blob: baeddb06811d738a6ea8be4ce920e5ea39a9645a [file] [log] [blame]
/*
* 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>
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
#include <linux/cpumask.h>
#include <linux/spinlock.h>
#include <linux/page-flags.h>
#include <linux/srcu.h>
#include <linux/miscdevice.h>
#include <linux/debugfs.h>
#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
#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>
#include <asm/cputhreads.h>
#include <asm/page.h>
#include <asm/hvcall.h>
#include <asm/switch_to.h>
#include <asm/smp.h>
#include <asm/dbell.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/module.h>
#include "book3s.h"
#define CREATE_TRACE_POINTS
#include "trace_hv.h"
/* #define EXIT_DEBUG */
/* #define EXIT_DEBUG_SIMPLE */
/* #define EXIT_DEBUG_INT */
/* Used to indicate that a guest page fault needs to be handled */
#define RESUME_PAGE_FAULT (RESUME_GUEST | RESUME_FLAG_ARCH1)
/* Used as a "null" value for timebase values */
#define TB_NIL (~(u64)0)
static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
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)");
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)");
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
static bool kvmppc_ipi_thread(int cpu)
{
/* 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())) {
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
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)
if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
xics_wake_cpu(cpu);
return true;
}
#endif
return false;
}
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
int cpu;
wait_queue_head_t *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
if (waitqueue_active(wqp)) {
wake_up_interruptible(wqp);
++vcpu->stat.halt_wakeup;
}
if (kvmppc_ipi_thread(vcpu->arch.thread_cpu))
return;
/* CPU points to the first thread of the core */
cpu = vcpu->cpu;
if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
smp_send_reschedule(cpu);
}
/*
* 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;
* 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.)
*/
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);
}
static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
unsigned long flags;
/*
* 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.
*/
if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
kvmppc_core_end_stolen(vc);
spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
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;
}
spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}
static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
unsigned long flags;
if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
kvmppc_core_start_stolen(vc);
spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
vcpu->arch.busy_preempt = mftb();
spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}
static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
{
/*
* 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;
vcpu->arch.shregs.msr = msr;
kvmppc_end_cede(vcpu);
}
static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
{
vcpu->arch.pvr = pvr;
}
static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
{
unsigned long pcr = 0;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
if (arch_compat) {
switch (arch_compat) {
case PVR_ARCH_205:
/*
* If an arch bit is set in PCR, all the defined
* higher-order arch bits also have to be set.
*/
pcr = PCR_ARCH_206 | PCR_ARCH_205;
break;
case PVR_ARCH_206:
case PVR_ARCH_206p:
pcr = PCR_ARCH_206;
break;
case PVR_ARCH_207:
break;
default:
return -EINVAL;
}
if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
/* POWER7 can't emulate POWER8 */
if (!(pcr & PCR_ARCH_206))
return -EINVAL;
pcr &= ~PCR_ARCH_206;
}
}
spin_lock(&vc->lock);
vc->arch_compat = arch_compat;
vc->pcr = pcr;
spin_unlock(&vc->lock);
return 0;
}
static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
{
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",
vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
vcpu->arch.last_inst);
}
static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
{
struct kvm_vcpu *ret;
mutex_lock(&kvm->lock);
ret = kvm_get_vcpu_by_id(kvm, id);
mutex_unlock(&kvm->lock);
return ret;
}
static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
{
vpa->__old_status |= LPPACA_OLD_SHARED_PROC;
vpa->yield_count = cpu_to_be32(1);
