linux-brain/arch/powerpc/kvm/powerpc.c

1521 lines
34 KiB
C
Raw Normal View History

/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright IBM Corp. 2007
*
* Authors: Hollis Blanchard <hollisb@us.ibm.com>
* Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
#include <linux/vmalloc.h>
#include <linux/hrtimer.h>
#include <linux/fs.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 17:04:11 +09:00
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/irqbypass.h>
#include <linux/kvm_irqfd.h>
#include <asm/cputable.h>
#include <asm/uaccess.h>
#include <asm/kvm_ppc.h>
#include <asm/tlbflush.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 09:23:08 +09:00
#include <asm/cputhreads.h>
#include <asm/irqflags.h>
#include <asm/iommu.h>
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
struct kvmppc_ops *kvmppc_hv_ops;
EXPORT_SYMBOL_GPL(kvmppc_hv_ops);
struct kvmppc_ops *kvmppc_pr_ops;
EXPORT_SYMBOL_GPL(kvmppc_pr_ops);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
return !!(v->arch.pending_exceptions) ||
v->requests;
}
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return 1;
}
/*
* Common checks before entering the guest world. Call with interrupts
* disabled.
*
* returns:
*
* == 1 if we're ready to go into guest state
* <= 0 if we need to go back to the host with return value
*/
int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
{
int r;
WARN_ON(irqs_disabled());
hard_irq_disable();
while (true) {
if (need_resched()) {
local_irq_enable();
cond_resched();
hard_irq_disable();
continue;
}
if (signal_pending(current)) {
kvmppc_account_exit(vcpu, SIGNAL_EXITS);
vcpu->run->exit_reason = KVM_EXIT_INTR;
r = -EINTR;
break;
}
vcpu->mode = IN_GUEST_MODE;
/*
* Reading vcpu->requests must happen after setting vcpu->mode,
* so we don't miss a request because the requester sees
* OUTSIDE_GUEST_MODE and assumes we'll be checking requests
* before next entering the guest (and thus doesn't IPI).
* This also orders the write to mode from any reads
* to the page tables done while the VCPU is running.
* Please see the comment in kvm_flush_remote_tlbs.
*/
smp_mb();
if (vcpu->requests) {
/* Make sure we process requests preemptable */
local_irq_enable();
trace_kvm_check_requests(vcpu);
r = kvmppc_core_check_requests(vcpu);
hard_irq_disable();
if (r > 0)
continue;
break;
}
if (kvmppc_core_prepare_to_enter(vcpu)) {
/* interrupts got enabled in between, so we
are back at square 1 */
continue;
}
guest_enter_irqoff();
return 1;
}
/* return to host */
local_irq_enable();
return r;
}
EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
static void kvmppc_swab_shared(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
int i;
shared->sprg0 = swab64(shared->sprg0);
shared->sprg1 = swab64(shared->sprg1);
shared->sprg2 = swab64(shared->sprg2);
shared->sprg3 = swab64(shared->sprg3);
shared->srr0 = swab64(shared->srr0);
shared->srr1 = swab64(shared->srr1);
shared->dar = swab64(shared->dar);
shared->msr = swab64(shared->msr);
shared->dsisr = swab32(shared->dsisr);
shared->int_pending = swab32(shared->int_pending);
for (i = 0; i < ARRAY_SIZE(shared->sr); i++)
shared->sr[i] = swab32(shared->sr[i]);
}
#endif
int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
{
int nr = kvmppc_get_gpr(vcpu, 11);
int r;
unsigned long __maybe_unused param1 = kvmppc_get_gpr(vcpu, 3);
unsigned long __maybe_unused param2 = kvmppc_get_gpr(vcpu, 4);
unsigned long __maybe_unused param3 = kvmppc_get_gpr(vcpu, 5);
unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
unsigned long r2 = 0;
if (!(kvmppc_get_msr(vcpu) & MSR_SF)) {
/* 32 bit mode */
param1 &= 0xffffffff;
param2 &= 0xffffffff;
param3 &= 0xffffffff;
param4 &= 0xffffffff;
}
switch (nr) {
case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
{
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
/* Book3S can be little endian, find it out here */
int shared_big_endian = true;
if (vcpu->arch.intr_msr & MSR_LE)
shared_big_endian = false;
if (shared_big_endian != vcpu->arch.shared_big_endian)
kvmppc_swab_shared(vcpu);
vcpu->arch.shared_big_endian = shared_big_endian;
#endif
if (!(param2 & MAGIC_PAGE_FLAG_NOT_MAPPED_NX)) {
/*
* Older versions of the Linux magic page code had
* a bug where they would map their trampoline code
* NX. If that's the case, remove !PR NX capability.
*/
vcpu->arch.disable_kernel_nx = true;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
vcpu->arch.magic_page_pa = param1 & ~0xfffULL;
vcpu->arch.magic_page_ea = param2 & ~0xfffULL;
#ifdef CONFIG_PPC_64K_PAGES
/*
* Make sure our 4k magic page is in the same window of a 64k
* page within the guest and within the host's page.
