_LOCAL. Then, to cope with the
possibility that vcpus moving around to different physical cores might
expose stale TLB entries, there is some code in kvmppc_hv_entry to
flush the whole TLB of entries for this VM if either this vcpu is now
running on a different physical core from where it last ran, or if this
physical core last ran a different vcpu.
There are a number of problems on POWER7 with this as it stands:
- The TLB invalidation is done per thread, whereas it only needs to be
done per core, since the TLB is shared between the threads.
- With the possibility of the host paging out guest pages, the use of
H_LOCAL by an SMP guest is dangerous since the guest could possibly
retain and use a stale TLB entry pointing to a page that had been
removed from the guest.
- The TLB invalidations that we do when a vcpu moves from one physical
core to another are unnecessary in the case of an SMP guest that isn't
using H_LOCAL.
- The optimization of using local invalidations rather than global should
apply to guests with one virtual core, not just one vcpu.
(None of this applies on PPC970, since there we always have to
invalidate the whole TLB when entering and leaving the guest, and we
can't support paging out guest memory.)
To fix these problems and simplify the code, we now maintain a simple
cpumask of which cpus need to flush the TLB on entry to the guest.
(This is indexed by cpu, though we only ever use the bits for thread
0 of each core.) Whenever we do a local TLB invalidation, we set the
bits for every cpu except the bit for thread 0 of the core that we're
currently running on. Whenever we enter a guest, we test and clear the
bit for our core, and flush the TLB if it was set.
On initial startup of the VM, and when resetting the HPT, we set all the
bits in the need_tlb_flush cpumask, since any core could potentially have
stale TLB entries from the previous VM to use the same LPID, or the
previous contents of the HPT.
Then, we maintain a count of the number of online virtual cores, and use
that when deciding whether to use a local invalidation rather than the
number of online vcpus. The code to make that decision is extracted out
into a new function, global_invalidates(). For multi-core guests on
POWER7 (i.e. when we are using mmu notifiers), we now never do local
invalidations regardless of the H_LOCAL flag.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-22 06:28:08 +07:00
|
|
|
*/
|
2016-11-18 04:28:51 +07:00
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
cpumask_setall(&kvm->arch.need_tlb_flush);
|
KVM: PPC: Book3S HV: Improve handling of local vs. global TLB invalidations
When we change or remove a HPT (hashed page table) entry, we can do
either a global TLB invalidation (tlbie) that works across the whole
machine, or a local invalidation (tlbiel) that only affects this core.
Currently we do local invalidations if the VM has only one vcpu or if
the guest requests it with the H_LOCAL flag, though the guest Linux
kernel currently doesn't ever use H_LOCAL. Then, to cope with the
possibility that vcpus moving around to different physical cores might
expose stale TLB entries, there is some code in kvmppc_hv_entry to
flush the whole TLB of entries for this VM if either this vcpu is now
running on a different physical core from where it last ran, or if this
physical core last ran a different vcpu.
There are a number of problems on POWER7 with this as it stands:
- The TLB invalidation is done per thread, whereas it only needs to be
done per core, since the TLB is shared between the threads.
- With the possibility of the host paging out guest pages, the use of
H_LOCAL by an SMP guest is dangerous since the guest could possibly
retain and use a stale TLB entry pointing to a page that had been
removed from the guest.
- The TLB invalidations that we do when a vcpu moves from one physical
core to another are unnecessary in the case of an SMP guest that isn't
using H_LOCAL.
- The optimization of using local invalidations rather than global should
apply to guests with one virtual core, not just one vcpu.
(None of this applies on PPC970, since there we always have to
invalidate the whole TLB when entering and leaving the guest, and we
can't support paging out guest memory.)
To fix these problems and simplify the code, we now maintain a simple
cpumask of which cpus need to flush the TLB on entry to the guest.
(This is indexed by cpu, though we only ever use the bits for thread
0 of each core.) Whenever we do a local TLB invalidation, we set the
bits for every cpu except the bit for thread 0 of the core that we're
currently running on. Whenever we enter a guest, we test and clear the
bit for our core, and flush the TLB if it was set.
On initial startup of the VM, and when resetting the HPT, we set all the
bits in the need_tlb_flush cpumask, since any core could potentially have
stale TLB entries from the previous VM to use the same LPID, or the
previous contents of the HPT.
Then, we maintain a count of the number of online virtual cores, and use
that when deciding whether to use a local invalidation rather than the
number of online vcpus. The code to make that decision is extracted out
into a new function, global_invalidates(). For multi-core guests on
POWER7 (i.e. when we are using mmu notifiers), we now never do local
invalidations regardless of the H_LOCAL flag.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-22 06:28:08 +07:00
|
|
|
|
2014-06-02 08:02:59 +07:00
|
|
|
/* Start out with the default set of hcalls enabled */
|
|
|
|
memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
|
|
|
|
sizeof(kvm->arch.enabled_hcalls));
|
|
|
|
|
2016-11-16 18:25:20 +07:00
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
2014-12-03 09:30:38 +07:00
|
|
|
/* Init LPCR for virtual RMA mode */
|
|
|
|
kvm->arch.host_lpid = mfspr(SPRN_LPID);
|
|
|
|
kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
|
|
|
|
lpcr &= LPCR_PECE | LPCR_LPES;
|
|
|
|
lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
|
|
|
|
LPCR_VPM0 | LPCR_VPM1;
|
|
|
|
kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
|
|
|
|
(VRMA_VSID << SLB_VSID_SHIFT_1T);
|
|
|
|
/* On POWER8 turn on online bit to enable PURR/SPURR */
|
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
|
|
lpcr |= LPCR_ONL;
|
2016-11-22 10:30:14 +07:00
|
|
|
/*
|
|
|
|
* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
|
|
|
|
* Set HVICE bit to enable hypervisor virtualization interrupts.