}
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;
}
/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
struct reg_vpa {
u32 dummy;
union {
__be16 hword;
__be32 word;
} length;
};
static int vpa_is_registered(struct kvmppc_vpa *vpap)
{
if (vpap->update_pending)
return vpap->next_gpa != 0;
return vpap->pinned_addr != NULL;
}
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;
unsigned long len, nb;
void *va;
struct kvm_vcpu *tvcpu;
int err;
int subfunc;
struct kvmppc_vpa *vpap;
tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
if (!tvcpu)
return H_PARAMETER;
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)
return H_PARAMETER;
/* convert logical addr to kernel addr and read length */
va = kvmppc_pin_guest_page(kvm, vpa, &nb);
if (va == NULL)
return H_PARAMETER;
if (subfunc == H_VPA_REG_VPA)
len = be16_to_cpu(((struct reg_vpa *)va)->length.hword);
else
len = be32_to_cpu(((struct reg_vpa *)va)->length.word);
kvmppc_unpin_guest_page(kvm, va, vpa, false);
/* 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))
break;
vpap = &tvcpu->arch.vpa;
err = 0;
break;
case H_VPA_REG_DTL: /* register DTL */
if (len < sizeof(struct dtl_entry))
break;
len -= len % sizeof(struct dtl_entry);
/* Check that they have previously registered a VPA */
err = H_RESOURCE;
if (!vpa_is_registered(&tvcpu->arch.vpa))
break;
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))
break;
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))
break;
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;
}
spin_unlock(&tvcpu->arch.vpa_update_lock);
return err;
}
static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
{
struct kvm *kvm = vcpu->kvm;
void *va;
unsigned long nb;
unsigned long gpa;
/*
* 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)
va = kvmppc_pin_guest_page(kvm, gpa, &nb);
spin_lock(&vcpu->arch.vpa_update_lock);
if (gpa == vpap->next_gpa)
break;
/* sigh... unpin that one and try again */
if (va)
kvmppc_unpin_guest_page(kvm, va, gpa, false);
}
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.
*/
kvmppc_unpin_guest_page(kvm, va, gpa, false);
va = NULL;
}
if (vpap->pinned_addr)
kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
vpap->dirty);
vpap->gpa = gpa;
vpap->pinned_addr = va;
vpap->dirty = false;
if (va)
vpap->pinned_end = va + vpap->len;
}
static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
{
if (!(vcpu->arch.vpa.update_pending ||
vcpu->arch.slb_shadow.update_pending ||
vcpu->arch.dtl.update_pending))
return;
spin_lock(&vcpu->arch.vpa_update_lock);
if (vcpu->arch.vpa.update_pending) {
kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
if (vcpu->arch.vpa.pinned_addr)
init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
}
if (vcpu->arch.dtl.update_pending) {
kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
vcpu->arch.dtl_index = 0;
}
if (vcpu->arch.slb_shadow.update_pending)
kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
spin_unlock(&vcpu->arch.vpa_update_lock);
}
/*
* 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;
unsigned long flags;
spin_lock_irqsave(&vc->stoltb_lock, flags);
p = vc->stolen_tb;
if (vc->vcore_state != VCORE_INACTIVE &&
vc->preempt_tb != TB_NIL)
p += now - vc->preempt_tb;
spin_unlock_irqrestore(&vc->stoltb_lock, flags);
return p;
}
static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
struct kvmppc_vcore *vc)
{
struct dtl_entry *dt;
struct lppaca *vpa;
unsigned long stolen;
unsigned long core_stolen;
u64 now;
dt = vcpu->arch.dtl_ptr;
vpa = vcpu->arch.vpa.pinned_addr;
now = mftb();
core_stolen = vcore_stolen_time(vc, now);
stolen = core_stolen - vcpu->arch.stolen_logged;
vcpu->arch.stolen_logged = core_stolen;
spin_lock_irq(&vcpu->arch.tbacct_lock);
stolen += vcpu->arch.busy_stolen;
vcpu->arch.busy_stolen = 0;
spin_unlock_irq(&vcpu->arch.tbacct_lock);
if (!dt || !vpa)
return;
memset(dt, 0, sizeof(struct dtl_entry));
dt->dispatch_reason = 7;
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);
++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();
vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index);
vcpu->arch.dtl.dirty = true;
}
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;
}
}
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 &&
vcore->vcore_state != VCORE_INACTIVE &&
vcore->runner)
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)
yield_count = be32_to_cpu(lppaca->yield_count);