*/
if ((vcpu->arch.magic_page_pa & 0xf000) !=
((ulong)vcpu->arch.shared & 0xf000)) {
void *old_shared = vcpu->arch.shared;
ulong shared = (ulong)vcpu->arch.shared;
void *new_shared;
shared &= PAGE_MASK;
shared |= vcpu->arch.magic_page_pa & 0xf000;
new_shared = (void*)shared;
memcpy(new_shared, old_shared, 0x1000);
vcpu->arch.shared = new_shared;
}
#endif
r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
r = EV_SUCCESS;
break;
}
case KVM_HCALL_TOKEN(KVM_HC_FEATURES):
r = EV_SUCCESS;
#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
#endif
/* Second return value is in r4 */
break;
case EV_HCALL_TOKEN(EV_IDLE):
r = EV_SUCCESS;
kvm_vcpu_block(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
break;
default:
r = EV_UNIMPLEMENTED;
break;
}
kvmppc_set_gpr(vcpu, 4, r2);
return r;
}
EXPORT_SYMBOL_GPL(kvmppc_kvm_pv);
int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
{
int r = false;
/* We have to know what CPU to virtualize */
if (!vcpu->arch.pvr)
goto out;
/* PAPR only works with book3s_64 */
if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled)
goto out;
/* HV KVM can only do PAPR mode for now */
if (!vcpu->arch.papr_enabled && is_kvmppc_hv_enabled(vcpu->kvm))
goto out;
#ifdef CONFIG_KVM_BOOKE_HV
if (!cpu_has_feature(CPU_FTR_EMB_HV))
goto out;
#endif
r = true;
out:
vcpu->arch.sane = r;
return r ? 0 : -EINVAL;
}
EXPORT_SYMBOL_GPL(kvmppc_sanity_check);
int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
enum emulation_result er;
int r;
er = kvmppc_emulate_loadstore(vcpu);
switch (er) {
case EMULATE_DONE:
/* Future optimization: only reload non-volatiles if they were
* actually modified. */
r = RESUME_GUEST_NV;
break;
case EMULATE_AGAIN:
r = RESUME_GUEST;
break;
case EMULATE_DO_MMIO:
run->exit_reason = KVM_EXIT_MMIO;
/* We must reload nonvolatiles because "update" load/store
* instructions modify register state. */
/* Future optimization: only reload non-volatiles if they were
* actually modified. */
r = RESUME_HOST_NV;
break;
case EMULATE_FAIL:
{
u32 last_inst;
kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
/* XXX Deliver Program interrupt to guest. */
pr_emerg("%s: emulation failed (%08x)\n", __func__, last_inst);
r = RESUME_HOST;
break;
}
default:
WARN_ON(1);
r = RESUME_GUEST;
}
return r;
}
EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio);
int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
bool data)
{
ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
struct kvmppc_pte pte;
int r;
vcpu->stat.st++;
r = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
XLATE_WRITE, &pte);
if (r < 0)
return r;
*eaddr = pte.raddr;
if (!pte.may_write)
return -EPERM;
/* Magic page override */
if (kvmppc_supports_magic_page(vcpu) && mp_pa &&
((pte.raddr & KVM_PAM & PAGE_MASK) == mp_pa) &&
!(kvmppc_get_msr(vcpu) & MSR_PR)) {
void *magic = vcpu->arch.shared;
magic += pte.eaddr & 0xfff;
memcpy(magic, ptr, size);
return EMULATE_DONE;
}
if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size))
return EMULATE_DO_MMIO;
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvmppc_st);
int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
bool data)
{
ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
struct kvmppc_pte pte;
int rc;
vcpu->stat.ld++;
rc = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
XLATE_READ, &pte);
if (rc)
return rc;
*eaddr = pte.raddr;
if (!pte.may_read)
return -EPERM;
if (!data && !pte.may_execute)
return -ENOEXEC;
/* Magic page override */
if (kvmppc_supports_magic_page(vcpu) && mp_pa &&
((pte.raddr & KVM_PAM & PAGE_MASK) == mp_pa) &&
!(kvmppc_get_msr(vcpu) & MSR_PR)) {
void *magic = vcpu->arch.shared;
magic += pte.eaddr & 0xfff;
memcpy(ptr, magic, size);
return EMULATE_DONE;
}
if (kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size))
return EMULATE_DO_MMIO;
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvmppc_ld);
int kvm_arch_hardware_enable(void)
{
return 0;
}
int kvm_arch_hardware_setup(void)
{
return 0;
}
void kvm_arch_check_processor_compat(void *rtn)
{
*(int *)rtn = kvmppc_core_check_processor_compat();
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
struct kvmppc_ops *kvm_ops = NULL;
/*
* if we have both HV and PR enabled, default is HV
*/
if (type == 0) {
if (kvmppc_hv_ops)
kvm_ops = kvmppc_hv_ops;
else
kvm_ops = kvmppc_pr_ops;
if (!kvm_ops)
goto err_out;
} else if (type == KVM_VM_PPC_HV) {
if (!kvmppc_hv_ops)
goto err_out;
kvm_ops = kvmppc_hv_ops;
} else if (type == KVM_VM_PPC_PR) {
if (!kvmppc_pr_ops)
goto err_out;
kvm_ops = kvmppc_pr_ops;
} else
goto err_out;
if (kvm_ops->owner && !try_module_get(kvm_ops->owner))
return -ENOENT;
kvm->arch.kvm_ops = kvm_ops;
return kvmppc_core_init_vm(kvm);
err_out:
return -EINVAL;
}
bool kvm_arch_has_vcpu_debugfs(void)
{
return false;
}
int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
return 0;
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
unsigned int i;
struct kvm_vcpu *vcpu;
#ifdef CONFIG_KVM_XICS
/*
* We call kick_all_cpus_sync() to ensure that all
* CPUs have executed any pending IPIs before we
* continue and free VCPUs structures below.