|
|
|
|
*/
|
|
|
|
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
|
2016-11-16 18:25:20 +07:00
|
|
|
lpcr &= ~LPCR_VPM0;
|
2016-11-22 10:30:14 +07:00
|
|
|
lpcr |= LPCR_HVICE;
|
|
|
|
}
|
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
/*
|
|
|
|
* For now, if the host uses radix, the guest must be radix.
|
|
|
|
*/
|
|
|
|
if (radix_enabled()) {
|
|
|
|
kvm->arch.radix = 1;
|
|
|
|
lpcr &= ~LPCR_VPM1;
|
|
|
|
lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR;
|
|
|
|
ret = kvmppc_init_vm_radix(kvm);
|
|
|
|
if (ret) {
|
|
|
|
kvmppc_free_lpid(kvm->arch.lpid);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
kvmppc_setup_partition_table(kvm);
|
|
|
|
}
|
|
|
|
|
KVM: PPC: book3s_hv: Add support for PPC970-family processors
This adds support for running KVM guests in supervisor mode on those
PPC970 processors that have a usable hypervisor mode. Unfortunately,
Apple G5 machines have supervisor mode disabled (MSR[HV] is forced to
1), but the YDL PowerStation does have a usable hypervisor mode.
There are several differences between the PPC970 and POWER7 in how
guests are managed. These differences are accommodated using the
CPU_FTR_ARCH_201 (PPC970) and CPU_FTR_ARCH_206 (POWER7) CPU feature
bits. Notably, on PPC970:
* The LPCR, LPID or RMOR registers don't exist, and the functions of
those registers are provided by bits in HID4 and one bit in HID0.
* External interrupts can be directed to the hypervisor, but unlike
POWER7 they are masked by MSR[EE] in non-hypervisor modes and use
SRR0/1 not HSRR0/1.
* There is no virtual RMA (VRMA) mode; the guest must use an RMO
(real mode offset) area.
* The TLB entries are not tagged with the LPID, so it is necessary to
flush the whole TLB on partition switch. Furthermore, when switching
partitions we have to ensure that no other CPU is executing the tlbie
or tlbsync instructions in either the old or the new partition,
otherwise undefined behaviour can occur.
* The PMU has 8 counters (PMC registers) rather than 6.
* The DSCR, PURR, SPURR, AMR, AMOR, UAMOR registers don't exist.
* The SLB has 64 entries rather than 32.
* There is no mediated external interrupt facility, so if we switch to
a guest that has a virtual external interrupt pending but the guest
has MSR[EE] = 0, we have to arrange to have an interrupt pending for
it so that we can get control back once it re-enables interrupts. We
do that by sending ourselves an IPI with smp_send_reschedule after
hard-disabling interrupts.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:40:08 +07:00
|
|
|
kvm->arch.lpcr = lpcr;
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
2016-12-20 12:49:05 +07:00
|
|
|
/* Initialization for future HPT resizes */
|
|
|
|
kvm->arch.resize_hpt = NULL;
|
|
|
|
|
2016-11-18 04:28:51 +07:00
|
|
|
/*
|
|
|
|
* Work out how many sets the TLB has, for the use of
|
|
|
|
* the TLB invalidation loop in book3s_hv_rmhandlers.S.
|
|
|
|
*/
|
2017-01-30 17:21:53 +07:00
|
|
|
if (kvm_is_radix(kvm))
|
|
|
|
kvm->arch.tlb_sets = POWER9_TLB_SETS_RADIX; /* 128 */
|
|
|
|
else if (cpu_has_feature(CPU_FTR_ARCH_300))
|
2016-11-18 04:28:51 +07:00
|
|
|
kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH; /* 256 */
|
|
|
|
else if (cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
|
|
kvm->arch.tlb_sets = POWER8_TLB_SETS; /* 512 */
|
|
|
|
else
|
|
|
|
kvm->arch.tlb_sets = POWER7_TLB_SETS; /* 128 */
|
|
|
|
|
2012-10-15 08:15:41 +07:00
|
|
|
/*
|
2014-05-23 15:15:25 +07:00
|
|
|
* Track that we now have a HV mode VM active. This blocks secondary
|
|
|
|
* CPU threads from coming online.
|
2017-01-30 17:21:53 +07:00
|
|
|
* On POWER9, we only need to do this for HPT guests on a radix
|
|
|
|
* host, which is not yet supported.
|
2012-10-15 08:15:41 +07:00
|
|
|
*/
|
2017-01-30 17:21:53 +07:00
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
kvm_hv_vm_activated();
|
2012-10-15 08:15:41 +07:00
|
|
|
|
2015-03-28 10:21:01 +07:00
|
|
|
/*
|
|
|
|
* Create a debugfs directory for the VM
|
|
|
|
*/
|
|
|
|
snprintf(buf, sizeof(buf), "vm%d", current->pid);
|
|
|
|
kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
|
|
|
|
if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
|
|
|
|
kvmppc_mmu_debugfs_init(kvm);
|
|
|
|
|
2011-06-29 07:22:41 +07:00
|
|
|
return 0;
|
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
|
|
|
}
|
|
|
|
|
2013-09-27 17:03:43 +07:00
|
|
|
static void kvmppc_free_vcores(struct kvm *kvm)
|
|
|
|
{
|
|
|
|
long int i;
|
|
|
|
|
2015-10-21 12:03:14 +07:00
|
|
|
for (i = 0; i < KVM_MAX_VCORES; ++i)
|
2013-09-27 17:03:43 +07:00
|
|
|
kfree(kvm->arch.vcores[i]);
|
|
|
|
kvm->arch.online_vcores = 0;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
|
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
|
|
|
{
|
2015-03-28 10:21:01 +07:00
|
|
|
debugfs_remove_recursive(kvm->arch.debugfs_dir);
|
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
kvm_hv_vm_deactivated();
|
2012-10-15 08:15:41 +07:00
|
|
|
|
2013-09-27 17:03:43 +07:00
|
|
|
kvmppc_free_vcores(kvm);
|
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 07:25:44 +07:00
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
kvmppc_free_lpid(kvm->arch.lpid);
|
|
|
|
|
2017-01-30 17:21:46 +07:00
|
|
|
if (kvm_is_radix(kvm))
|
|
|
|
kvmppc_free_radix(kvm);
|
|
|
|
else
|
KVM: PPC: Book3S HV: Split HPT allocation from activation
Currently, kvmppc_alloc_hpt() both allocates a new hashed page table (HPT)
and sets it up as the active page table for a VM. For the upcoming HPT
resize implementation we're going to want to allocate HPTs separately from
activating them.