spin_unlock(&vcpu->arch.vpa_update_lock);
return yield_count;
}
int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
{
unsigned long req = kvmppc_get_gpr(vcpu, 3);
unsigned long target, ret = H_SUCCESS;
int yield_count;
struct kvm_vcpu *tvcpu;
int idx, rc;
if (req <= MAX_HCALL_OPCODE &&
!test_bit(req/4, vcpu->kvm->arch.enabled_hcalls))
return RESUME_HOST;
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();
if (vcpu->arch.ceded) {
if (waitqueue_active(&vcpu->wq)) {
wake_up_interruptible(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
break;
case H_CONFER:
target = kvmppc_get_gpr(vcpu, 4);
if (target == -1)
break;
tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
if (!tvcpu) {
ret = H_PARAMETER;
break;
}
yield_count = kvmppc_get_gpr(vcpu, 5);
if (kvmppc_get_yield_count(tvcpu) != yield_count)
break;
kvm_arch_vcpu_yield_to(tvcpu);
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;
case H_RTAS:
if (list_empty(&vcpu->kvm->arch.rtas_tokens))
return RESUME_HOST;
idx = srcu_read_lock(&vcpu->kvm->srcu);
rc = kvmppc_rtas_hcall(vcpu);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (rc == -ENOENT)
return RESUME_HOST;
else if (rc == 0)
break;
/* Send the error out to userspace via KVM_RUN */
return rc;
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;
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;
case H_XIRR:
case H_CPPR:
case H_EOI:
case H_IPI:
case H_IPOLL:
case H_XIRR_X:
if (kvmppc_xics_enabled(vcpu)) {
ret = kvmppc_xics_hcall(vcpu, req);
break;
} /* fallthrough */
default:
return RESUME_HOST;
}
kvmppc_set_gpr(vcpu, 3, ret);
vcpu->arch.hcall_needed = 0;
return RESUME_GUEST;
}
static int kvmppc_hcall_impl_hv(unsigned long cmd)
{
switch (cmd) {
case H_CEDE:
case H_PROD:
case H_CONFER:
case H_REGISTER_VPA:
case H_SET_MODE:
case H_LOGICAL_CI_LOAD:
case H_LOGICAL_CI_STORE:
#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);
}
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;
}
}
static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
struct task_struct *tsk)
{
int r = RESUME_HOST;
vcpu->stat.sum_exits++;
/*
* 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;
}
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:
case BOOK3S_INTERRUPT_H_DOORBELL:
vcpu->stat.ext_intr_exits++;
r = RESUME_GUEST;
break;
/* HMI is hypervisor interrupt and host has handled it. Resume guest.*/
case BOOK3S_INTERRUPT_HMI:
case BOOK3S_INTERRUPT_PERFMON:
r = RESUME_GUEST;
break;
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;
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;
/* hypercall with MSR_PR has already been handled in rmode,
* and never reaches here.
*/
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;
}
/*
* 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.
*/
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
r = RESUME_PAGE_FAULT;
break;
case BOOK3S_INTERRUPT_H_INST_STORAGE:
vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
vcpu->arch.fault_dsisr = 0;
r = RESUME_PAGE_FAULT;
break;
/*
* This occurs if the guest executes an illegal instruction.
* 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.
*/
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
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;
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;
}
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);
r = RESUME_GUEST;
break;
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);
run->hw.hardware_exit_reason = vcpu->arch.trap;
r = RESUME_HOST;
break;
}
return r;
}
static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
int i;
memset(sregs, 0, sizeof(struct kvm_sregs));
sregs->pvr = vcpu->arch.pvr;
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;
}
static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
int i, j;
/* Only accept the same PVR as the host's, since we can't spoof it */
if (sregs->pvr != vcpu->arch.pvr)
return -EINVAL;
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;
}
static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
bool preserve_top32)
{
struct kvm *kvm = vcpu->kvm;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
u64 mask;
mutex_lock(&kvm->lock);
spin_lock(&vc->lock);
/*
* 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;
}
}
/*
* Userspace can only modify DPFD (default prefetch depth),
* ILE (interrupt little-endian) and TC (translation control).
* On POWER8 userspace can also modify AIL (alt. interrupt loc.)