*/
if (is_kvmppc_hv_enabled(kvm))
kick_all_cpus_sync();
#endif
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_arch_vcpu_free(vcpu);
mutex_lock(&kvm->lock);
for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
kvm->vcpus[i] = NULL;
atomic_set(&kvm->online_vcpus, 0);
kvmppc_core_destroy_vm(kvm);
mutex_unlock(&kvm->lock);
/* drop the module reference */
module_put(kvm->arch.kvm_ops->owner);
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
/* Assume we're using HV mode when the HV module is loaded */
int hv_enabled = kvmppc_hv_ops ? 1 : 0;
if (kvm) {
/*
* Hooray - we know which VM type we're running on. Depend on
* that rather than the guess above.
*/
hv_enabled = is_kvmppc_hv_enabled(kvm);
}
switch (ext) {
#ifdef CONFIG_BOOKE
case KVM_CAP_PPC_BOOKE_SREGS:
case KVM_CAP_PPC_BOOKE_WATCHDOG:
case KVM_CAP_PPC_EPR:
#else
case KVM_CAP_PPC_SEGSTATE:
case KVM_CAP_PPC_HIOR:
case KVM_CAP_PPC_PAPR:
#endif
case KVM_CAP_PPC_UNSET_IRQ:
case KVM_CAP_PPC_IRQ_LEVEL:
case KVM_CAP_ENABLE_CAP:
KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling This provides a way for userspace controls which sPAPR hcalls get handled in the kernel. Each hcall can be individually enabled or disabled for in-kernel handling, except for H_RTAS. The exception for H_RTAS is because userspace can already control whether individual RTAS functions are handled in-kernel or not via the KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for H_RTAS is out of the normal sequence of hcall numbers. Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM. The args field of the struct kvm_enable_cap specifies the hcall number in args[0] and the enable/disable flag in args[1]; 0 means disable in-kernel handling (so that the hcall will always cause an exit to userspace) and 1 means enable. Enabling or disabling in-kernel handling of an hcall is effective across the whole VM. The ability for KVM_ENABLE_CAP to be used on a VM file descriptor on PowerPC is new, added by this commit. The KVM_CAP_ENABLE_CAP_VM capability advertises that this ability exists. When a VM is created, an initial set of hcalls are enabled for in-kernel handling. The set that is enabled is the set that have an in-kernel implementation at this point. Any new hcall implementations from this point onwards should not be added to the default set without a good reason. No distinction is made between real-mode and virtual-mode hcall implementations; the one setting controls them both. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-06-02 10:02:59 +09:00
case KVM_CAP_ENABLE_CAP_VM:
case KVM_CAP_ONE_REG:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
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 09:21:34 +09:00
r = 1;
break;
case KVM_CAP_PPC_PAIRED_SINGLES:
case KVM_CAP_PPC_OSI:
case KVM_CAP_PPC_GET_PVINFO:
#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
case KVM_CAP_SW_TLB:
#endif
/* We support this only for PR */
r = !hv_enabled;
break;
#ifdef CONFIG_KVM_MMIO
case KVM_CAP_COALESCED_MMIO:
r = KVM_COALESCED_MMIO_PAGE_OFFSET;
break;
#endif
#ifdef CONFIG_KVM_MPIC
case KVM_CAP_IRQ_MPIC:
r = 1;
break;
#endif
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_SPAPR_TCE:
case KVM_CAP_SPAPR_TCE_64:
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 11:32:53 +09:00
case KVM_CAP_PPC_ALLOC_HTAB:
case KVM_CAP_PPC_RTAS:
case KVM_CAP_PPC_FIXUP_HCALL:
KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling This provides a way for userspace controls which sPAPR hcalls get handled in the kernel. Each hcall can be individually enabled or disabled for in-kernel handling, except for H_RTAS. The exception for H_RTAS is because userspace can already control whether individual RTAS functions are handled in-kernel or not via the KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for H_RTAS is out of the normal sequence of hcall numbers. Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM. The args field of the struct kvm_enable_cap specifies the hcall number in args[0] and the enable/disable flag in args[1]; 0 means disable in-kernel handling (so that the hcall will always cause an exit to userspace) and 1 means enable. Enabling or disabling in-kernel handling of an hcall is effective across the whole VM. The ability for KVM_ENABLE_CAP to be used on a VM file descriptor on PowerPC is new, added by this commit. The KVM_CAP_ENABLE_CAP_VM capability advertises that this ability exists. When a VM is created, an initial set of hcalls are enabled for in-kernel handling. The set that is enabled is the set that have an in-kernel implementation at this point. Any new hcall implementations from this point onwards should not be added to the default set without a good reason. No distinction is made between real-mode and virtual-mode hcall implementations; the one setting controls them both. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-06-02 10:02:59 +09:00
case KVM_CAP_PPC_ENABLE_HCALL:
#ifdef CONFIG_KVM_XICS
case KVM_CAP_IRQ_XICS:
#endif
r = 1;
break;
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
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 09:23:08 +09:00
case KVM_CAP_PPC_SMT:
if (hv_enabled)
r = threads_per_subcore;
else
r = 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 09:23:08 +09:00
break;
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 09:25:44 +09:00
case KVM_CAP_PPC_RMA:
r = 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 09:25:44 +09:00
break;
case KVM_CAP_PPC_HWRNG:
r = kvmppc_hwrng_present();
break;
#endif
case KVM_CAP_SYNC_MMU:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
r = hv_enabled;
#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
r = 1;
#else
r = 0;
KVM: PPC: Book3S HV: Provide a method for userspace to read and write the HPT A new ioctl, KVM_PPC_GET_HTAB_FD, returns a file descriptor. Reads on this fd return the contents of the HPT (hashed page table), writes create and/or remove entries in the HPT. There is a new capability, KVM_CAP_PPC_HTAB_FD, to indicate the presence of the ioctl. The ioctl takes an argument structure with the index of the first HPT entry to read out and a set of flags. The flags indicate whether the user is intending to read or write the HPT, and whether to return all entries or only the "bolted" entries (those with the bolted bit, 0x10, set in the first doubleword). This is intended for use in implementing qemu's savevm/loadvm and for live migration. Therefore, on reads, the first pass returns information about all HPTEs (or all bolted HPTEs). When the first pass reaches the end of the HPT, it returns from the read. Subsequent reads only return information about HPTEs that have changed since they were last read. A read that finds no changed HPTEs in the HPT following where the last read finished will return 0 bytes. The format of the data provides a simple run-length compression of the invalid entries. Each block of data starts with a header that indicates the index (position in the HPT, which is just an array), the number of valid entries starting at that index (may be zero), and the number of invalid entries following those valid entries. The valid entries, 16 bytes each, follow the header. The invalid entries are not explicitly represented. Signed-off-by: Paul Mackerras <paulus@samba.org> [agraf: fix documentation] Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-20 07:57:20 +09:00