So, split the allocation itself out into kvmppc_allocate_hpt() and perform
the activation with a new kvmppc_set_hpt() function. Likewise we split
kvmppc_free_hpt(), which just frees the HPT, from kvmppc_release_hpt()
which unsets it as an active HPT, then frees it.
We also move the logic to fall back to smaller HPT sizes if the first try
fails into the single caller which used that behaviour,
kvmppc_hv_setup_htab_rma(). This introduces a slight semantic change, in
that previously if the initial attempt at CMA allocation failed, we would
fall back to attempting smaller sizes with the page allocator. Now, we
try first CMA, then the page allocator at each size. As far as I can tell
this change should be harmless.
To match, we make kvmppc_free_hpt() just free the actual HPT itself. The
call to kvmppc_free_lpid() that was there, we move to the single caller.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-12-20 12:49:02 +07:00
|
|
|
kvmppc_free_hpt(&kvm->arch.hpt);
|
2016-08-19 12:35:50 +07:00
|
|
|
|
|
|
|
kvmppc_free_pimap(kvm);
|
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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
/* We don't need to emulate any privileged instructions or dcbz */
|
|
|
|
static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
|
|
|
|
unsigned int inst, int *advance)
|
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
|
|
|
{
|
2013-10-07 23:47:53 +07:00
|
|
|
return EMULATE_FAIL;
|
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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn,
|
|
|
|
ulong spr_val)
|
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
|
|
|
{
|
|
|
|
return EMULATE_FAIL;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
|
|
|
|
ulong *spr_val)
|
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
|
|
|
{
|
|
|
|
return EMULATE_FAIL;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_core_check_processor_compat_hv(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
|
|
|
{
|
2014-12-03 09:30:38 +07:00
|
|
|
if (!cpu_has_feature(CPU_FTR_HVMODE) ||
|
|
|
|
!cpu_has_feature(CPU_FTR_ARCH_206))
|
2013-10-07 23:47:53 +07:00
|
|
|
return -EIO;
|
2016-04-29 20:25:43 +07:00
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
return 0;
|
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
|
|
|
}
|
|
|
|
|
2016-08-19 12:35:48 +07:00
|
|
|
#ifdef CONFIG_KVM_XICS
|
|
|
|
|
|
|
|
void kvmppc_free_pimap(struct kvm *kvm)
|
|
|
|
{
|
|
|
|
kfree(kvm->arch.pimap);
|
|
|
|
}
|
|
|
|
|
2016-08-19 12:35:50 +07:00
|
|
|
static struct kvmppc_passthru_irqmap *kvmppc_alloc_pimap(void)
|
2016-08-19 12:35:48 +07:00
|
|
|
{
|
|
|
|
return kzalloc(sizeof(struct kvmppc_passthru_irqmap), GFP_KERNEL);
|
|
|
|
}
|
2016-08-19 12:35:50 +07:00
|
|
|
|
|
|
|
static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
|
|
|
|
{
|
|
|
|
struct irq_desc *desc;
|
|
|
|
struct kvmppc_irq_map *irq_map;
|
|
|
|
struct kvmppc_passthru_irqmap *pimap;
|
|
|
|
struct irq_chip *chip;
|
|
|
|
int i;
|
|
|
|
|
2016-08-19 12:35:54 +07:00
|
|
|
if (!kvm_irq_bypass)
|
|
|
|
return 1;
|
|
|
|
|
2016-08-19 12:35:50 +07:00
|
|
|
desc = irq_to_desc(host_irq);
|
|
|
|
if (!desc)
|
|
|
|
return -EIO;
|
|
|
|
|
|
|
|
mutex_lock(&kvm->lock);
|
|
|
|
|
|
|
|
pimap = kvm->arch.pimap;
|
|
|
|
if (pimap == NULL) {
|
|
|
|
/* First call, allocate structure to hold IRQ map */
|
|
|
|
pimap = kvmppc_alloc_pimap();
|
|
|
|
if (pimap == NULL) {
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
kvm->arch.pimap = pimap;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For now, we only support interrupts for which the EOI operation
|
|
|
|
* is an OPAL call followed by a write to XIRR, since that's
|
|
|
|
* what our real-mode EOI code does.
|
|
|
|
*/
|
|
|
|
chip = irq_data_get_irq_chip(&desc->irq_data);
|
|
|
|
if (!chip || !is_pnv_opal_msi(chip)) {
|
|
|
|
pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n",
|
|
|
|
host_irq, guest_gsi);
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* See if we already have an entry for this guest IRQ number.
|
|
|
|
* If it's mapped to a hardware IRQ number, that's an error,
|
|
|
|
* otherwise re-use this entry.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < pimap->n_mapped; i++) {
|
|
|
|
if (guest_gsi == pimap->mapped[i].v_hwirq) {
|
|
|
|
if (pimap->mapped[i].r_hwirq) {
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (i == KVMPPC_PIRQ_MAPPED) {
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return -EAGAIN; /* table is full */
|
|
|
|
}
|
|
|
|
|
|
|
|
irq_map = &pimap->mapped[i];
|
|
|
|
|
|
|
|
irq_map->v_hwirq = guest_gsi;
|
|
|
|
irq_map->desc = desc;
|
|
|
|
|
KVM: PPC: Book3S HV: Handle passthrough interrupts in guest
Currently, KVM switches back to the host to handle any external
interrupt (when the interrupt is received while running in the
guest). This patch updates real-mode KVM to check if an interrupt
is generated by a passthrough adapter that is owned by this guest.