*/
mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
if (cpu_has_feature(CPU_FTR_ARCH_207S))
mask |= LPCR_AIL;
/* Broken 32-bit version of LPCR must not clear top bits */
if (preserve_top32)
mask &= 0xFFFFFFFF;
vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
spin_unlock(&vc->lock);
mutex_unlock(&kvm->lock);
}
static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
union kvmppc_one_reg *val)
{
int r = 0;
long int i;
switch (id) {
case KVM_REG_PPC_DEBUG_INST:
*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
break;
case KVM_REG_PPC_HIOR:
*val = get_reg_val(id, 0);
break;
case KVM_REG_PPC_DABR:
*val = get_reg_val(id, vcpu->arch.dabr);
break;
case KVM_REG_PPC_DABRX:
*val = get_reg_val(id, vcpu->arch.dabrx);
break;
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;
case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
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]);
break;
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;
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;
case KVM_REG_PPC_SIER:
*val = get_reg_val(id, vcpu->arch.sier);
break;
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;
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);
break;
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;
case KVM_REG_PPC_TB_OFFSET:
*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
break;
case KVM_REG_PPC_LPCR:
case KVM_REG_PPC_LPCR_64:
*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
break;
case KVM_REG_PPC_PPR:
*val = get_reg_val(id, vcpu->arch.ppr);
break;
#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;
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
case KVM_REG_PPC_ARCH_COMPAT:
*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
break;
default:
r = -EINVAL;
break;
}
return r;
}
static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
union kvmppc_one_reg *val)
{
int r = 0;
long int i;
unsigned long addr, len;
switch (id) {
case KVM_REG_PPC_HIOR:
/* Only allow this to be set to zero */
if (set_reg_val(id, *val))
r = -EINVAL;
break;
case KVM_REG_PPC_DABR:
vcpu->arch.dabr = set_reg_val(id, *val);
break;
case KVM_REG_PPC_DABRX:
vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
break;
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;
case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
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;
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;
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;
case KVM_REG_PPC_SIER:
vcpu->arch.sier = set_reg_val(id, *val);
break;
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;
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);
break;
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;
if (addr && (len < sizeof(struct dtl_entry) ||
!vcpu->arch.vpa.next_gpa))
break;
len -= len % sizeof(struct dtl_entry);
r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
break;
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;
case KVM_REG_PPC_LPCR:
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);
break;
case KVM_REG_PPC_PPR:
vcpu->arch.ppr = set_reg_val(id, *val);
break;
#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;
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
case KVM_REG_PPC_ARCH_COMPAT:
r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
break;
default:
r = -EINVAL;
break;
}
return r;
}
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;
INIT_LIST_HEAD(&vcore->runnable_threads);
spin_lock_init(&vcore->lock);
spin_lock_init(&vcore->stoltb_lock);
init_waitqueue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
vcore->first_vcpuid = core * threads_per_subcore;
vcore->kvm = kvm;
INIT_LIST_HEAD(&vcore->preempt_list);
return vcore;
}
#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 */
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
unsigned int id)
{
struct kvm_vcpu *vcpu;
int err = -EINVAL;
int core;
struct kvmppc_vcore *vcore;
core = id / threads_per_subcore;
if (core >= KVM_MAX_VCORES)
goto out;
err = -ENOMEM;
vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
if (!vcpu)
goto out;
err = kvm_vcpu_init(vcpu, kvm, id);
if (err)
goto free_vcpu;
vcpu->arch.shared = &vcpu->arch.shregs;
#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
vcpu->arch.mmcr[0] = MMCR0_FC;
vcpu->arch.ctrl = CTRL_RUNLATCH;
/* default to host PVR, since we can't spoof it */
kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
spin_lock_init(&vcpu->arch.vpa_update_lock);
spin_lock_init(&vcpu->arch.tbacct_lock);
vcpu->arch.busy_preempt = TB_NIL;
vcpu->arch.intr_msr = MSR_SF | MSR_ME;
kvmppc_mmu_book3s_hv_init(vcpu);
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