#endif
break;
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
KVM: PPC: Book3S HV: Provide a method for userspace to read and write the HPT A new ioctl, KVM_PPC_GET_HTAB_FD, returns a file descriptor. Reads on this fd return the contents of the HPT (hashed page table), writes create and/or remove entries in the HPT. There is a new capability, KVM_CAP_PPC_HTAB_FD, to indicate the presence of the ioctl. The ioctl takes an argument structure with the index of the first HPT entry to read out and a set of flags. The flags indicate whether the user is intending to read or write the HPT, and whether to return all entries or only the "bolted" entries (those with the bolted bit, 0x10, set in the first doubleword). This is intended for use in implementing qemu's savevm/loadvm and for live migration. Therefore, on reads, the first pass returns information about all HPTEs (or all bolted HPTEs). When the first pass reaches the end of the HPT, it returns from the read. Subsequent reads only return information about HPTEs that have changed since they were last read. A read that finds no changed HPTEs in the HPT following where the last read finished will return 0 bytes. The format of the data provides a simple run-length compression of the invalid entries. Each block of data starts with a header that indicates the index (position in the HPT, which is just an array), the number of valid entries starting at that index (may be zero), and the number of invalid entries following those valid entries. The valid entries, 16 bytes each, follow the header. The invalid entries are not explicitly represented. Signed-off-by: Paul Mackerras <paulus@samba.org> [agraf: fix documentation] Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-20 07:57:20 +09:00
case KVM_CAP_PPC_HTAB_FD:
r = hv_enabled;
KVM: PPC: Book3S HV: Provide a method for userspace to read and write the HPT A new ioctl, KVM_PPC_GET_HTAB_FD, returns a file descriptor. Reads on this fd return the contents of the HPT (hashed page table), writes create and/or remove entries in the HPT. There is a new capability, KVM_CAP_PPC_HTAB_FD, to indicate the presence of the ioctl. The ioctl takes an argument structure with the index of the first HPT entry to read out and a set of flags. The flags indicate whether the user is intending to read or write the HPT, and whether to return all entries or only the "bolted" entries (those with the bolted bit, 0x10, set in the first doubleword). This is intended for use in implementing qemu's savevm/loadvm and for live migration. Therefore, on reads, the first pass returns information about all HPTEs (or all bolted HPTEs). When the first pass reaches the end of the HPT, it returns from the read. Subsequent reads only return information about HPTEs that have changed since they were last read. A read that finds no changed HPTEs in the HPT following where the last read finished will return 0 bytes. The format of the data provides a simple run-length compression of the invalid entries. Each block of data starts with a header that indicates the index (position in the HPT, which is just an array), the number of valid entries starting at that index (may be zero), and the number of invalid entries following those valid entries. The valid entries, 16 bytes each, follow the header. The invalid entries are not explicitly represented. Signed-off-by: Paul Mackerras <paulus@samba.org> [agraf: fix documentation] Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-20 07:57:20 +09:00
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 09:21:34 +09:00
#endif
case KVM_CAP_NR_VCPUS:
/*
* Recommending a number of CPUs is somewhat arbitrary; we
* return the number of present CPUs for -HV (since a host
* will have secondary threads "offline"), and for other KVM
* implementations just count online CPUs.
*/
if (hv_enabled)
r = num_present_cpus();
else
r = num_online_cpus();
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_PPC_GET_SMMU_INFO:
r = 1;
break;
case KVM_CAP_SPAPR_MULTITCE:
r = 1;
break;
#endif
case KVM_CAP_PPC_HTM:
r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled;
break;
default:
r = 0;
break;
}
return r;
}
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
return -EINVAL;
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
kvmppc_core_free_memslot(kvm, free, dont);
}
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned long npages)
{
return kvmppc_core_create_memslot(kvm, slot, npages);
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
kvmppc_core_commit_memory_region(kvm, mem, old, new);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
kvmppc_core_flush_memslot(kvm, slot);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
struct kvm_vcpu *vcpu;
vcpu = kvmppc_core_vcpu_create(kvm, id);
if (!IS_ERR(vcpu)) {
vcpu->arch.wqp = &vcpu->wq;
kvmppc_create_vcpu_debugfs(vcpu, id);
}
return vcpu;
}
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
}
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
/* Make sure we're not using the vcpu anymore */
hrtimer_cancel(&vcpu->arch.dec_timer);
kvmppc_remove_vcpu_debugfs(vcpu);
switch (vcpu->arch.irq_type) {
case KVMPPC_IRQ_MPIC:
kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
break;
case KVMPPC_IRQ_XICS:
kvmppc_xics_free_icp(vcpu);
break;
}
kvmppc_core_vcpu_free(vcpu);
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
kvm_arch_vcpu_free(vcpu);
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
return kvmppc_core_pending_dec(vcpu);
}
static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
kvmppc_decrementer_func(vcpu);
return HRTIMER_NORESTART;
}
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
int ret;
hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
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 09:21:34 +09:00
vcpu->arch.dec_expires = ~(u64)0;
#ifdef CONFIG_KVM_EXIT_TIMING
mutex_init(&vcpu->arch.exit_timing_lock);
#endif
ret = kvmppc_subarch_vcpu_init(vcpu);
return ret;
}
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
kvmppc_mmu_destroy(vcpu);
kvmppc_subarch_vcpu_uninit(vcpu);
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
#ifdef CONFIG_BOOKE
/*
* vrsave (formerly usprg0) isn't used by Linux, but may
* be used by the guest.