If so, the real mode KVM will directly inject the corresponding
virtual interrupt to the guest VCPU's ICS and also EOI the interrupt
in hardware. In short, the interrupt is handled entirely in real
mode in the guest context without switching back to the host.
In some rare cases, the interrupt cannot be completely handled in
real mode, for instance, a VCPU that is sleeping needs to be woken
up. In this case, KVM simply switches back to the host with trap
reason set to 0x500. This works, but it is clearly not very efficient.
A following patch will distinguish this case and handle it
correctly in the host. Note that we can use the existing
check_too_hard() routine even though we are not in a hypercall to
determine if there is unfinished business that needs to be
completed in host virtual mode.
The patch assumes that the mapping between hardware interrupt IRQ
and virtual IRQ to be injected to the guest already exists for the
PCI passthrough interrupts that need to be handled in real mode.
If the mapping does not exist, KVM falls back to the default
existing behavior.
The KVM real mode code reads mappings from the mapped array in the
passthrough IRQ map without taking any lock. We carefully order the
loads and stores of the fields in the kvmppc_irq_map data structure
using memory barriers to avoid an inconsistent mapping being seen by
the reader. Thus, although it is possible to miss a map entry, it is
not possible to read a stale value.
[paulus@ozlabs.org - get irq_chip from irq_map rather than pimap,
pulled out powernv eoi change into a separate patch, made
kvmppc_read_intr get the vcpu from the paca rather than being
passed in, rewrote the logic at the end of kvmppc_read_intr to
avoid deep indentation, simplified logic in book3s_hv_rmhandlers.S
since we were always restoring SRR0/1 anyway, get rid of the cached
array (just use the mapped array), removed the kick_all_cpus_sync()
call, clear saved_xirr PACA field when we handle the interrupt in
real mode, fix compilation with CONFIG_KVM_XICS=n.]
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-19 12:35:51 +07:00
|
|
|
/*
|
|
|
|
* Order the above two stores before the next to serialize with
|
|
|
|
* the KVM real mode handler.
|
|
|
|
*/
|
|
|
|
smp_wmb();
|
|
|
|
irq_map->r_hwirq = desc->irq_data.hwirq;
|
|
|
|
|
2016-08-19 12:35:50 +07:00
|
|
|
if (i == pimap->n_mapped)
|
|
|
|
pimap->n_mapped++;
|
|
|
|
|
KVM: PPC: Book3S HV: Set server for passed-through interrupts
When a guest has a PCI pass-through device with an interrupt, it
will direct the interrupt to a particular guest VCPU. In fact the
physical interrupt might arrive on any CPU, and then get
delivered to the target VCPU in the emulated XICS (guest interrupt
controller), and eventually delivered to the target VCPU.
Now that we have code to handle device interrupts in real mode
without exiting to the host kernel, there is an advantage to having
the device interrupt arrive on the same sub(core) as the target
VCPU is running on. In this situation, the interrupt can be
delivered to the target VCPU without any exit to the host kernel
(using a hypervisor doorbell interrupt between threads if
necessary).
This patch aims to get passed-through device interrupts arriving
on the correct core by setting the interrupt server in the real
hardware XICS for the interrupt to the first thread in the (sub)core
where its target VCPU is running. We do this in the real-mode H_EOI
code because the H_EOI handler already needs to look at the
emulated ICS state for the interrupt (whereas the H_XIRR handler
doesn't), and we know we are running in the target VCPU context
at that point.
We set the server CPU in hardware using an OPAL call, regardless of
what the IRQ affinity mask for the interrupt says, and without
updating the affinity mask. This amounts to saying that when an
interrupt is passed through to a guest, as a matter of policy we
allow the guest's affinity for the interrupt to override the host's.
This is inspired by an earlier patch from Suresh Warrier, although
none of this code came from that earlier patch.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-19 12:35:56 +07:00
|
|
|
kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
|
|
|
|
|
2016-08-19 12:35:50 +07:00
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
|
|
|
|
{
|
|
|
|
struct irq_desc *desc;
|
|
|
|
struct kvmppc_passthru_irqmap *pimap;
|
|
|
|
int i;
|
|
|
|
|
2016-08-19 12:35:54 +07:00
|
|
|
if (!kvm_irq_bypass)
|
|
|
|
return 0;
|
|
|
|
|
2016-08-19 12:35:50 +07:00
|
|
|
desc = irq_to_desc(host_irq);
|
|
|
|
if (!desc)
|
|
|
|
return -EIO;
|
|
|
|
|
|
|
|
mutex_lock(&kvm->lock);
|
|
|
|
|
|
|
|
if (kvm->arch.pimap == NULL) {
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
pimap = kvm->arch.pimap;
|
|
|
|
|
|
|
|
for (i = 0; i < pimap->n_mapped; i++) {
|
|
|
|
if (guest_gsi == pimap->mapped[i].v_hwirq)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (i == pimap->n_mapped) {
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
KVM: PPC: Book3S HV: Set server for passed-through interrupts
When a guest has a PCI pass-through device with an interrupt, it
will direct the interrupt to a particular guest VCPU. In fact the
physical interrupt might arrive on any CPU, and then get
delivered to the target VCPU in the emulated XICS (guest interrupt
controller), and eventually delivered to the target VCPU.