init_waitqueue_head(&vcpu->arch.cpu_run);
mutex_lock(&kvm->lock);
vcore = kvm->arch.vcores[core];
if (!vcore) {
vcore = kvmppc_vcore_create(kvm, core);
kvm->arch.vcores[core] = vcore;
kvm->arch.online_vcores++;
}
mutex_unlock(&kvm->lock);
if (!vcore)
goto free_vcpu;
spin_lock(&vcore->lock);
++vcore->num_threads;
spin_unlock(&vcore->lock);
vcpu->arch.vcore = vcore;
vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
vcpu->arch.thread_cpu = -1;
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
debugfs_vcpu_init(vcpu, id);
return vcpu;
free_vcpu:
kmem_cache_free(kvm_vcpu_cache, vcpu);
out:
return ERR_PTR(err);
}
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);
}
static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
{
spin_lock(&vcpu->arch.vpa_update_lock);
unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
spin_unlock(&vcpu->arch.vpa_update_lock);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
{
/* Indicate we want to get back into the guest */
return 1;
}
static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
{
unsigned long dec_nsec, now;
now = get_tb();
if (now > vcpu->arch.dec_expires) {
/* decrementer has already gone negative */
kvmppc_core_queue_dec(vcpu);
kvmppc_core_prepare_to_enter(vcpu);
return;
}
dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
/ tb_ticks_per_sec;
hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
HRTIMER_MODE_REL);
vcpu->arch.timer_running = 1;
}
static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
{
vcpu->arch.ceded = 0;
if (vcpu->arch.timer_running) {
hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
vcpu->arch.timer_running = 0;
}
}
extern void __kvmppc_vcore_entry(void);
static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
struct kvm_vcpu *vcpu)
{
u64 now;
if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
return;
spin_lock_irq(&vcpu->arch.tbacct_lock);
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;
spin_unlock_irq(&vcpu->arch.tbacct_lock);
--vc->n_runnable;
list_del(&vcpu->arch.run_list);
}
static int kvmppc_grab_hwthread(int cpu)
{
struct paca_struct *tpaca;
long timeout = 10000;
tpaca = &paca[cpu];
/* Ensure the thread won't go into the kernel if it wakes */
tpaca->kvm_hstate.kvm_vcpu = NULL;
tpaca->kvm_hstate.kvm_vcore = NULL;
tpaca->kvm_hstate.napping = 0;
smp_wmb();
tpaca->kvm_hstate.hwthread_req = 1;
/*
* 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;
tpaca->kvm_hstate.kvm_vcore = NULL;
tpaca->kvm_hstate.kvm_split_mode = NULL;
}
static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
{
int cpu;
struct paca_struct *tpaca;
struct kvmppc_vcore *mvc = vc->master_vcore;
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;
}
tpaca = &paca[cpu];
tpaca->kvm_hstate.kvm_vcpu = vcpu;
tpaca->kvm_hstate.ptid = cpu - mvc->pcpu;
/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
smp_wmb();
tpaca->kvm_hstate.kvm_vcore = mvc;
if (cpu != smp_processor_id())
kvmppc_ipi_thread(cpu);
}
static void kvmppc_wait_for_nap(void)
{
int cpu = smp_processor_id();
int i, loops;
for (loops = 0; loops < 1000000; ++loops) {
/*
* Check if all threads are finished.
* We set the vcore pointer when starting a thread
* and the thread clears it when finished, so we look
* for any threads that still have a non-NULL vcore ptr.
*/
for (i = 1; i < threads_per_subcore; ++i)
if (paca[cpu + i].kvm_hstate.kvm_vcore)
break;
if (i == threads_per_subcore) {
HMT_medium();
return;
}
HMT_low();
}
HMT_medium();
for (i = 1; i < threads_per_subcore; ++i)
if (paca[cpu + i].kvm_hstate.kvm_vcore)
pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
/*
* Check that we are on thread 0 and that any other threads in
* this core are off-line. Then grab the threads so they can't
* enter the kernel.
*/
static int on_primary_thread(void)
{
int cpu = smp_processor_id();
int thr;
/* Are we on a primary subcore? */
if (cpu_thread_in_subcore(cpu))
return 0;
thr = 0;
while (++thr < threads_per_subcore)
if (cpu_online(cpu + thr))
return 0;
/* Grab all hw threads so they can't go into the kernel */
for (thr = 1; thr < threads_per_subcore; ++thr) {
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;
}
}
return 1;
}
/*
* 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();
if (vc->num_threads < threads_per_subcore) {
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)
{
struct preempted_vcore_list *lp;
kvmppc_core_end_stolen(vc);
if (!list_empty(&vc->preempt_list)) {
lp = &per_cpu(preempted_vcores, vc->pcpu);
spin_lock(&lp->lock);
list_del_init(&vc->preempt_list);
spin_unlock(&lp->lock);
}
vc->vcore_state = VCORE_INACTIVE;
}
/*
* This stores information about the virtual cores currently
* assigned to a physical core.