*
* On non-booke this is associated with Altivec and
* is handled by code in book3s.c.
*/
mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
#endif
kvmppc_core_vcpu_load(vcpu, cpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
kvmppc_core_vcpu_put(vcpu);
#ifdef CONFIG_BOOKE
vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
#endif
}
/*
* irq_bypass_add_producer and irq_bypass_del_producer are only
* useful if the architecture supports PCI passthrough.
* irq_bypass_stop and irq_bypass_start are not needed and so
* kvm_ops are not defined for them.
*/
bool kvm_arch_has_irq_bypass(void)
{
return ((kvmppc_hv_ops && kvmppc_hv_ops->irq_bypass_add_producer) ||
(kvmppc_pr_ops && kvmppc_pr_ops->irq_bypass_add_producer));
}
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
struct kvm *kvm = irqfd->kvm;
if (kvm->arch.kvm_ops->irq_bypass_add_producer)
return kvm->arch.kvm_ops->irq_bypass_add_producer(cons, prod);
return 0;
}
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
struct kvm *kvm = irqfd->kvm;
if (kvm->arch.kvm_ops->irq_bypass_del_producer)
kvm->arch.kvm_ops->irq_bypass_del_producer(cons, prod);
}
static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
struct kvm_run *run)
{
u64 uninitialized_var(gpr);
if (run->mmio.len > sizeof(gpr)) {
printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
return;
}
if (!vcpu->arch.mmio_host_swabbed) {
switch (run->mmio.len) {
case 8: gpr = *(u64 *)run->mmio.data; break;
case 4: gpr = *(u32 *)run->mmio.data; break;
case 2: gpr = *(u16 *)run->mmio.data; break;
case 1: gpr = *(u8 *)run->mmio.data; break;
}
} else {
switch (run->mmio.len) {
case 8: gpr = swab64(*(u64 *)run->mmio.data); break;
case 4: gpr = swab32(*(u32 *)run->mmio.data); break;
case 2: gpr = swab16(*(u16 *)run->mmio.data); break;
case 1: gpr = *(u8 *)run->mmio.data; break;
}
}
if (vcpu->arch.mmio_sign_extend) {
switch (run->mmio.len) {
#ifdef CONFIG_PPC64
case 4:
gpr = (s64)(s32)gpr;
break;
#endif
case 2:
gpr = (s64)(s16)gpr;
break;
case 1:
gpr = (s64)(s8)gpr;
break;
}
}
kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
switch (vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) {
case KVM_MMIO_REG_GPR:
kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
break;
case KVM_MMIO_REG_FPR:
VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
break;
#ifdef CONFIG_PPC_BOOK3S
case KVM_MMIO_REG_QPR:
vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
break;
case KVM_MMIO_REG_FQPR:
VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
break;
#endif
default:
BUG();
}
}
static int __kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int rt, unsigned int bytes,
int is_default_endian, int sign_extend)
{
int idx, ret;
bool host_swabbed;
/* Pity C doesn't have a logical XOR operator */
if (kvmppc_need_byteswap(vcpu)) {
host_swabbed = is_default_endian;
} else {
host_swabbed = !is_default_endian;
}
if (bytes > sizeof(run->mmio.data)) {
printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
run->mmio.len);
}
run->mmio.phys_addr = vcpu->arch.paddr_accessed;
run->mmio.len = bytes;
run->mmio.is_write = 0;
vcpu->arch.io_gpr = rt;
vcpu->arch.mmio_host_swabbed = host_swabbed;
vcpu->mmio_needed = 1;
vcpu->mmio_is_write = 0;
vcpu->arch.mmio_sign_extend = sign_extend;
idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr,
bytes, &run->mmio.data);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (!ret) {
kvmppc_complete_mmio_load(vcpu, run);
vcpu->mmio_needed = 0;
return EMULATE_DONE;
}
return EMULATE_DO_MMIO;
}
int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int rt, unsigned int bytes,
int is_default_endian)
{
return __kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian, 0);
}
EXPORT_SYMBOL_GPL(kvmppc_handle_load);
/* Same as above, but sign extends */
int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int rt, unsigned int bytes,
int is_default_endian)
{
return __kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian, 1);
}
int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
u64 val, unsigned int bytes, int is_default_endian)
{
void *data = run->mmio.data;
int idx, ret;
bool host_swabbed;
/* Pity C doesn't have a logical XOR operator */
if (kvmppc_need_byteswap(vcpu)) {
host_swabbed = is_default_endian;
} else {
host_swabbed = !is_default_endian;
}
if (bytes > sizeof(run->mmio.data)) {
printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
run->mmio.len);
}
run->mmio.phys_addr = vcpu->arch.paddr_accessed;
run->mmio.len = bytes;
run->mmio.is_write = 1;
vcpu->mmio_needed = 1;
vcpu->mmio_is_write = 1;
/* Store the value at the lowest bytes in 'data'. */
if (!host_swabbed) {
switch (bytes) {
case 8: *(u64 *)data = val; break;
case 4: *(u32 *)data = val; break;
case 2: *(u16 *)data = val; break;
case 1: *(u8 *)data = val; break;
}
} else {
switch (bytes) {
case 8: *(u64 *)data = swab64(val); break;
case 4: *(u32 *)data = swab32(val); break;
case 2: *(u16 *)data = swab16(val); break;
case 1: *(u8 *)data = val; break;
}
}
idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr,