Now that we have code to handle device interrupts in real mode
without exiting to the host kernel, there is an advantage to having
the device interrupt arrive on the same sub(core) as the target
VCPU is running on. In this situation, the interrupt can be
delivered to the target VCPU without any exit to the host kernel
(using a hypervisor doorbell interrupt between threads if
necessary).
This patch aims to get passed-through device interrupts arriving
on the correct core by setting the interrupt server in the real
hardware XICS for the interrupt to the first thread in the (sub)core
where its target VCPU is running. We do this in the real-mode H_EOI
code because the H_EOI handler already needs to look at the
emulated ICS state for the interrupt (whereas the H_XIRR handler
doesn't), and we know we are running in the target VCPU context
at that point.
We set the server CPU in hardware using an OPAL call, regardless of
what the IRQ affinity mask for the interrupt says, and without
updating the affinity mask. This amounts to saying that when an
interrupt is passed through to a guest, as a matter of policy we
allow the guest's affinity for the interrupt to override the host's.
This is inspired by an earlier patch from Suresh Warrier, although
none of this code came from that earlier patch.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-08-19 12:35:56 +07:00
|
|
|
kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
|
|
|
|
|
2016-08-19 12:35:50 +07:00
|
|
|
/* invalidate the entry */
|
|
|
|
pimap->mapped[i].r_hwirq = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We don't free this structure even when the count goes to
|
|
|
|
* zero. The structure is freed when we destroy the VM.
|
|
|
|
*/
|
|
|
|
|
|
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons,
|
|
|
|
struct irq_bypass_producer *prod)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
struct kvm_kernel_irqfd *irqfd =
|
|
|
|
container_of(cons, struct kvm_kernel_irqfd, consumer);
|
|
|
|
|
|
|
|
irqfd->producer = prod;
|
|
|
|
|
|
|
|
ret = kvmppc_set_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi);
|
|
|
|
if (ret)
|
|
|
|
pr_info("kvmppc_set_passthru_irq (irq %d, gsi %d) fails: %d\n",
|
|
|
|
prod->irq, irqfd->gsi, ret);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void kvmppc_irq_bypass_del_producer_hv(struct irq_bypass_consumer *cons,
|
|
|
|
struct irq_bypass_producer *prod)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct kvm_kernel_irqfd *irqfd =
|
|
|
|
container_of(cons, struct kvm_kernel_irqfd, consumer);
|
|
|
|
|
|
|
|
irqfd->producer = NULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When producer of consumer is unregistered, we change back to
|
|
|
|
* default external interrupt handling mode - KVM real mode
|
|
|
|
* will switch back to host.
|
|
|
|
*/
|
|
|
|
ret = kvmppc_clr_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi);
|
|
|
|
if (ret)
|
|
|
|
pr_warn("kvmppc_clr_passthru_irq (irq %d, gsi %d) fails: %d\n",
|
|
|
|
prod->irq, irqfd->gsi, ret);
|
|
|
|
}
|
2016-08-19 12:35:48 +07:00
|
|
|
#endif
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static long kvm_arch_vm_ioctl_hv(struct file *filp,
|
|
|
|
unsigned int ioctl, unsigned long arg)
|
|
|
|
{
|
|
|
|
struct kvm *kvm __maybe_unused = filp->private_data;
|
|
|
|
void __user *argp = (void __user *)arg;
|
|
|
|
long r;
|
|
|
|
|
|
|
|
switch (ioctl) {
|
|
|
|
|
|
|
|
case KVM_PPC_ALLOCATE_HTAB: {
|
|
|
|
u32 htab_order;
|
|
|
|
|
|
|
|
r = -EFAULT;
|
|
|
|
if (get_user(htab_order, (u32 __user *)argp))
|
|
|
|
break;
|
2016-12-20 12:49:03 +07:00
|
|
|
r = kvmppc_alloc_reset_hpt(kvm, htab_order);
|
2013-10-07 23:47:53 +07:00
|
|
|
if (r)
|
|
|
|
break;
|
|
|
|
r = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
case KVM_PPC_GET_HTAB_FD: {
|
|
|
|
struct kvm_get_htab_fd ghf;
|
|
|
|
|
|
|
|
r = -EFAULT;
|
|
|
|
if (copy_from_user(&ghf, argp, sizeof(ghf)))
|
|
|
|
break;
|
|
|
|
r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2016-12-20 12:49:05 +07:00
|
|
|
case KVM_PPC_RESIZE_HPT_PREPARE: {
|
|
|
|
struct kvm_ppc_resize_hpt rhpt;
|
|
|
|
|
|
|
|
r = -EFAULT;
|
|
|
|
if (copy_from_user(&rhpt, argp, sizeof(rhpt)))
|
|
|
|
break;
|
|
|
|
|
|
|
|
r = kvm_vm_ioctl_resize_hpt_prepare(kvm, &rhpt);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
case KVM_PPC_RESIZE_HPT_COMMIT: {
|
|
|
|
struct kvm_ppc_resize_hpt rhpt;
|
|
|
|
|
|
|
|
r = -EFAULT;
|
|
|
|
if (copy_from_user(&rhpt, argp, sizeof(rhpt)))
|
|
|
|
break;
|
|
|
|
|
|
|
|
r = kvm_vm_ioctl_resize_hpt_commit(kvm, &rhpt);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
default:
|
|
|
|
r = -ENOTTY;
|
|
|
|
}
|
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2014-06-02 08:02:59 +07:00
|
|
|
/*
|
|
|
|
* List of hcall numbers to enable by default.