*/
struct core_info {
int n_subcores;
int max_subcore_threads;
int total_threads;
int subcore_threads[MAX_SUBCORES];
struct kvm *subcore_vm[MAX_SUBCORES];
struct list_head vcs[MAX_SUBCORES];
};
/*
* 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 };
static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc)
{
int sub;
memset(cip, 0, sizeof(*cip));
cip->n_subcores = 1;
cip->max_subcore_threads = vc->num_threads;
cip->total_threads = vc->num_threads;
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;
}
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;
}
/*
* See if the existing subcores can be split into 3 (or fewer) subcores
* of at most two threads each, so we can fit in another vcore. This
* assumes there are at most two subcores and at most 6 threads in total.
*/
static bool can_split_piggybacked_subcores(struct core_info *cip)
{
int sub, new_sub;
int large_sub = -1;
int thr;
int n_subcores = cip->n_subcores;
struct kvmppc_vcore *vc, *vcnext;
struct kvmppc_vcore *master_vc = NULL;
for (sub = 0; sub < cip->n_subcores; ++sub) {
if (cip->subcore_threads[sub] <= 2)
continue;
if (large_sub >= 0)
return false;
large_sub = sub;
vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore,
preempt_list);
if (vc->num_threads > 2)
return false;
n_subcores += (cip->subcore_threads[sub] - 1) >> 1;
}
if (large_sub < 0 || !subcore_config_ok(n_subcores + 1, 2))
return false;
/*
* Seems feasible, so go through and move vcores to new subcores.
* Note that when we have two or more vcores in one subcore,
* all those vcores must have only one thread each.
*/
new_sub = cip->n_subcores;
thr = 0;
sub = large_sub;
list_for_each_entry_safe(vc, vcnext, &cip->vcs[sub], preempt_list) {
if (thr >= 2) {
list_del(&vc->preempt_list);
list_add_tail(&vc->preempt_list, &cip->vcs[new_sub]);
/* vc->num_threads must be 1 */
if (++cip->subcore_threads[new_sub] == 1) {
cip->subcore_vm[new_sub] = vc->kvm;
init_master_vcore(vc);
master_vc = vc;
++cip->n_subcores;
} else {
vc->master_vcore = master_vc;
++new_sub;
}
}
thr += vc->num_threads;
}
cip->subcore_threads[large_sub] = 2;
cip->max_subcore_threads = 2;
return true;
}
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;
if (subcore_config_ok(cip->n_subcores + 1, n_threads)) {
cip->max_subcore_threads = n_threads;
} else if (cip->n_subcores <= 2 && cip->total_threads <= 6 &&
vc->num_threads <= 2) {
/*
* We may be able to fit another subcore in by
* splitting an existing subcore with 3 or 4
* threads into two 2-thread subcores, or one
* with 5 or 6 threads into three subcores.
* We can only do this if those subcores have
* piggybacked virtual cores.