bytes, &run->mmio.data);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (!ret) {
vcpu->mmio_needed = 0;
return EMULATE_DONE;
}
return EMULATE_DO_MMIO;
}
EXPORT_SYMBOL_GPL(kvmppc_handle_store);
int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
int r = 0;
union kvmppc_one_reg val;
int size;
size = one_reg_size(reg->id);
if (size > sizeof(val))
return -EINVAL;
r = kvmppc_get_one_reg(vcpu, reg->id, &val);
if (r == -EINVAL) {
r = 0;
switch (reg->id) {
#ifdef CONFIG_ALTIVEC
case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
r = -ENXIO;
break;
}
val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
break;
case KVM_REG_PPC_VSCR:
if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
r = -ENXIO;
break;
}
val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
break;
case KVM_REG_PPC_VRSAVE:
val = get_reg_val(reg->id, vcpu->arch.vrsave);
break;
#endif /* CONFIG_ALTIVEC */
default:
r = -EINVAL;
break;
}
}
if (r)
return r;
if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size))
r = -EFAULT;
return r;
}
int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
int r;
union kvmppc_one_reg val;
int size;
size = one_reg_size(reg->id);
if (size > sizeof(val))
return -EINVAL;
if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
return -EFAULT;
r = kvmppc_set_one_reg(vcpu, reg->id, &val);
if (r == -EINVAL) {
r = 0;
switch (reg->id) {
#ifdef CONFIG_ALTIVEC
case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
r = -ENXIO;
break;
}
vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
break;
case KVM_REG_PPC_VSCR:
if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
r = -ENXIO;
break;
}
vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
break;
case KVM_REG_PPC_VRSAVE:
if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
r = -ENXIO;
break;
}
vcpu->arch.vrsave = set_reg_val(reg->id, val);
break;
#endif /* CONFIG_ALTIVEC */
default:
r = -EINVAL;
break;
}
}
return r;
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int r;
sigset_t sigsaved;
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
if (vcpu->mmio_needed) {
if (!vcpu->mmio_is_write)
kvmppc_complete_mmio_load(vcpu, run);
vcpu->mmio_needed = 0;
} else if (vcpu->arch.osi_needed) {
u64 *gprs = run->osi.gprs;
int i;
for (i = 0; i < 32; i++)
kvmppc_set_gpr(vcpu, i, gprs[i]);
vcpu->arch.osi_needed = 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 09:21:34 +09:00
} else if (vcpu->arch.hcall_needed) {
int i;
kvmppc_set_gpr(vcpu, 3, run->papr_hcall.ret);
for (i = 0; i < 9; ++i)
kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]);
vcpu->arch.hcall_needed = 0;
#ifdef CONFIG_BOOKE
} else if (vcpu->arch.epr_needed) {
kvmppc_set_epr(vcpu, run->epr.epr);
vcpu->arch.epr_needed = 0;
#endif
}
r = kvmppc_vcpu_run(run, vcpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
return r;
}
int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
{
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 16:42:46 +09:00
if (irq->irq == KVM_INTERRUPT_UNSET) {
kvmppc_core_dequeue_external(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 16:42:46 +09:00
return 0;
}
kvmppc_core_queue_external(vcpu, irq);
kvm_vcpu_kick(vcpu);
return 0;
}
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
struct kvm_enable_cap *cap)
{
int r;
if (cap->flags)
return -EINVAL;
switch (cap->cap) {
case KVM_CAP_PPC_OSI:
r = 0;
vcpu->arch.osi_enabled = true;
break;
case KVM_CAP_PPC_PAPR:
r = 0;
vcpu->arch.papr_enabled = true;
break;
case KVM_CAP_PPC_EPR:
r = 0;
if (cap->args[0])
vcpu->arch.epr_flags |= KVMPPC_EPR_USER;
else
vcpu->arch.epr_flags &= ~KVMPPC_EPR_USER;
break;
#ifdef CONFIG_BOOKE
case KVM_CAP_PPC_BOOKE_WATCHDOG:
r = 0;
vcpu->arch.watchdog_enabled = true;
break;
#endif
#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
case KVM_CAP_SW_TLB: {
struct kvm_config_tlb cfg;
void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];
r = -EFAULT;
if (copy_from_user(&cfg, user_ptr, sizeof(cfg)))
break;
r = kvm_vcpu_ioctl_config_tlb(vcpu, &cfg);
break;
}
#endif
#ifdef CONFIG_KVM_MPIC
case KVM_CAP_IRQ_MPIC: {
struct fd f;
struct kvm_device *dev;
r = -EBADF;
f = fdget(cap->args[0]);
if (!f.file)
break;
r = -EPERM;
dev = kvm_device_from_filp(f.file);
if (dev)
r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]);
fdput(f);
break;
}
#endif
#ifdef CONFIG_KVM_XICS
case KVM_CAP_IRQ_XICS: {
struct fd f;
struct kvm_device *dev;
r = -EBADF;
f = fdget(cap->args[0]);
if (!f.file)
break;
r = -EPERM;
dev = kvm_device_from_filp(f.file);
if (dev)
r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
fdput(f);
break;
}
#endif /* CONFIG_KVM_XICS */
default:
r = -EINVAL;
break;
}
if (!r)
r = kvmppc_sanity_check(vcpu);
return r;
}
bool kvm_arch_intc_initialized(struct kvm *kvm)
{
#ifdef CONFIG_KVM_MPIC
if (kvm->arch.mpic)
return true;
#endif
#ifdef CONFIG_KVM_XICS
if (kvm->arch.xics)
return true;
#endif
return false;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
return -EINVAL;
}
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
long r;