|
|
|
|
* For compatibility with old userspace, we enable by default
|
|
|
|
* all hcalls that were implemented before the hcall-enabling
|
|
|
|
* facility was added. Note this list should not include H_RTAS.
|
|
|
|
*/
|
|
|
|
static unsigned int default_hcall_list[] = {
|
|
|
|
H_REMOVE,
|
|
|
|
H_ENTER,
|
|
|
|
H_READ,
|
|
|
|
H_PROTECT,
|
|
|
|
H_BULK_REMOVE,
|
|
|
|
H_GET_TCE,
|
|
|
|
H_PUT_TCE,
|
|
|
|
H_SET_DABR,
|
|
|
|
H_SET_XDABR,
|
|
|
|
H_CEDE,
|
|
|
|
H_PROD,
|
|
|
|
H_CONFER,
|
|
|
|
H_REGISTER_VPA,
|
|
|
|
#ifdef CONFIG_KVM_XICS
|
|
|
|
H_EOI,
|
|
|
|
H_CPPR,
|
|
|
|
H_IPI,
|
|
|
|
H_IPOLL,
|
|
|
|
H_XIRR,
|
|
|
|
H_XIRR_X,
|
|
|
|
#endif
|
|
|
|
0
|
|
|
|
};
|
|
|
|
|
|
|
|
static void init_default_hcalls(void)
|
|
|
|
{
|
|
|
|
int i;
|
2014-06-02 08:03:00 +07:00
|
|
|
unsigned int hcall;
|
2014-06-02 08:02:59 +07:00
|
|
|
|
2014-06-02 08:03:00 +07:00
|
|
|
for (i = 0; default_hcall_list[i]; ++i) {
|
|
|
|
hcall = default_hcall_list[i];
|
|
|
|
WARN_ON(!kvmppc_hcall_impl_hv(hcall));
|
|
|
|
__set_bit(hcall / 4, default_enabled_hcalls);
|
|
|
|
}
|
2014-06-02 08:02:59 +07:00
|
|
|
}
|
|
|
|
|
2017-01-30 17:21:41 +07:00
|
|
|
static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
|
|
|
|
{
|
2017-01-30 17:21:42 +07:00
|
|
|
unsigned long lpcr;
|
2017-01-30 17:21:53 +07:00
|
|
|
int radix;
|
2017-01-30 17:21:42 +07:00
|
|
|
|
|
|
|
/* If not on a POWER9, reject it */
|
|
|
|
if (!cpu_has_feature(CPU_FTR_ARCH_300))
|
|
|
|
return -ENODEV;
|
|
|
|
|
|
|
|
/* If any unknown flags set, reject it */
|
|
|
|
if (cfg->flags & ~(KVM_PPC_MMUV3_RADIX | KVM_PPC_MMUV3_GTSE))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2017-01-30 17:21:53 +07:00
|
|
|
/* We can't change a guest to/from radix yet */
|
|
|
|
radix = !!(cfg->flags & KVM_PPC_MMUV3_RADIX);
|
|
|
|
if (radix != kvm_is_radix(kvm))
|
2017-01-30 17:21:42 +07:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/* GR (guest radix) bit in process_table field must match */
|
2017-01-30 17:21:53 +07:00
|
|
|
if (!!(cfg->process_table & PATB_GR) != radix)
|
2017-01-30 17:21:42 +07:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/* Process table size field must be reasonable, i.e. <= 24 */
|
|
|
|
if ((cfg->process_table & PRTS_MASK) > 24)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
kvm->arch.process_table = cfg->process_table;
|
|
|
|
kvmppc_setup_partition_table(kvm);
|
|
|
|
|
|
|
|
lpcr = (cfg->flags & KVM_PPC_MMUV3_GTSE) ? LPCR_GTSE : 0;
|
|
|
|
kvmppc_update_lpcr(kvm, lpcr, LPCR_GTSE);
|
|
|
|
|
|
|
|
return 0;
|
2017-01-30 17:21:41 +07:00
|
|
|
}
|
|
|
|
|
2013-10-07 23:48:01 +07:00
|
|
|
static struct kvmppc_ops kvm_ops_hv = {
|
2013-10-07 23:47:53 +07:00
|
|
|
.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
|
|
|
|
.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
|
|
|
|
.get_one_reg = kvmppc_get_one_reg_hv,
|
|
|
|
.set_one_reg = kvmppc_set_one_reg_hv,
|
|
|
|
.vcpu_load = kvmppc_core_vcpu_load_hv,
|
|
|
|
.vcpu_put = kvmppc_core_vcpu_put_hv,
|
|
|
|
.set_msr = kvmppc_set_msr_hv,
|
|
|
|
.vcpu_run = kvmppc_vcpu_run_hv,
|
|
|
|
.vcpu_create = kvmppc_core_vcpu_create_hv,
|
|
|
|
.vcpu_free = kvmppc_core_vcpu_free_hv,
|
|
|
|
.check_requests = kvmppc_core_check_requests_hv,
|
|
|
|
.get_dirty_log = kvm_vm_ioctl_get_dirty_log_hv,
|
|
|
|
.flush_memslot = kvmppc_core_flush_memslot_hv,
|
|
|
|
.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
|
|
|
|
.commit_memory_region = kvmppc_core_commit_memory_region_hv,
|
|
|
|
.unmap_hva = kvm_unmap_hva_hv,
|
|
|
|
.unmap_hva_range = kvm_unmap_hva_range_hv,
|
|
|
|
.age_hva = kvm_age_hva_hv,
|
|
|
|
.test_age_hva = kvm_test_age_hva_hv,
|
|
|
|
.set_spte_hva = kvm_set_spte_hva_hv,
|
|
|
|
.mmu_destroy = kvmppc_mmu_destroy_hv,
|
|
|
|
.free_memslot = kvmppc_core_free_memslot_hv,
|
|
|
|
.create_memslot = kvmppc_core_create_memslot_hv,
|
|
|
|
.init_vm = kvmppc_core_init_vm_hv,
|
|
|
|
.destroy_vm = kvmppc_core_destroy_vm_hv,
|
|
|
|
.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
|
|
|
|
.emulate_op = kvmppc_core_emulate_op_hv,
|
|
|
|
.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
|
|
|
|
.emulate_mfspr = kvmppc_core_emulate_mfspr_hv,
|
|
|
|
.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
|
|
|
|
.arch_vm_ioctl = kvm_arch_vm_ioctl_hv,
|
2014-06-02 08:03:00 +07:00
|
|
|
.hcall_implemented = kvmppc_hcall_impl_hv,
|
2016-08-19 12:35:50 +07:00
|
|
|
#ifdef CONFIG_KVM_XICS
|
|
|
|
.irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv,
|
|
|
|
.irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv,
|
|
|
|
#endif
|
2017-01-30 17:21:41 +07:00
|
|
|
.configure_mmu = kvmhv_configure_mmu,
|
|
|
|
.get_rmmu_info = kvmhv_get_rmmu_info,
|
2013-10-07 23:47:53 +07:00
|
|
|
};
|
|
|
|
|
KVM: PPC: Book3S HV: Fix TB corruption in guest exit path on HMI interrupt
When a guest is assigned to a core it converts the host Timebase (TB)
into guest TB by adding guest timebase offset before entering into
guest. During guest exit it restores the guest TB to host TB. This means
under certain conditions (Guest migration) host TB and guest TB can differ.