*/
if (!can_split_piggybacked_subcores(cip))
return false;
} else {
return false;
}
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);
list_del(&vc->preempt_list);
list_add_tail(&vc->preempt_list, &cip->vcs[sub]);
return true;
}
static bool can_piggyback_subcore(struct kvmppc_vcore *pvc,
struct core_info *cip, int sub)
{
struct kvmppc_vcore *vc;
int n_thr;
vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore,
preempt_list);
/* require same VM and same per-core reg values */
if (pvc->kvm != vc->kvm ||
pvc->tb_offset != vc->tb_offset ||
pvc->pcr != vc->pcr ||
pvc->lpcr != vc->lpcr)
return false;
/* P8 guest with > 1 thread per core would see wrong TIR value */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
(vc->num_threads > 1 || pvc->num_threads > 1))
return false;
n_thr = cip->subcore_threads[sub] + pvc->num_threads;
if (n_thr > cip->max_subcore_threads) {
if (!subcore_config_ok(cip->n_subcores, n_thr))
return false;
cip->max_subcore_threads = n_thr;
}
cip->total_threads += pvc->num_threads;
cip->subcore_threads[sub] = n_thr;
pvc->master_vcore = vc;
list_del(&pvc->preempt_list);
list_add_tail(&pvc->preempt_list, &cip->vcs[sub]);
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)
{
int sub;
if (cip->total_threads + pvc->num_threads > target_threads)
return false;
for (sub = 0; sub < cip->n_subcores; ++sub)
if (cip->subcore_threads[sub] &&
can_piggyback_subcore(pvc, cip, sub))
return true;
if (can_dynamic_split(pvc, cip))
return true;
return false;
}
static void prepare_threads(struct kvmppc_vcore *vc)
{
struct kvm_vcpu *vcpu, *vnext;
list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
arch.run_list) {
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);
}
}
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)
{
int still_running = 0;
u64 now;
long ret;
struct kvm_vcpu *vcpu, *vnext;
spin_lock(&vc->lock);
now = get_tb();
list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
arch.run_list) {
/* 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;
if (is_kvmppc_resume_guest(vcpu->arch.ret)) {
if (vcpu->arch.pending_exceptions)
kvmppc_core_prepare_to_enter(vcpu);
if (vcpu->arch.ceded)
kvmppc_set_timer(vcpu);
else
++still_running;
} else {
kvmppc_remove_runnable(vc, vcpu);
wake_up(&vcpu->arch.cpu_run);
}
}
list_del_init(&vc->preempt_list);
if (!is_master) {
if (still_running > 0) {
kvmppc_vcore_preempt(vc);
} else if (vc->runner) {
vc->vcore_state = VCORE_PREEMPT;
kvmppc_core_start_stolen(vc);
} else {
vc->vcore_state = VCORE_INACTIVE;
}
if (vc->n_runnable > 0 && vc->runner == NULL) {
/* make sure there's a candidate runner awake */
vcpu = list_first_entry(&vc->runnable_threads,
struct kvm_vcpu, arch.run_list);
wake_up(&vcpu->arch.cpu_run);
}
}
spin_unlock(&vc->lock);
}
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
struct kvm_vcpu *vcpu, *vnext;
int i;
int srcu_idx;
struct core_info core_info;
struct kvmppc_vcore *pvc, *vcnext;
struct kvm_split_mode split_info, *sip;
int split, subcore_size, active;
int sub;
bool thr0_done;
unsigned long cmd_bit, stat_bit;
int pcpu, thr;
int target_threads;
/*
* 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;
/*
* Initialize *vc.
*/
init_master_vcore(vc);
vc->preempt_tb = TB_NIL;
/*
* 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.
*/
if ((threads_per_core > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
arch.run_list) {
vcpu->arch.ret = -EBUSY;
kvmppc_remove_runnable(vc, vcpu);
wake_up(&vcpu->arch.cpu_run);
}
goto out;
}
/*
* 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();
target_threads = threads_per_subcore;
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);
/* 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();
for (thr = 0; thr < threads_per_subcore; ++thr)
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();
}
}
/* 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;
list_for_each_entry(vcpu, &pvc->runnable_threads,
arch.run_list) {
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;
}
}
/*
* 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 */
/*
* 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);
vc->vcore_state = VCORE_RUNNING;
preempt_disable();
trace_kvmppc_run_core(vc, 0);
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_guest_enter();
srcu_idx = srcu_read_lock(&vc->kvm->srcu);
__kvmppc_vcore_entry();
srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
spin_lock(&vc->lock);
/* prevent other vcpu threads from doing kvmppc_start_thread() now */
vc->vcore_state = VCORE_EXITING;
/* wait for secondary threads to finish writing their state to memory */
kvmppc_wait_for_nap();
/* 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 */
for (i = 0; i < threads_per_subcore; ++i) {
kvmppc_release_hwthread(pcpu + i);
if (sip && sip->napped[i])
kvmppc_ipi_thread(pcpu + i);
}
spin_unlock(&vc->lock);
/* make sure updates to secondary vcpu structs are visible now */
smp_mb();
kvm_guest_exit();
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);
spin_lock(&vc->lock);
preempt_enable();
out:
vc->vcore_state = VCORE_INACTIVE;
trace_kvmppc_run_core(vc, 1);
}
/*
* Wait for some other vcpu thread to execute us, and
* wake us up when we need to handle something in the host.
*/
static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc,
struct kvm_vcpu *vcpu, int wait_state)
{
DEFINE_WAIT(wait);
prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
spin_unlock(&vc->lock);
schedule();
spin_lock(&vc->lock);
}
finish_wait(&vcpu->arch.cpu_run, &wait);
}
/*
* 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)
{
struct kvm_vcpu *vcpu;
int do_sleep = 1;
DEFINE_WAIT(wait);
prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
/*
* Check one last time for pending exceptions and ceded state after
* we put ourselves on the wait queue
*/
list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) {
do_sleep = 0;
break;
}
}
if (!do_sleep) {
finish_wait(&vc->wq, &wait);
return;
}
vc->vcore_state = VCORE_SLEEPING;
trace_kvmppc_vcore_blocked(vc, 0);
spin_unlock(&vc->lock);
schedule();
finish_wait(&vc->wq, &wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
trace_kvmppc_vcore_blocked(vc, 1);
}
static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
int n_ceded;
struct kvmppc_vcore *vc;
struct kvm_vcpu *v, *vn;
trace_kvmppc_run_vcpu_enter(vcpu);
kvm_run->exit_reason = 0;
vcpu->arch.ret = RESUME_GUEST;
vcpu->arch.trap = 0;
kvmppc_update_vpas(vcpu);
/*
* Synchronize with other threads in this virtual core
*/
vc = vcpu->arch.vcore;
spin_lock(&vc->lock);
vcpu->arch.ceded = 0;
vcpu->arch.run_task = current;
vcpu->arch.kvm_run = kvm_run;
vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
vcpu->arch.busy_preempt = TB_NIL;
list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
++vc->n_runnable;
/*
* 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.
*/
if (!signal_pending(current)) {
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);
kvmppc_start_thread(vcpu, vc);
trace_kvm_guest_enter(vcpu);
}
spin_unlock(&mvc->lock);
}
} else if (vc->vcore_state == VCORE_RUNNING &&
!VCORE_IS_EXITING(vc)) {
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu, vc);
trace_kvm_guest_enter(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
wake_up(&vc->wq);
}
}
while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
!signal_pending(current)) {
if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
kvmppc_vcore_end_preempt(vc);
if (vc->vcore_state != VCORE_INACTIVE) {
kvmppc_wait_for_exec(vc, vcpu, TASK_INTERRUPTIBLE);
continue;
}
list_for_each_entry_safe(v, vn, &vc->runnable_threads,
arch.run_list) {
kvmppc_core_prepare_to_enter(v);
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);
}
}
if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
break;
n_ceded = 0;
list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
if (!v->arch.pending_exceptions)
n_ceded += v->arch.ceded;
else
v->arch.ceded = 0;
}
vc->runner = vcpu;
if (n_ceded == vc->n_runnable) {
kvmppc_vcore_blocked(vc);
} else if (need_resched()) {
kvmppc_vcore_preempt(vc);
/* Let something else run */
cond_resched_lock(&vc->lock);
if (vc->vcore_state == VCORE_PREEMPT)
kvmppc_vcore_end_preempt(vc);
} else {
kvmppc_run_core(vc);
}
vc->runner = NULL;
}
while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
(vc->vcore_state == VCORE_RUNNING ||
vc->vcore_state == VCORE_EXITING ||
vc->vcore_state == VCORE_PIGGYBACK))
kvmppc_wait_for_exec(vc, vcpu, TASK_UNINTERRUPTIBLE);
if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
kvmppc_vcore_end_preempt(vc);
if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
kvmppc_remove_runnable(vc, vcpu);
vcpu->stat.signal_exits++;
kvm_run->exit_reason = KVM_EXIT_INTR;