switch (ioctl) {
case KVM_INTERRUPT: {
struct kvm_interrupt irq;
r = -EFAULT;
if (copy_from_user(&irq, argp, sizeof(irq)))
goto out;
r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
goto out;
}
case KVM_ENABLE_CAP:
{
struct kvm_enable_cap cap;
r = -EFAULT;
if (copy_from_user(&cap, argp, sizeof(cap)))
goto out;
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
break;
}
case KVM_SET_ONE_REG:
case KVM_GET_ONE_REG:
{
struct kvm_one_reg reg;
r = -EFAULT;
if (copy_from_user(&reg, argp, sizeof(reg)))
goto out;
if (ioctl == KVM_SET_ONE_REG)
r = kvm_vcpu_ioctl_set_one_reg(vcpu, &reg);
else
r = kvm_vcpu_ioctl_get_one_reg(vcpu, &reg);
break;
}
#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
case KVM_DIRTY_TLB: {
struct kvm_dirty_tlb dirty;
r = -EFAULT;
if (copy_from_user(&dirty, argp, sizeof(dirty)))
goto out;
r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
break;
}
#endif
default:
r = -EINVAL;
}
out:
return r;
}
int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
}
static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
{
u32 inst_nop = 0x60000000;
#ifdef CONFIG_KVM_BOOKE_HV
u32 inst_sc1 = 0x44000022;
pvinfo->hcall[0] = cpu_to_be32(inst_sc1);
pvinfo->hcall[1] = cpu_to_be32(inst_nop);
pvinfo->hcall[2] = cpu_to_be32(inst_nop);
pvinfo->hcall[3] = cpu_to_be32(inst_nop);
#else
u32 inst_lis = 0x3c000000;
u32 inst_ori = 0x60000000;
u32 inst_sc = 0x44000002;
u32 inst_imm_mask = 0xffff;
/*
* The hypercall to get into KVM from within guest context is as
* follows:
*
* lis r0, r0, KVM_SC_MAGIC_R0@h
* ori r0, KVM_SC_MAGIC_R0@l
* sc
* nop
*/
pvinfo->hcall[0] = cpu_to_be32(inst_lis | ((KVM_SC_MAGIC_R0 >> 16) & inst_imm_mask));
pvinfo->hcall[1] = cpu_to_be32(inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask));
pvinfo->hcall[2] = cpu_to_be32(inst_sc);
pvinfo->hcall[3] = cpu_to_be32(inst_nop);
#endif
pvinfo->flags = KVM_PPC_PVINFO_FLAGS_EV_IDLE;
return 0;
}
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
bool line_status)
{
if (!irqchip_in_kernel(kvm))
return -ENXIO;
irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
irq_event->irq, irq_event->level,
line_status);
return 0;
}
KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling This provides a way for userspace controls which sPAPR hcalls get handled in the kernel. Each hcall can be individually enabled or disabled for in-kernel handling, except for H_RTAS. The exception for H_RTAS is because userspace can already control whether individual RTAS functions are handled in-kernel or not via the KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for H_RTAS is out of the normal sequence of hcall numbers. Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM. The args field of the struct kvm_enable_cap specifies the hcall number in args[0] and the enable/disable flag in args[1]; 0 means disable in-kernel handling (so that the hcall will always cause an exit to userspace) and 1 means enable. Enabling or disabling in-kernel handling of an hcall is effective across the whole VM. The ability for KVM_ENABLE_CAP to be used on a VM file descriptor on PowerPC is new, added by this commit. The KVM_CAP_ENABLE_CAP_VM capability advertises that this ability exists. When a VM is created, an initial set of hcalls are enabled for in-kernel handling. The set that is enabled is the set that have an in-kernel implementation at this point. Any new hcall implementations from this point onwards should not be added to the default set without a good reason. No distinction is made between real-mode and virtual-mode hcall implementations; the one setting controls them both. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-06-02 10:02:59 +09:00
static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap)
{
int r;
if (cap->flags)
return -EINVAL;
switch (cap->cap) {
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
case KVM_CAP_PPC_ENABLE_HCALL: {
unsigned long hcall = cap->args[0];
r = -EINVAL;
if (hcall > MAX_HCALL_OPCODE || (hcall & 3) ||
cap->args[1] > 1)
break;
if (!kvmppc_book3s_hcall_implemented(kvm, hcall))
break;
KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling This provides a way for userspace controls which sPAPR hcalls get handled in the kernel. Each hcall can be individually enabled or disabled for in-kernel handling, except for H_RTAS. The exception for H_RTAS is because userspace can already control whether individual RTAS functions are handled in-kernel or not via the KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for H_RTAS is out of the normal sequence of hcall numbers. Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM. The args field of the struct kvm_enable_cap specifies the hcall number in args[0] and the enable/disable flag in args[1]; 0 means disable in-kernel handling (so that the hcall will always cause an exit to userspace) and 1 means enable. Enabling or disabling in-kernel handling of an hcall is effective across the whole VM. The ability for KVM_ENABLE_CAP to be used on a VM file descriptor on PowerPC is new, added by this commit. The KVM_CAP_ENABLE_CAP_VM capability advertises that this ability exists. When a VM is created, an initial set of hcalls are enabled for in-kernel handling. The set that is enabled is the set that have an in-kernel implementation at this point. Any new hcall implementations from this point onwards should not be added to the default set without a good reason. No distinction is made between real-mode and virtual-mode hcall implementations; the one setting controls them both. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-06-02 10:02:59 +09:00