When we get an HMI for TB related issues the opal HMI handler would
try fixing errors and restore the correct host TB value. With no guest
running, we don't have any issues. But with guest running on the core
we run into TB corruption issues.
If we get an HMI while in the guest, the current HMI handler invokes opal
hmi handler before forcing guest to exit. The guest exit path subtracts
the guest TB offset from the current TB value which may have already
been restored with host value by opal hmi handler. This leads to incorrect
host and guest TB values.
With split-core, things become more complex. With split-core, TB also gets
split and each subcore gets its own TB register. When a hmi handler fixes
a TB error and restores the TB value, it affects all the TB values of
sibling subcores on the same core. On TB errors all the thread in the core
gets HMI. With existing code, the individual threads call opal hmi handle
independently which can easily throw TB out of sync if we have guest
running on subcores. Hence we will need to co-ordinate with all the
threads before making opal hmi handler call followed by TB resync.
This patch introduces a sibling subcore state structure (shared by all
threads in the core) in paca which holds information about whether sibling
subcores are in Guest mode or host mode. An array in_guest[] of size
MAX_SUBCORE_PER_CORE=4 is used to maintain the state of each subcore.
The subcore id is used as index into in_guest[] array. Only primary
thread entering/exiting the guest is responsible to set/unset its
designated array element.
On TB error, we get HMI interrupt on every thread on the core. Upon HMI,
this patch will now force guest to vacate the core/subcore. Primary
thread from each subcore will then turn off its respective bit
from the above bitmap during the guest exit path just after the
guest->host partition switch is complete.
All other threads that have just exited the guest OR were already in host
will wait until all other subcores clears their respective bit.
Once all the subcores turn off their respective bit, all threads will
will make call to opal hmi handler.
It is not necessary that opal hmi handler would resync the TB value for
every HMI interrupts. It would do so only for the HMI caused due to
TB errors. For rest, it would not touch TB value. Hence to make things
simpler, primary thread would call TB resync explicitly once for each
core immediately after opal hmi handler instead of subtracting guest
offset from TB. TB resync call will restore the TB with host value.
Thus we can be sure about the TB state.
One of the primary threads exiting the guest will take up the
responsibility of calling TB resync. It will use one of the top bits
(bit 63) from subcore state flags bitmap to make the decision. The first
primary thread (among the subcores) that is able to set the bit will
have to call the TB resync. Rest all other threads will wait until TB
resync is complete. Once TB resync is complete all threads will then
proceed.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-05-15 11:14:26 +07:00
|
|
|
static int kvm_init_subcore_bitmap(void)
|
|
|
|
{
|
|
|
|
int i, j;
|
|
|
|
int nr_cores = cpu_nr_cores();
|
|
|
|
struct sibling_subcore_state *sibling_subcore_state;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_cores; i++) {
|
|
|
|
int first_cpu = i * threads_per_core;
|
|
|
|
int node = cpu_to_node(first_cpu);
|
|
|
|
|
|
|
|
/* Ignore if it is already allocated. */
|
|
|
|
if (paca[first_cpu].sibling_subcore_state)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
sibling_subcore_state =
|
|
|
|
kmalloc_node(sizeof(struct sibling_subcore_state),
|
|
|
|
GFP_KERNEL, node);
|
|
|
|
if (!sibling_subcore_state)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
memset(sibling_subcore_state, 0,
|
|
|
|
sizeof(struct sibling_subcore_state));
|
|
|
|
|
|
|
|
for (j = 0; j < threads_per_core; j++) {
|
|
|
|
int cpu = first_cpu + j;
|
|
|
|
|
|
|
|
paca[cpu].sibling_subcore_state = sibling_subcore_state;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-01-30 17:21:46 +07:00
|
|
|
static int kvmppc_radix_possible(void)
|
|
|
|
{
|
|
|
|
return cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled();
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static int kvmppc_book3s_init_hv(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
|
|
|
{
|
|
|
|
int r;
|
2013-10-07 23:48:01 +07:00
|
|
|
/*
|
|
|
|
* FIXME!! Do we need to check on all cpus ?
|
|
|
|
*/
|
|
|
|
r = kvmppc_core_check_processor_compat_hv();
|
|
|
|
if (r < 0)
|
2014-03-25 06:47:05 +07:00
|
|
|
return -ENODEV;
|
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
|
|
|
|
KVM: PPC: Book3S HV: Fix TB corruption in guest exit path on HMI interrupt
When a guest is assigned to a core it converts the host Timebase (TB)
into guest TB by adding guest timebase offset before entering into
guest. During guest exit it restores the guest TB to host TB. This means
under certain conditions (Guest migration) host TB and guest TB can differ.
When we get an HMI for TB related issues the opal HMI handler would
try fixing errors and restore the correct host TB value. With no guest
running, we don't have any issues. But with guest running on the core
we run into TB corruption issues.
If we get an HMI while in the guest, the current HMI handler invokes opal
hmi handler before forcing guest to exit. The guest exit path subtracts
the guest TB offset from the current TB value which may have already
been restored with host value by opal hmi handler. This leads to incorrect
host and guest TB values.
With split-core, things become more complex. With split-core, TB also gets
split and each subcore gets its own TB register. When a hmi handler fixes
a TB error and restores the TB value, it affects all the TB values of
sibling subcores on the same core. On TB errors all the thread in the core
gets HMI. With existing code, the individual threads call opal hmi handle
independently which can easily throw TB out of sync if we have guest
running on subcores. Hence we will need to co-ordinate with all the
threads before making opal hmi handler call followed by TB resync.
This patch introduces a sibling subcore state structure (shared by all
threads in the core) in paca which holds information about whether sibling
subcores are in Guest mode or host mode. An array in_guest[] of size
MAX_SUBCORE_PER_CORE=4 is used to maintain the state of each subcore.
The subcore id is used as index into in_guest[] array. Only primary
thread entering/exiting the guest is responsible to set/unset its
designated array element.
On TB error, we get HMI interrupt on every thread on the core. Upon HMI,
this patch will now force guest to vacate the core/subcore. Primary
thread from each subcore will then turn off its respective bit
from the above bitmap during the guest exit path just after the
guest->host partition switch is complete.
All other threads that have just exited the guest OR were already in host
will wait until all other subcores clears their respective bit.
Once all the subcores turn off their respective bit, all threads will
will make call to opal hmi handler.
It is not necessary that opal hmi handler would resync the TB value for
every HMI interrupts. It would do so only for the HMI caused due to
TB errors. For rest, it would not touch TB value. Hence to make things
simpler, primary thread would call TB resync explicitly once for each
core immediately after opal hmi handler instead of subtracting guest
offset from TB. TB resync call will restore the TB with host value.
Thus we can be sure about the TB state.
One of the primary threads exiting the guest will take up the
responsibility of calling TB resync. It will use one of the top bits
(bit 63) from subcore state flags bitmap to make the decision. The first
primary thread (among the subcores) that is able to set the bit will
have to call the TB resync. Rest all other threads will wait until TB
resync is complete. Once TB resync is complete all threads will then
proceed.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-05-15 11:14:26 +07:00
|
|
|
r = kvm_init_subcore_bitmap();
|
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
|
KVM: PPC: Book3S HV: Use OPAL XICS emulation on POWER9
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2016-11-18 05:02:08 +07:00
|
|
|
/*
|
|
|
|
* We need a way of accessing the XICS interrupt controller,
|
|
|
|
* either directly, via paca[cpu].kvm_hstate.xics_phys, or
|
|
|
|
* indirectly, via OPAL.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
if (!get_paca()->kvm_hstate.xics_phys) {
|
|
|
|
struct device_node *np;
|
|
|
|
|
|
|
|
np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
|
|
|
|
if (!np) {
|
|
|
|
pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2013-10-07 23:48:01 +07:00
|
|
|
kvm_ops_hv.owner = THIS_MODULE;
|
|
|
|
kvmppc_hv_ops = &kvm_ops_hv;
|
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
|
|
|
|
2014-06-02 08:02:59 +07:00
|
|
|
init_default_hcalls();
|
|
|
|
|
KVM: PPC: Book3S HV: Make use of unused threads when running guests
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 18:18:03 +07:00
|
|
|
init_vcore_lists();
|
|
|
|
|
2013-10-07 23:48:01 +07:00
|
|
|
r = kvmppc_mmu_hv_init();
|
2017-01-30 17:21:46 +07:00
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
|
|
|
|
if (kvmppc_radix_possible())
|
|
|
|
r = kvmppc_radix_init();
|
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
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
static void kvmppc_book3s_exit_hv(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
|
|
|
{
|
2015-12-18 03:59:06 +07:00
|
|
|
kvmppc_free_host_rm_ops();
|
2017-01-30 17:21:46 +07:00
|
|
|
if (kvmppc_radix_possible())
|
|
|
|
kvmppc_radix_exit();
|
2013-10-07 23:48:01 +07:00
|
|
|
kvmppc_hv_ops = NULL;
|
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
|
|
|
}
|
|
|
|
|
2013-10-07 23:47:53 +07:00
|
|
|
module_init(kvmppc_book3s_init_hv);
|
|
|
|
module_exit(kvmppc_book3s_exit_hv);
|
2013-10-07 23:47:59 +07:00
|
|
|
MODULE_LICENSE("GPL");
|
2013-12-09 19:53:42 +07:00
|
|
|
MODULE_ALIAS_MISCDEV(KVM_MINOR);
|
|
|
|
MODULE_ALIAS("devname:kvm");
|
2016-11-18 04:28:51 +07:00
|
|
|
|