if (cap->args[1])
set_bit(hcall / 4, kvm->arch.enabled_hcalls);
else
clear_bit(hcall / 4, kvm->arch.enabled_hcalls);
r = 0;
break;
}
#endif
default:
r = -EINVAL;
break;
}
return r;
}
long kvm_arch_vm_ioctl(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_GET_PVINFO: {
struct kvm_ppc_pvinfo pvinfo;
memset(&pvinfo, 0, sizeof(pvinfo));
r = kvm_vm_ioctl_get_pvinfo(&pvinfo);
if (copy_to_user(argp, &pvinfo, sizeof(pvinfo))) {
r = -EFAULT;
goto out;
}
break;
}
KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling This provides a way for userspace controls which sPAPR hcalls get handled in the kernel. Each hcall can be individually enabled or disabled for in-kernel handling, except for H_RTAS. The exception for H_RTAS is because userspace can already control whether individual RTAS functions are handled in-kernel or not via the KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for H_RTAS is out of the normal sequence of hcall numbers. Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM. The args field of the struct kvm_enable_cap specifies the hcall number in args[0] and the enable/disable flag in args[1]; 0 means disable in-kernel handling (so that the hcall will always cause an exit to userspace) and 1 means enable. Enabling or disabling in-kernel handling of an hcall is effective across the whole VM. The ability for KVM_ENABLE_CAP to be used on a VM file descriptor on PowerPC is new, added by this commit. The KVM_CAP_ENABLE_CAP_VM capability advertises that this ability exists. When a VM is created, an initial set of hcalls are enabled for in-kernel handling. The set that is enabled is the set that have an in-kernel implementation at this point. Any new hcall implementations from this point onwards should not be added to the default set without a good reason. No distinction is made between real-mode and virtual-mode hcall implementations; the one setting controls them both. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-06-02 10:02:59 +09:00
case KVM_ENABLE_CAP:
{
struct kvm_enable_cap cap;
r = -EFAULT;
if (copy_from_user(&cap, argp, sizeof(cap)))
goto out;
r = kvm_vm_ioctl_enable_cap(kvm, &cap);
break;
}
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CREATE_SPAPR_TCE_64: {
struct kvm_create_spapr_tce_64 create_tce_64;
r = -EFAULT;
if (copy_from_user(&create_tce_64, argp, sizeof(create_tce_64)))
goto out;
if (create_tce_64.flags) {
r = -EINVAL;
goto out;
}
r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
goto out;
}
case KVM_CREATE_SPAPR_TCE: {
struct kvm_create_spapr_tce create_tce;
struct kvm_create_spapr_tce_64 create_tce_64;
r = -EFAULT;
if (copy_from_user(&create_tce, argp, sizeof(create_tce)))
goto out;
create_tce_64.liobn = create_tce.liobn;
create_tce_64.page_shift = IOMMU_PAGE_SHIFT_4K;
create_tce_64.offset = 0;
create_tce_64.size = create_tce.window_size >>
IOMMU_PAGE_SHIFT_4K;
create_tce_64.flags = 0;
r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
goto out;
}
case KVM_PPC_GET_SMMU_INFO: {
struct kvm_ppc_smmu_info info;
struct kvm *kvm = filp->private_data;
memset(&info, 0, sizeof(info));
r = kvm->arch.kvm_ops->get_smmu_info(kvm, &info);
if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
r = -EFAULT;
break;
}
case KVM_PPC_RTAS_DEFINE_TOKEN: {
struct kvm *kvm = filp->private_data;
r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
break;
}
default: {
struct kvm *kvm = filp->private_data;
r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
}
#else /* CONFIG_PPC_BOOK3S_64 */
default:
r = -ENOTTY;
#endif
}
out:
return r;
}
static unsigned long lpid_inuse[BITS_TO_LONGS(KVMPPC_NR_LPIDS)];
static unsigned long nr_lpids;
long kvmppc_alloc_lpid(void)
{
long lpid;
do {
lpid = find_first_zero_bit(lpid_inuse, KVMPPC_NR_LPIDS);
if (lpid >= nr_lpids) {
pr_err("%s: No LPIDs free\n", __func__);
return -ENOMEM;
}
} while (test_and_set_bit(lpid, lpid_inuse));
return lpid;
}
EXPORT_SYMBOL_GPL(kvmppc_alloc_lpid);
void kvmppc_claim_lpid(long lpid)
{
set_bit(lpid, lpid_inuse);
}
EXPORT_SYMBOL_GPL(kvmppc_claim_lpid);
void kvmppc_free_lpid(long lpid)
{
clear_bit(lpid, lpid_inuse);
}
EXPORT_SYMBOL_GPL(kvmppc_free_lpid);
void kvmppc_init_lpid(unsigned long nr_lpids_param)
{
nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param);
memset(lpid_inuse, 0, sizeof(lpid_inuse));
}
EXPORT_SYMBOL_GPL(kvmppc_init_lpid);
int kvm_arch_init(void *opaque)
{
return 0;
}
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr);