aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-10-24 12:47:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-10-24 12:47:25 -0700
commit1765a1fe5d6f82c0eceb1ad10594cfc83759b6d0 (patch)
treea701020f0fa3a1932a36d174c5fffd20496303a9 /arch/powerpc/kvm
parentbdaf12b41235b0c59949914de022341e77907461 (diff)
parent2a31339aa014c0d0b97c57d3ebc997732f8f47fc (diff)
downloadkernel_samsung_smdk4412-1765a1fe5d6f82c0eceb1ad10594cfc83759b6d0.zip
kernel_samsung_smdk4412-1765a1fe5d6f82c0eceb1ad10594cfc83759b6d0.tar.gz
kernel_samsung_smdk4412-1765a1fe5d6f82c0eceb1ad10594cfc83759b6d0.tar.bz2
Merge branch 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm
* 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (321 commits) KVM: Drop CONFIG_DMAR dependency around kvm_iommu_map_pages KVM: Fix signature of kvm_iommu_map_pages stub KVM: MCE: Send SRAR SIGBUS directly KVM: MCE: Add MCG_SER_P into KVM_MCE_CAP_SUPPORTED KVM: fix typo in copyright notice KVM: Disable interrupts around get_kernel_ns() KVM: MMU: Avoid sign extension in mmu_alloc_direct_roots() pae root address KVM: MMU: move access code parsing to FNAME(walk_addr) function KVM: MMU: audit: check whether have unsync sps after root sync KVM: MMU: audit: introduce audit_printk to cleanup audit code KVM: MMU: audit: unregister audit tracepoints before module unloaded KVM: MMU: audit: fix vcpu's spte walking KVM: MMU: set access bit for direct mapping KVM: MMU: cleanup for error mask set while walk guest page table KVM: MMU: update 'root_hpa' out of loop in PAE shadow path KVM: x86 emulator: Eliminate compilation warning in x86_decode_insn() KVM: x86: Fix constant type in kvm_get_time_scale KVM: VMX: Add AX to list of registers clobbered by guest switch KVM guest: Move a printk that's using the clock before it's ready KVM: x86: TSC catchup mode ...
Diffstat (limited to 'arch/powerpc/kvm')
-rw-r--r--arch/powerpc/kvm/44x.c10
-rw-r--r--arch/powerpc/kvm/44x_tlb.c9
-rw-r--r--arch/powerpc/kvm/book3s.c272
-rw-r--r--arch/powerpc/kvm/book3s_32_mmu.c111
-rw-r--r--arch/powerpc/kvm/book3s_32_mmu_host.c75
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu.c42
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_host.c74
-rw-r--r--arch/powerpc/kvm/book3s_emulate.c73
-rw-r--r--arch/powerpc/kvm/book3s_mmu_hpte.c140
-rw-r--r--arch/powerpc/kvm/book3s_paired_singles.c11
-rw-r--r--arch/powerpc/kvm/book3s_rmhandlers.S32
-rw-r--r--arch/powerpc/kvm/booke.c108
-rw-r--r--arch/powerpc/kvm/booke.h10
-rw-r--r--arch/powerpc/kvm/booke_emulate.c14
-rw-r--r--arch/powerpc/kvm/booke_interrupts.S3
-rw-r--r--arch/powerpc/kvm/e500.c7
-rw-r--r--arch/powerpc/kvm/e500_tlb.c18
-rw-r--r--arch/powerpc/kvm/e500_tlb.h2
-rw-r--r--arch/powerpc/kvm/emulate.c36
-rw-r--r--arch/powerpc/kvm/powerpc.c88
-rw-r--r--arch/powerpc/kvm/trace.h239
21 files changed, 984 insertions, 390 deletions
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 73c0a3f..74d0e74 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -43,7 +43,7 @@ int kvmppc_core_check_processor_compat(void)
{
int r;
- if (strcmp(cur_cpu_spec->platform, "ppc440") == 0)
+ if (strncmp(cur_cpu_spec->platform, "ppc440", 6) == 0)
r = 0;
else
r = -ENOTSUPP;
@@ -72,6 +72,7 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
/* Since the guest can directly access the timebase, it must know the
* real timebase frequency. Accordingly, it must see the state of
* CCR1[TCS]. */
+ /* XXX CCR1 doesn't exist on all 440 SoCs. */
vcpu->arch.ccr1 = mfspr(SPRN_CCR1);
for (i = 0; i < ARRAY_SIZE(vcpu_44x->shadow_refs); i++)
@@ -123,8 +124,14 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
if (err)
goto free_vcpu;
+ vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+ if (!vcpu->arch.shared)
+ goto uninit_vcpu;
+
return vcpu;
+uninit_vcpu:
+ kvm_vcpu_uninit(vcpu);
free_vcpu:
kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
out:
@@ -135,6 +142,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
+ free_page((unsigned long)vcpu->arch.shared);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
}
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 9b9b5cd..5f3cff8 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -47,6 +47,7 @@
#ifdef DEBUG
void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
{
+ struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
struct kvmppc_44x_tlbe *tlbe;
int i;
@@ -221,14 +222,14 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
- unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+ unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
}
int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
- unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+ unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);
return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
}
@@ -354,7 +355,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
stlbe.word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf);
stlbe.word2 = kvmppc_44x_tlb_shadow_attrib(flags,
- vcpu->arch.msr & MSR_PR);
+ vcpu->arch.shared->msr & MSR_PR);
stlbe.tid = !(asid & 0xff);
/* Keep track of the reference so we can properly release it later. */
@@ -423,7 +424,7 @@ static int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
/* Does it match current guest AS? */
/* XXX what about IS != DS? */
- if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+ if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
return 0;
gpa = get_tlb_raddr(tlbe);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index a3cef30..e316847 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -17,6 +17,7 @@
#include <linux/kvm_host.h>
#include <linux/err.h>
#include <linux/slab.h>
+#include "trace.h"
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -35,7 +36,6 @@
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
/* #define EXIT_DEBUG */
-/* #define EXIT_DEBUG_SIMPLE */
/* #define DEBUG_EXT */
static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
@@ -105,65 +105,71 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
kvmppc_giveup_ext(vcpu, MSR_VSX);
}
-#if defined(EXIT_DEBUG)
-static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
-{
- u64 jd = mftb() - vcpu->arch.dec_jiffies;
- return vcpu->arch.dec - jd;
-}
-#endif
-
static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
{
- vcpu->arch.shadow_msr = vcpu->arch.msr;
+ ulong smsr = vcpu->arch.shared->msr;
+
/* Guest MSR values */
- vcpu->arch.shadow_msr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE |
- MSR_BE | MSR_DE;
+ smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE;
/* Process MSR values */
- vcpu->arch.shadow_msr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR |
- MSR_EE;
+ smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
/* External providers the guest reserved */
- vcpu->arch.shadow_msr |= (vcpu->arch.msr & vcpu->arch.guest_owned_ext);
+ smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext);
/* 64-bit Process MSR values */
#ifdef CONFIG_PPC_BOOK3S_64
- vcpu->arch.shadow_msr |= MSR_ISF | MSR_HV;
+ smsr |= MSR_ISF | MSR_HV;
#endif
+ vcpu->arch.shadow_msr = smsr;
}
void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
{
- ulong old_msr = vcpu->arch.msr;
+ ulong old_msr = vcpu->arch.shared->msr;
#ifdef EXIT_DEBUG
printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
#endif
msr &= to_book3s(vcpu)->msr_mask;
- vcpu->arch.msr = msr;
+ vcpu->arch.shared->msr = msr;
kvmppc_recalc_shadow_msr(vcpu);
- if (msr & (MSR_WE|MSR_POW)) {
+ if (msr & MSR_POW) {
if (!vcpu->arch.pending_exceptions) {
kvm_vcpu_block(vcpu);
vcpu->stat.halt_wakeup++;
+
+ /* Unset POW bit after we woke up */
+ msr &= ~MSR_POW;
+ vcpu->arch.shared->msr = msr;
}
}
- if ((vcpu->arch.msr & (MSR_PR|MSR_IR|MSR_DR)) !=
+ if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) !=
(old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
kvmppc_mmu_flush_segments(vcpu);
kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+
+ /* Preload magic page segment when in kernel mode */
+ if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) {
+ struct kvm_vcpu_arch *a = &vcpu->arch;
+
+ if (msr & MSR_DR)
+ kvmppc_mmu_map_segment(vcpu, a->magic_page_ea);
+ else
+ kvmppc_mmu_map_segment(vcpu, a->magic_page_pa);
+ }
}
/* Preload FPU if it's enabled */
- if (vcpu->arch.msr & MSR_FP)
+ if (vcpu->arch.shared->msr & MSR_FP)
kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
}
void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
{
- vcpu->arch.srr0 = kvmppc_get_pc(vcpu);
- vcpu->arch.srr1 = vcpu->arch.msr | flags;
+ vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
+ vcpu->arch.shared->srr1 = vcpu->arch.shared->msr | flags;
kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec);
vcpu->arch.mmu.reset_msr(vcpu);
}
@@ -180,6 +186,7 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec)
case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE; break;
case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT; break;
case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL; break;
+ case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL; break;
case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT; break;
case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM; break;
case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL; break;
@@ -199,6 +206,9 @@ static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
{
clear_bit(kvmppc_book3s_vec2irqprio(vec),
&vcpu->arch.pending_exceptions);
+
+ if (!vcpu->arch.pending_exceptions)
+ vcpu->arch.shared->int_pending = 0;
}
void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
@@ -237,13 +247,19 @@ void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
- kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
+ unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL;
+
+ if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
+ vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL;
+
+ kvmppc_book3s_queue_irqprio(vcpu, vec);
}
void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
+ kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
}
int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
@@ -251,14 +267,29 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
int deliver = 1;
int vec = 0;
ulong flags = 0ULL;
+ ulong crit_raw = vcpu->arch.shared->critical;
+ ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+ bool crit;
+
+ /* Truncate crit indicators in 32 bit mode */
+ if (!(vcpu->arch.shared->msr & MSR_SF)) {
+ crit_raw &= 0xffffffff;
+ crit_r1 &= 0xffffffff;
+ }
+
+ /* Critical section when crit == r1 */
+ crit = (crit_raw == crit_r1);
+ /* ... and we're in supervisor mode */
+ crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
switch (priority) {
case BOOK3S_IRQPRIO_DECREMENTER:
- deliver = vcpu->arch.msr & MSR_EE;
+ deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
vec = BOOK3S_INTERRUPT_DECREMENTER;
break;
case BOOK3S_IRQPRIO_EXTERNAL:
- deliver = vcpu->arch.msr & MSR_EE;
+ case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
+ deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
vec = BOOK3S_INTERRUPT_EXTERNAL;
break;
case BOOK3S_IRQPRIO_SYSTEM_RESET:
@@ -320,9 +351,27 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
return deliver;
}
+/*
+ * This function determines if an irqprio should be cleared once issued.
+ */
+static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
+{
+ switch (priority) {
+ case BOOK3S_IRQPRIO_DECREMENTER:
+ /* DEC interrupts get cleared by mtdec */
+ return false;
+ case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
+ /* External interrupts get cleared by userspace */
+ return false;
+ }
+
+ return true;
+}
+
void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
{
unsigned long *pending = &vcpu->arch.pending_exceptions;
+ unsigned long old_pending = vcpu->arch.pending_exceptions;
unsigned int priority;
#ifdef EXIT_DEBUG
@@ -332,8 +381,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
priority = __ffs(*pending);
while (priority < BOOK3S_IRQPRIO_MAX) {
if (kvmppc_book3s_irqprio_deliver(vcpu, priority) &&
- (priority != BOOK3S_IRQPRIO_DECREMENTER)) {
- /* DEC interrupts get cleared by mtdec */
+ clear_irqprio(vcpu, priority)) {
clear_bit(priority, &vcpu->arch.pending_exceptions);
break;
}
@@ -342,6 +390,12 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
BITS_PER_BYTE * sizeof(*pending),
priority + 1);
}
+
+ /* Tell the guest about our interrupt status */
+ if (*pending)
+ vcpu->arch.shared->int_pending = 1;
+ else if (old_pending)
+ vcpu->arch.shared->int_pending = 0;
}
void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
@@ -398,6 +452,25 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
}
}
+pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ ulong mp_pa = vcpu->arch.magic_page_pa;
+
+ /* Magic page override */
+ if (unlikely(mp_pa) &&
+ unlikely(((gfn << PAGE_SHIFT) & KVM_PAM) ==
+ ((mp_pa & PAGE_MASK) & KVM_PAM))) {
+ ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
+ pfn_t pfn;
+
+ pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
+ get_page(pfn_to_page(pfn));
+ return pfn;
+ }
+
+ return gfn_to_pfn(vcpu->kvm, gfn);
+}
+
/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
* make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
* emulate 32 bytes dcbz length.
@@ -415,8 +488,10 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
int i;
hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
- if (is_error_page(hpage))
+ if (is_error_page(hpage)) {
+ kvm_release_page_clean(hpage);
return;
+ }
hpage_offset = pte->raddr & ~PAGE_MASK;
hpage_offset &= ~0xFFFULL;
@@ -437,14 +512,14 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
struct kvmppc_pte *pte)
{
- int relocated = (vcpu->arch.msr & (data ? MSR_DR : MSR_IR));
+ int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR));
int r;
if (relocated) {
r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
} else {
pte->eaddr = eaddr;
- pte->raddr = eaddr & 0xffffffff;
+ pte->raddr = eaddr & KVM_PAM;
pte->vpage = VSID_REAL | eaddr >> 12;
pte->may_read = true;
pte->may_write = true;
@@ -533,6 +608,13 @@ mmio:
static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
+ ulong mp_pa = vcpu->arch.magic_page_pa;
+
+ if (unlikely(mp_pa) &&
+ unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) {
+ return 1;
+ }
+
return kvm_is_visible_gfn(vcpu->kvm, gfn);
}
@@ -545,8 +627,8 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
int page_found = 0;
struct kvmppc_pte pte;
bool is_mmio = false;
- bool dr = (vcpu->arch.msr & MSR_DR) ? true : false;
- bool ir = (vcpu->arch.msr & MSR_IR) ? true : false;
+ bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false;
+ bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false;
u64 vsid;
relocated = data ? dr : ir;
@@ -558,12 +640,12 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
pte.may_execute = true;
pte.may_read = true;
pte.may_write = true;
- pte.raddr = eaddr & 0xffffffff;
+ pte.raddr = eaddr & KVM_PAM;
pte.eaddr = eaddr;
pte.vpage = eaddr >> 12;
}
- switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+ switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
case 0:
pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
break;
@@ -571,7 +653,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
case MSR_IR:
vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
- if ((vcpu->arch.msr & (MSR_DR|MSR_IR)) == MSR_DR)
+ if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR)
pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
else
pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
@@ -594,20 +676,23 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
if (page_found == -ENOENT) {
/* Page not found in guest PTE entries */
- vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
- to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
- vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+ vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+ vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+ vcpu->arch.shared->msr |=
+ (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
kvmppc_book3s_queue_irqprio(vcpu, vec);
} else if (page_found == -EPERM) {
/* Storage protection */
- vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
- to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
- to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
- vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+ vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+ vcpu->arch.shared->dsisr =
+ to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
+ vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
+ vcpu->arch.shared->msr |=
+ (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
kvmppc_book3s_queue_irqprio(vcpu, vec);
} else if (page_found == -EINVAL) {
/* Page not found in guest SLB */
- vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+ vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
} else if (!is_mmio &&
kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
@@ -695,9 +780,11 @@ static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
if (ret == -ENOENT) {
- vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 33, 1);
- vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 34, 36, 0);
- vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0);
+ ulong msr = vcpu->arch.shared->msr;
+
+ msr = kvmppc_set_field(msr, 33, 33, 1);
+ msr = kvmppc_set_field(msr, 34, 36, 0);
+ vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0);
kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
return EMULATE_AGAIN;
}
@@ -736,7 +823,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
return RESUME_GUEST;
- if (!(vcpu->arch.msr & msr)) {
+ if (!(vcpu->arch.shared->msr & msr)) {
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
return RESUME_GUEST;
}
@@ -796,16 +883,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
run->exit_reason = KVM_EXIT_UNKNOWN;
run->ready_for_interrupt_injection = 1;
-#ifdef EXIT_DEBUG
- printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n",
- exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
- kvmppc_get_dec(vcpu), to_svcpu(vcpu)->shadow_srr1);
-#elif defined (EXIT_DEBUG_SIMPLE)
- if ((exit_nr != 0x900) && (exit_nr != 0x500))
- printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n",
- exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
- vcpu->arch.msr);
-#endif
+
+ trace_kvm_book3s_exit(exit_nr, vcpu);
kvm_resched(vcpu);
switch (exit_nr) {
case BOOK3S_INTERRUPT_INST_STORAGE:
@@ -836,9 +915,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
r = RESUME_GUEST;
} else {
- vcpu->arch.msr |= to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
+ vcpu->arch.shared->msr |=
+ to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
- kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
r = RESUME_GUEST;
}
break;
@@ -861,17 +940,16 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
} else {
- vcpu->arch.dear = dar;
- to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
+ vcpu->arch.shared->dar = dar;
+ vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
- kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFUL);
r = RESUME_GUEST;
}
break;
}
case BOOK3S_INTERRUPT_DATA_SEGMENT:
if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
- vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+ vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
kvmppc_book3s_queue_irqprio(vcpu,
BOOK3S_INTERRUPT_DATA_SEGMENT);
}
@@ -904,7 +982,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
program_interrupt:
flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
- if (vcpu->arch.msr & MSR_PR) {
+ if (vcpu->arch.shared->msr & MSR_PR) {
#ifdef EXIT_DEBUG
printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
#endif
@@ -941,10 +1019,10 @@ program_interrupt:
break;
}
case BOOK3S_INTERRUPT_SYSCALL:
- // XXX make user settable
if (vcpu->arch.osi_enabled &&
(((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
(((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
+ /* MOL hypercalls */
u64 *gprs = run->osi.gprs;
int i;
@@ -953,8 +1031,13 @@ program_interrupt:
gprs[i] = kvmppc_get_gpr(vcpu, i);
vcpu->arch.osi_needed = 1;
r = RESUME_HOST_NV;
-
+ } else if (!(vcpu->arch.shared->msr & MSR_PR) &&
+ (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
+ /* KVM PV hypercalls */
+ kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+ r = RESUME_GUEST;
} else {
+ /* Guest syscalls */
vcpu->stat.syscall_exits++;
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
r = RESUME_GUEST;
@@ -989,9 +1072,9 @@ program_interrupt:
}
case BOOK3S_INTERRUPT_ALIGNMENT:
if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
- to_book3s(vcpu)->dsisr = kvmppc_alignment_dsisr(vcpu,
+ vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
kvmppc_get_last_inst(vcpu));
- vcpu->arch.dear = kvmppc_alignment_dar(vcpu,
+ vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu,
kvmppc_get_last_inst(vcpu));
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
}
@@ -1031,9 +1114,7 @@ program_interrupt:
}
}
-#ifdef EXIT_DEBUG
- printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, kvmppc_get_pc(vcpu), r);
-#endif
+ trace_kvm_book3s_reenter(r, vcpu);
return r;
}
@@ -1052,14 +1133,14 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
regs->ctr = kvmppc_get_ctr(vcpu);
regs->lr = kvmppc_get_lr(vcpu);
regs->xer = kvmppc_get_xer(vcpu);
- regs->msr = vcpu->arch.msr;
- regs->srr0 = vcpu->arch.srr0;
- regs->srr1 = vcpu->arch.srr1;
+ regs->msr = vcpu->arch.shared->msr;
+ regs->srr0 = vcpu->arch.shared->srr0;
+ regs->srr1 = vcpu->arch.shared->srr1;
regs->pid = vcpu->arch.pid;
- regs->sprg0 = vcpu->arch.sprg0;
- regs->sprg1 = vcpu->arch.sprg1;
- regs->sprg2 = vcpu->arch.sprg2;
- regs->sprg3 = vcpu->arch.sprg3;
+ regs->sprg0 = vcpu->arch.shared->sprg0;
+ regs->sprg1 = vcpu->arch.shared->sprg1;
+ regs->sprg2 = vcpu->arch.shared->sprg2;
+ regs->sprg3 = vcpu->arch.shared->sprg3;
regs->sprg5 = vcpu->arch.sprg4;
regs->sprg6 = vcpu->arch.sprg5;
regs->sprg7 = vcpu->arch.sprg6;
@@ -1080,12 +1161,12 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
kvmppc_set_lr(vcpu, regs->lr);
kvmppc_set_xer(vcpu, regs->xer);
kvmppc_set_msr(vcpu, regs->msr);
- vcpu->arch.srr0 = regs->srr0;
- vcpu->arch.srr1 = regs->srr1;
- vcpu->arch.sprg0 = regs->sprg0;
- vcpu->arch.sprg1 = regs->sprg1;
- vcpu->arch.sprg2 = regs->sprg2;
- vcpu->arch.sprg3 = regs->sprg3;
+ vcpu->arch.shared->srr0 = regs->srr0;
+ vcpu->arch.shared->srr1 = regs->srr1;
+ vcpu->arch.shared->sprg0 = regs->sprg0;
+ vcpu->arch.shared->sprg1 = regs->sprg1;
+ vcpu->arch.shared->sprg2 = regs->sprg2;
+ vcpu->arch.shared->sprg3 = regs->sprg3;
vcpu->arch.sprg5 = regs->sprg4;
vcpu->arch.sprg6 = regs->sprg5;
vcpu->arch.sprg7 = regs->sprg6;
@@ -1111,10 +1192,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv;
}
} else {
- for (i = 0; i < 16; i++) {
- sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
- sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
- }
+ for (i = 0; i < 16; i++)
+ sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i];
+
for (i = 0; i < 8; i++) {
sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
@@ -1225,6 +1305,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
struct kvmppc_vcpu_book3s *vcpu_book3s;
struct kvm_vcpu *vcpu;
int err = -ENOMEM;
+ unsigned long p;
vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s));
if (!vcpu_book3s)
@@ -1242,6 +1323,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
if (err)
goto free_shadow_vcpu;
+ p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
+ /* the real shared page fills the last 4k of our page */
+ vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
+ if (!p)
+ goto uninit_vcpu;
+
vcpu->arch.host_retip = kvm_return_point;
vcpu->arch.host_msr = mfmsr();
#ifdef CONFIG_PPC_BOOK3S_64
@@ -1268,10 +1355,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
err = kvmppc_mmu_init(vcpu);
if (err < 0)
- goto free_shadow_vcpu;
+ goto uninit_vcpu;
return vcpu;
+uninit_vcpu:
+ kvm_vcpu_uninit(vcpu);
free_shadow_vcpu:
kfree(vcpu_book3s->shadow_vcpu);
free_vcpu:
@@ -1284,6 +1373,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+ free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
kvm_vcpu_uninit(vcpu);
kfree(vcpu_book3s->shadow_vcpu);
vfree(vcpu_book3s);
@@ -1346,7 +1436,7 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
local_irq_enable();
/* Preload FPU if it's enabled */
- if (vcpu->arch.msr & MSR_FP)
+ if (vcpu->arch.shared->msr & MSR_FP)
kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 3292d76..c8cefdd 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -58,14 +58,39 @@ static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
#endif
}
+static inline u32 sr_vsid(u32 sr_raw)
+{
+ return sr_raw & 0x0fffffff;
+}
+
+static inline bool sr_valid(u32 sr_raw)
+{
+ return (sr_raw & 0x80000000) ? false : true;
+}
+
+static inline bool sr_ks(u32 sr_raw)
+{
+ return (sr_raw & 0x40000000) ? true: false;
+}
+
+static inline bool sr_kp(u32 sr_raw)
+{
+ return (sr_raw & 0x20000000) ? true: false;
+}
+
+static inline bool sr_nx(u32 sr_raw)
+{
+ return (sr_raw & 0x10000000) ? true: false;
+}
+
static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *pte, bool data);
static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
u64 *vsid);
-static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr)
+static u32 find_sr(struct kvm_vcpu *vcpu, gva_t eaddr)
{
- return &vcpu_book3s->sr[(eaddr >> 28) & 0xf];
+ return vcpu->arch.shared->sr[(eaddr >> 28) & 0xf];
}
static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
@@ -87,7 +112,7 @@ static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
}
static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3s,
- struct kvmppc_sr *sre, gva_t eaddr,
+ u32 sre, gva_t eaddr,
bool primary)
{
u32 page, hash, pteg, htabmask;
@@ -96,7 +121,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
page = (eaddr & 0x0FFFFFFF) >> 12;
htabmask = ((vcpu_book3s->sdr1 & 0x1FF) << 16) | 0xFFC0;
- hash = ((sre->vsid ^ page) << 6);
+ hash = ((sr_vsid(sre) ^ page) << 6);
if (!primary)
hash = ~hash;
hash &= htabmask;
@@ -104,8 +129,8 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
pteg = (vcpu_book3s->sdr1 & 0xffff0000) | hash;
dprintk("MMU: pc=0x%lx eaddr=0x%lx sdr1=0x%llx pteg=0x%x vsid=0x%x\n",
- vcpu_book3s->vcpu.arch.pc, eaddr, vcpu_book3s->sdr1, pteg,
- sre->vsid);
+ kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg,
+ sr_vsid(sre));
r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
if (kvm_is_error_hva(r))
@@ -113,10 +138,9 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
return r | (pteg & ~PAGE_MASK);
}
-static u32 kvmppc_mmu_book3s_32_get_ptem(struct kvmppc_sr *sre, gva_t eaddr,
- bool primary)
+static u32 kvmppc_mmu_book3s_32_get_ptem(u32 sre, gva_t eaddr, bool primary)
{
- return ((eaddr & 0x0fffffff) >> 22) | (sre->vsid << 7) |
+ return ((eaddr & 0x0fffffff) >> 22) | (sr_vsid(sre) << 7) |
(primary ? 0 : 0x40) | 0x80000000;
}
@@ -133,7 +157,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
else
bat = &vcpu_book3s->ibat[i];
- if (vcpu->arch.msr & MSR_PR) {
+ if (vcpu->arch.shared->msr & MSR_PR) {
if (!bat->vp)
continue;
} else {
@@ -180,17 +204,17 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
bool primary)
{
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
- struct kvmppc_sr *sre;
+ u32 sre;
hva_t ptegp;
u32 pteg[16];
u32 ptem = 0;
int i;
int found = 0;
- sre = find_sr(vcpu_book3s, eaddr);
+ sre = find_sr(vcpu, eaddr);
dprintk_pte("SR 0x%lx: vsid=0x%x, raw=0x%x\n", eaddr >> 28,
- sre->vsid, sre->raw);
+ sr_vsid(sre), sre);
pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
@@ -214,8 +238,8 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
pte->raddr = (pteg[i+1] & ~(0xFFFULL)) | (eaddr & 0xFFF);
pp = pteg[i+1] & 3;
- if ((sre->Kp && (vcpu->arch.msr & MSR_PR)) ||
- (sre->Ks && !(vcpu->arch.msr & MSR_PR)))
+ if ((sr_kp(sre) && (vcpu->arch.shared->msr & MSR_PR)) ||
+ (sr_ks(sre) && !(vcpu->arch.shared->msr & MSR_PR)))
pp |= 4;
pte->may_write = false;
@@ -269,7 +293,7 @@ no_page_found:
dprintk_pte("KVM MMU: No PTE found (sdr1=0x%llx ptegp=0x%lx)\n",
to_book3s(vcpu)->sdr1, ptegp);
for (i=0; i<16; i+=2) {
- dprintk_pte(" %02d: 0x%x - 0x%x (0x%llx)\n",
+ dprintk_pte(" %02d: 0x%x - 0x%x (0x%x)\n",
i, pteg[i], pteg[i+1], ptem);
}
}
@@ -281,8 +305,24 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *pte, bool data)
{
int r;
+ ulong mp_ea = vcpu->arch.magic_page_ea;
pte->eaddr = eaddr;
+
+ /* Magic page override */
+ if (unlikely(mp_ea) &&
+ unlikely((eaddr & ~0xfffULL) == (mp_ea & ~0xfffULL)) &&
+ !(vcpu->arch.shared->msr & MSR_PR)) {
+ pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
+ pte->raddr = vcpu->arch.magic_page_pa | (pte->raddr & 0xfff);
+ pte->raddr &= KVM_PAM;
+ pte->may_execute = true;
+ pte->may_read = true;
+ pte->may_write = true;
+
+ return 0;
+ }
+
r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data);
if (r < 0)
r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true);
@@ -295,30 +335,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
static u32 kvmppc_mmu_book3s_32_mfsrin(struct kvm_vcpu *vcpu, u32 srnum)
{
- return to_book3s(vcpu)->sr[srnum].raw;
+ return vcpu->arch.shared->sr[srnum];
}
static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
ulong value)
{
- struct kvmppc_sr *sre;
-
- sre = &to_book3s(vcpu)->sr[srnum];
-
- /* Flush any left-over shadows from the previous SR */
-
- /* XXX Not necessary? */
- /* kvmppc_mmu_pte_flush(vcpu, ((u64)sre->vsid) << 28, 0xf0000000ULL); */
-
- /* And then put in the new SR */
- sre->raw = value;
- sre->vsid = (value & 0x0fffffff);
- sre->valid = (value & 0x80000000) ? false : true;
- sre->Ks = (value & 0x40000000) ? true : false;
- sre->Kp = (value & 0x20000000) ? true : false;
- sre->nx = (value & 0x10000000) ? true : false;
-
- /* Map the new segment */
+ vcpu->arch.shared->sr[srnum] = value;
kvmppc_mmu_map_segment(vcpu, srnum << SID_SHIFT);
}
@@ -331,19 +354,19 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
u64 *vsid)
{
ulong ea = esid << SID_SHIFT;
- struct kvmppc_sr *sr;
+ u32 sr;
u64 gvsid = esid;
- if (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
- sr = find_sr(to_book3s(vcpu), ea);
- if (sr->valid)
- gvsid = sr->vsid;
+ if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+ sr = find_sr(vcpu, ea);
+ if (sr_valid(sr))
+ gvsid = sr_vsid(sr);
}
/* In case we only have one of MSR_IR or MSR_DR set, let's put
that in the real-mode context (and hope RM doesn't access
high memory) */
- switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+ switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
case 0:
*vsid = VSID_REAL | esid;
break;
@@ -354,8 +377,8 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
*vsid = VSID_REAL_DR | gvsid;
break;
case MSR_DR|MSR_IR:
- if (sr->valid)
- *vsid = sr->vsid;
+ if (sr_valid(sr))
+ *vsid = sr_vsid(sr);
else
*vsid = VSID_BAT | gvsid;
break;
@@ -363,7 +386,7 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
BUG();
}
- if (vcpu->arch.msr & MSR_PR)
+ if (vcpu->arch.shared->msr & MSR_PR)
*vsid |= VSID_PR;
return 0;
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 0b51ef8..9fecbfb 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -19,7 +19,6 @@
*/
#include <linux/kvm_host.h>
-#include <linux/hash.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
@@ -77,7 +76,14 @@ void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
* a hash, so we don't waste cycles on looping */
static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
{
- return hash_64(gvsid, SID_MAP_BITS);
+ return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
}
@@ -86,7 +92,7 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
struct kvmppc_sid_map *map;
u16 sid_map_mask;
- if (vcpu->arch.msr & MSR_PR)
+ if (vcpu->arch.shared->msr & MSR_PR)
gvsid |= VSID_PR;
sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
@@ -147,8 +153,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
struct hpte_cache *pte;
/* Get host physical address for gpa */
- hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
- if (kvm_is_error_hva(hpaddr)) {
+ hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
+ if (is_error_pfn(hpaddr)) {
printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
orig_pte->eaddr);
return -EINVAL;
@@ -253,7 +259,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
u16 sid_map_mask;
static int backwards_map = 0;
- if (vcpu->arch.msr & MSR_PR)
+ if (vcpu->arch.shared->msr & MSR_PR)
gvsid |= VSID_PR;
/* We might get collisions that trap in preceding order, so let's
@@ -269,18 +275,15 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
backwards_map = !backwards_map;
/* Uh-oh ... out of mappings. Let's flush! */
- if (vcpu_book3s->vsid_next >= vcpu_book3s->vsid_max) {
- vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+ if (vcpu_book3s->vsid_next >= VSID_POOL_SIZE) {
+ vcpu_book3s->vsid_next = 0;
memset(vcpu_book3s->sid_map, 0,
sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
kvmppc_mmu_pte_flush(vcpu, 0, 0);
kvmppc_mmu_flush_segments(vcpu);
}
- map->host_vsid = vcpu_book3s->vsid_next;
-
- /* Would have to be 111 to be completely aligned with the rest of
- Linux, but that is just way too little space! */
- vcpu_book3s->vsid_next+=1;
+ map->host_vsid = vcpu_book3s->vsid_pool[vcpu_book3s->vsid_next];
+ vcpu_book3s->vsid_next++;
map->guest_vsid = gvsid;
map->valid = true;
@@ -327,40 +330,38 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
+ int i;
+
kvmppc_mmu_hpte_destroy(vcpu);
preempt_disable();
- __destroy_context(to_book3s(vcpu)->context_id);
+ for (i = 0; i < SID_CONTEXTS; i++)
+ __destroy_context(to_book3s(vcpu)->context_id[i]);
preempt_enable();
}
/* From mm/mmu_context_hash32.c */
-#define CTX_TO_VSID(ctx) (((ctx) * (897 * 16)) & 0xffffff)
+#define CTX_TO_VSID(c, id) ((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff)
int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
int err;
ulong sdr1;
+ int i;
+ int j;
- err = __init_new_context();
- if (err < 0)
- return -1;
- vcpu3s->context_id = err;
-
- vcpu3s->vsid_max = CTX_TO_VSID(vcpu3s->context_id + 1) - 1;
- vcpu3s->vsid_first = CTX_TO_VSID(vcpu3s->context_id);
-
-#if 0 /* XXX still doesn't guarantee uniqueness */
- /* We could collide with the Linux vsid space because the vsid
- * wraps around at 24 bits. We're safe if we do our own space
- * though, so let's always set the highest bit. */
+ for (i = 0; i < SID_CONTEXTS; i++) {
+ err = __init_new_context();
+ if (err < 0)
+ goto init_fail;
+ vcpu3s->context_id[i] = err;
- vcpu3s->vsid_max |= 0x00800000;
- vcpu3s->vsid_first |= 0x00800000;
-#endif
- BUG_ON(vcpu3s->vsid_max < vcpu3s->vsid_first);
+ /* Remember context id for this combination */
+ for (j = 0; j < 16; j++)
+ vcpu3s->vsid_pool[(i * 16) + j] = CTX_TO_VSID(err, j);
+ }
- vcpu3s->vsid_next = vcpu3s->vsid_first;
+ vcpu3s->vsid_next = 0;
/* Remember where the HTAB is */
asm ( "mfsdr1 %0" : "=r"(sdr1) );
@@ -370,4 +371,14 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
kvmppc_mmu_hpte_init(vcpu);
return 0;
+
+init_fail:
+ for (j = 0; j < i; j++) {
+ if (!vcpu3s->context_id[j])
+ continue;
+
+ __destroy_context(to_book3s(vcpu)->context_id[j]);
+ }
+
+ return -1;
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 4025ea2..d7889ef 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -163,6 +163,22 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
bool found = false;
bool perm_err = false;
int second = 0;
+ ulong mp_ea = vcpu->arch.magic_page_ea;
+
+ /* Magic page override */
+ if (unlikely(mp_ea) &&
+ unlikely((eaddr & ~0xfffULL) == (mp_ea & ~0xfffULL)) &&
+ !(vcpu->arch.shared->msr & MSR_PR)) {
+ gpte->eaddr = eaddr;
+ gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
+ gpte->raddr = vcpu->arch.magic_page_pa | (gpte->raddr & 0xfff);
+ gpte->raddr &= KVM_PAM;
+ gpte->may_execute = true;
+ gpte->may_read = true;
+ gpte->may_write = true;
+
+ return 0;
+ }
slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, eaddr);
if (!slbe)
@@ -180,9 +196,9 @@ do_second:
goto no_page_found;
}
- if ((vcpu->arch.msr & MSR_PR) && slbe->Kp)
+ if ((vcpu->arch.shared->msr & MSR_PR) && slbe->Kp)
key = 4;
- else if (!(vcpu->arch.msr & MSR_PR) && slbe->Ks)
+ else if (!(vcpu->arch.shared->msr & MSR_PR) && slbe->Ks)
key = 4;
for (i=0; i<16; i+=2) {
@@ -381,7 +397,7 @@ static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu)
for (i = 1; i < vcpu_book3s->slb_nr; i++)
vcpu_book3s->slb[i].valid = false;
- if (vcpu->arch.msr & MSR_IR) {
+ if (vcpu->arch.shared->msr & MSR_IR) {
kvmppc_mmu_flush_segments(vcpu);
kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
}
@@ -445,14 +461,15 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
ulong ea = esid << SID_SHIFT;
struct kvmppc_slb *slb;
u64 gvsid = esid;
+ ulong mp_ea = vcpu->arch.magic_page_ea;
- if (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+ if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
if (slb)
gvsid = slb->vsid;
}
- switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+ switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
case 0:
*vsid = VSID_REAL | esid;
break;
@@ -464,7 +481,7 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
break;
case MSR_DR|MSR_IR:
if (!slb)
- return -ENOENT;
+ goto no_slb;
*vsid = gvsid;
break;
@@ -473,10 +490,21 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
break;
}
- if (vcpu->arch.msr & MSR_PR)
+ if (vcpu->arch.shared->msr & MSR_PR)
*vsid |= VSID_PR;
return 0;
+
+no_slb:
+ /* Catch magic page case */
+ if (unlikely(mp_ea) &&
+ unlikely(esid == (mp_ea >> SID_SHIFT)) &&
+ !(vcpu->arch.shared->msr & MSR_PR)) {
+ *vsid = VSID_REAL | esid;
+ return 0;
+ }
+
+ return -EINVAL;
}
static bool kvmppc_mmu_book3s_64_is_dcbz32(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 384179a..fa2f084 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -20,7 +20,6 @@
*/
#include <linux/kvm_host.h>
-#include <linux/hash.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
@@ -28,24 +27,9 @@
#include <asm/machdep.h>
#include <asm/mmu_context.h>
#include <asm/hw_irq.h>
+#include "trace.h"
#define PTE_SIZE 12
-#define VSID_ALL 0
-
-/* #define DEBUG_MMU */
-/* #define DEBUG_SLB */
-
-#ifdef DEBUG_MMU
-#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
-#else
-#define dprintk_mmu(a, ...) do { } while(0)
-#endif
-
-#ifdef DEBUG_SLB
-#define dprintk_slb(a, ...) printk(KERN_INFO a, __VA_ARGS__)
-#else
-#define dprintk_slb(a, ...) do { } while(0)
-#endif
void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
@@ -58,34 +42,39 @@ void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
* a hash, so we don't waste cycles on looping */
static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
{
- return hash_64(gvsid, SID_MAP_BITS);
+ return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+ ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
}
+
static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
{
struct kvmppc_sid_map *map;
u16 sid_map_mask;
- if (vcpu->arch.msr & MSR_PR)
+ if (vcpu->arch.shared->msr & MSR_PR)
gvsid |= VSID_PR;
sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
map = &to_book3s(vcpu)->sid_map[sid_map_mask];
- if (map->guest_vsid == gvsid) {
- dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n",
- gvsid, map->host_vsid);
+ if (map->valid && (map->guest_vsid == gvsid)) {
+ trace_kvm_book3s_slb_found(gvsid, map->host_vsid);
return map;
}
map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
- if (map->guest_vsid == gvsid) {
- dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
- gvsid, map->host_vsid);
+ if (map->valid && (map->guest_vsid == gvsid)) {
+ trace_kvm_book3s_slb_found(gvsid, map->host_vsid);
return map;
}
- dprintk_slb("SLB: Searching %d/%d: 0x%llx -> not found\n",
- sid_map_mask, SID_MAP_MASK - sid_map_mask, gvsid);
+ trace_kvm_book3s_slb_fail(sid_map_mask, gvsid);
return NULL;
}
@@ -101,18 +90,13 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
struct kvmppc_sid_map *map;
/* Get host physical address for gpa */
- hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
- if (kvm_is_error_hva(hpaddr)) {
+ hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
+ if (is_error_pfn(hpaddr)) {
printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
return -EINVAL;
}
hpaddr <<= PAGE_SHIFT;
-#if PAGE_SHIFT == 12
-#elif PAGE_SHIFT == 16
- hpaddr |= orig_pte->raddr & 0xf000;
-#else
-#error Unknown page size
-#endif
+ hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
/* and write the mapping ea -> hpa into the pt */
vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
@@ -161,10 +145,7 @@ map_again:
} else {
struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu);
- dprintk_mmu("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx\n",
- ((rflags & HPTE_R_PP) == 3) ? '-' : 'w',
- (rflags & HPTE_R_N) ? '-' : 'x',
- orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr);
+ trace_kvm_book3s_64_mmu_map(rflags, hpteg, va, hpaddr, orig_pte);
/* The ppc_md code may give us a secondary entry even though we
asked for a primary. Fix up. */
@@ -191,7 +172,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
u16 sid_map_mask;
static int backwards_map = 0;
- if (vcpu->arch.msr & MSR_PR)
+ if (vcpu->arch.shared->msr & MSR_PR)
gvsid |= VSID_PR;
/* We might get collisions that trap in preceding order, so let's
@@ -219,8 +200,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
map->guest_vsid = gvsid;
map->valid = true;
- dprintk_slb("SLB: New mapping at %d: 0x%llx -> 0x%llx\n",
- sid_map_mask, gvsid, map->host_vsid);
+ trace_kvm_book3s_slb_map(sid_map_mask, gvsid, map->host_vsid);
return map;
}
@@ -292,7 +272,7 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
to_svcpu(vcpu)->slb[slb_index].esid = slb_esid;
to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid;
- dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid);
+ trace_kvm_book3s_slbmte(slb_vsid, slb_esid);
return 0;
}
@@ -306,7 +286,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
kvmppc_mmu_hpte_destroy(vcpu);
- __destroy_context(to_book3s(vcpu)->context_id);
+ __destroy_context(to_book3s(vcpu)->context_id[0]);
}
int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
@@ -317,10 +297,10 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
err = __init_new_context();
if (err < 0)
return -1;
- vcpu3s->context_id = err;
+ vcpu3s->context_id[0] = err;
- vcpu3s->vsid_max = ((vcpu3s->context_id + 1) << USER_ESID_BITS) - 1;
- vcpu3s->vsid_first = vcpu3s->context_id << USER_ESID_BITS;
+ vcpu3s->vsid_max = ((vcpu3s->context_id[0] + 1) << USER_ESID_BITS) - 1;
+ vcpu3s->vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
vcpu3s->vsid_next = vcpu3s->vsid_first;
kvmppc_mmu_hpte_init(vcpu);
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index c85f906..4668465 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -73,8 +73,8 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
switch (get_xop(inst)) {
case OP_19_XOP_RFID:
case OP_19_XOP_RFI:
- kvmppc_set_pc(vcpu, vcpu->arch.srr0);
- kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+ kvmppc_set_pc(vcpu, vcpu->arch.shared->srr0);
+ kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
*advance = 0;
break;
@@ -86,14 +86,15 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
case 31:
switch (get_xop(inst)) {
case OP_31_XOP_MFMSR:
- kvmppc_set_gpr(vcpu, get_rt(inst), vcpu->arch.msr);
+ kvmppc_set_gpr(vcpu, get_rt(inst),
+ vcpu->arch.shared->msr);
break;
case OP_31_XOP_MTMSRD:
{
ulong rs = kvmppc_get_gpr(vcpu, get_rs(inst));
if (inst & 0x10000) {
- vcpu->arch.msr &= ~(MSR_RI | MSR_EE);
- vcpu->arch.msr |= rs & (MSR_RI | MSR_EE);
+ vcpu->arch.shared->msr &= ~(MSR_RI | MSR_EE);
+ vcpu->arch.shared->msr |= rs & (MSR_RI | MSR_EE);
} else
kvmppc_set_msr(vcpu, rs);
break;
@@ -204,14 +205,14 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
ra = kvmppc_get_gpr(vcpu, get_ra(inst));
addr = (ra + rb) & ~31ULL;
- if (!(vcpu->arch.msr & MSR_SF))
+ if (!(vcpu->arch.shared->msr & MSR_SF))
addr &= 0xffffffff;
vaddr = addr;
r = kvmppc_st(vcpu, &addr, 32, zeros, true);
if ((r == -ENOENT) || (r == -EPERM)) {
*advance = 0;
- vcpu->arch.dear = vaddr;
+ vcpu->arch.shared->dar = vaddr;
to_svcpu(vcpu)->fault_dar = vaddr;
dsisr = DSISR_ISSTORE;
@@ -220,7 +221,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
else if (r == -EPERM)
dsisr |= DSISR_PROTFAULT;
- to_book3s(vcpu)->dsisr = dsisr;
+ vcpu->arch.shared->dsisr = dsisr;
to_svcpu(vcpu)->fault_dsisr = dsisr;
kvmppc_book3s_queue_irqprio(vcpu,
@@ -263,7 +264,7 @@ void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper,
}
}
-static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn)
+static struct kvmppc_bat *kvmppc_find_bat(struct kvm_vcpu *vcpu, int sprn)
{
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
struct kvmppc_bat *bat;
@@ -285,35 +286,7 @@ static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn)
BUG();
}
- if (sprn % 2)
- return bat->raw >> 32;
- else
- return bat->raw;
-}
-
-static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
-{
- struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
- struct kvmppc_bat *bat;
-
- switch (sprn) {
- case SPRN_IBAT0U ... SPRN_IBAT3L:
- bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2];
- break;
- case SPRN_IBAT4U ... SPRN_IBAT7L:
- bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)];
- break;
- case SPRN_DBAT0U ... SPRN_DBAT3L:
- bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2];
- break;
- case SPRN_DBAT4U ... SPRN_DBAT7L:
- bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)];
- break;
- default:
- BUG();
- }
-
- kvmppc_set_bat(vcpu, bat, !(sprn % 2), val);
+ return bat;
}
int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
@@ -326,10 +299,10 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
to_book3s(vcpu)->sdr1 = spr_val;
break;
case SPRN_DSISR:
- to_book3s(vcpu)->dsisr = spr_val;
+ vcpu->arch.shared->dsisr = spr_val;
break;
case SPRN_DAR:
- vcpu->arch.dear = spr_val;
+ vcpu->arch.shared->dar = spr_val;
break;
case SPRN_HIOR:
to_book3s(vcpu)->hior = spr_val;
@@ -338,12 +311,16 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
case SPRN_IBAT4U ... SPRN_IBAT7L:
case SPRN_DBAT0U ... SPRN_DBAT3L:
case SPRN_DBAT4U ... SPRN_DBAT7L:
- kvmppc_write_bat(vcpu, sprn, (u32)spr_val);
+ {
+ struct kvmppc_bat *bat = kvmppc_find_bat(vcpu, sprn);
+
+ kvmppc_set_bat(vcpu, bat, !(sprn % 2), (u32)spr_val);
/* BAT writes happen so rarely that we're ok to flush
* everything here */
kvmppc_mmu_pte_flush(vcpu, 0, 0);
kvmppc_mmu_flush_segments(vcpu);
break;
+ }
case SPRN_HID0:
to_book3s(vcpu)->hid[0] = spr_val;
break;
@@ -433,16 +410,24 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
case SPRN_IBAT4U ... SPRN_IBAT7L:
case SPRN_DBAT0U ... SPRN_DBAT3L:
case SPRN_DBAT4U ... SPRN_DBAT7L:
- kvmppc_set_gpr(vcpu, rt, kvmppc_read_bat(vcpu, sprn));
+ {
+ struct kvmppc_bat *bat = kvmppc_find_bat(vcpu, sprn);
+
+ if (sprn % 2)
+ kvmppc_set_gpr(vcpu, rt, bat->raw >> 32);
+ else
+ kvmppc_set_gpr(vcpu, rt, bat->raw);
+
break;
+ }
case SPRN_SDR1:
kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
break;
case SPRN_DSISR:
- kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->dsisr);
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dsisr);
break;
case SPRN_DAR:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear);
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar);
break;
case SPRN_HIOR:
kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior);
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 4868d4a..79751d8 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -21,6 +21,7 @@
#include <linux/kvm_host.h>
#include <linux/hash.h>
#include <linux/slab.h>
+#include "trace.h"
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
@@ -30,14 +31,6 @@
#define PTE_SIZE 12
-/* #define DEBUG_MMU */
-
-#ifdef DEBUG_MMU
-#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
-#else
-#define dprintk_mmu(a, ...) do { } while(0)
-#endif
-
static struct kmem_cache *hpte_cache;
static inline u64 kvmppc_mmu_hash_pte(u64 eaddr)
@@ -45,6 +38,12 @@ static inline u64 kvmppc_mmu_hash_pte(u64 eaddr)
return hash_64(eaddr >> PTE_SIZE, HPTEG_HASH_BITS_PTE);
}
+static inline u64 kvmppc_mmu_hash_pte_long(u64 eaddr)
+{
+ return hash_64((eaddr & 0x0ffff000) >> PTE_SIZE,
+ HPTEG_HASH_BITS_PTE_LONG);
+}
+
static inline u64 kvmppc_mmu_hash_vpte(u64 vpage)
{
return hash_64(vpage & 0xfffffffffULL, HPTEG_HASH_BITS_VPTE);
@@ -60,77 +59,128 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
u64 index;
+ trace_kvm_book3s_mmu_map(pte);
+
+ spin_lock(&vcpu->arch.mmu_lock);
+
/* Add to ePTE list */
index = kvmppc_mmu_hash_pte(pte->pte.eaddr);
- hlist_add_head(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]);
+ hlist_add_head_rcu(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]);
+
+ /* Add to ePTE_long list */
+ index = kvmppc_mmu_hash_pte_long(pte->pte.eaddr);
+ hlist_add_head_rcu(&pte->list_pte_long,
+ &vcpu->arch.hpte_hash_pte_long[index]);
/* Add to vPTE list */
index = kvmppc_mmu_hash_vpte(pte->pte.vpage);
- hlist_add_head(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]);
+ hlist_add_head_rcu(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]);
/* Add to vPTE_long list */
index = kvmppc_mmu_hash_vpte_long(pte->pte.vpage);
- hlist_add_head(&pte->list_vpte_long,
- &vcpu->arch.hpte_hash_vpte_long[index]);
+ hlist_add_head_rcu(&pte->list_vpte_long,
+ &vcpu->arch.hpte_hash_vpte_long[index]);
+
+ spin_unlock(&vcpu->arch.mmu_lock);
+}
+
+static void free_pte_rcu(struct rcu_head *head)
+{
+ struct hpte_cache *pte = container_of(head, struct hpte_cache, rcu_head);
+ kmem_cache_free(hpte_cache, pte);
}
static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
- dprintk_mmu("KVM: Flushing SPT: 0x%lx (0x%llx) -> 0x%llx\n",
- pte->pte.eaddr, pte->pte.vpage, pte->host_va);
+ trace_kvm_book3s_mmu_invalidate(pte);
/* Different for 32 and 64 bit */
kvmppc_mmu_invalidate_pte(vcpu, pte);
+ spin_lock(&vcpu->arch.mmu_lock);
+
+ /* pte already invalidated in between? */
+ if (hlist_unhashed(&pte->list_pte)) {
+ spin_unlock(&vcpu->arch.mmu_lock);
+ return;
+ }
+
+ hlist_del_init_rcu(&pte->list_pte);
+ hlist_del_init_rcu(&pte->list_pte_long);
+ hlist_del_init_rcu(&pte->list_vpte);
+ hlist_del_init_rcu(&pte->list_vpte_long);
+
if (pte->pte.may_write)
kvm_release_pfn_dirty(pte->pfn);
else
kvm_release_pfn_clean(pte->pfn);
- hlist_del(&pte->list_pte);
- hlist_del(&pte->list_vpte);
- hlist_del(&pte->list_vpte_long);
+ spin_unlock(&vcpu->arch.mmu_lock);
vcpu->arch.hpte_cache_count--;
- kmem_cache_free(hpte_cache, pte);
+ call_rcu(&pte->rcu_head, free_pte_rcu);
}
static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
{
struct hpte_cache *pte;
- struct hlist_node *node, *tmp;
+ struct hlist_node *node;
int i;
+ rcu_read_lock();
+
for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) {
struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i];
- hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte_long)
+ hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
invalidate_pte(vcpu, pte);
}
+
+ rcu_read_unlock();
}
static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea)
{
struct hlist_head *list;
- struct hlist_node *node, *tmp;
+ struct hlist_node *node;
struct hpte_cache *pte;
/* Find the list of entries in the map */
list = &vcpu->arch.hpte_hash_pte[kvmppc_mmu_hash_pte(guest_ea)];
+ rcu_read_lock();
+
/* Check the list for matching entries and invalidate */
- hlist_for_each_entry_safe(pte, node, tmp, list, list_pte)
+ hlist_for_each_entry_rcu(pte, node, list, list_pte)
if ((pte->pte.eaddr & ~0xfffUL) == guest_ea)
invalidate_pte(vcpu, pte);
+
+ rcu_read_unlock();
}
-void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea)
{
- u64 i;
+ struct hlist_head *list;
+ struct hlist_node *node;
+ struct hpte_cache *pte;
- dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%lx & 0x%lx\n",
- vcpu->arch.hpte_cache_count, guest_ea, ea_mask);
+ /* Find the list of entries in the map */
+ list = &vcpu->arch.hpte_hash_pte_long[
+ kvmppc_mmu_hash_pte_long(guest_ea)];
+ rcu_read_lock();
+
+ /* Check the list for matching entries and invalidate */
+ hlist_for_each_entry_rcu(pte, node, list, list_pte_long)
+ if ((pte->pte.eaddr & 0x0ffff000UL) == guest_ea)
+ invalidate_pte(vcpu, pte);
+
+ rcu_read_unlock();
+}
+
+void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+{
+ trace_kvm_book3s_mmu_flush("", vcpu, guest_ea, ea_mask);
guest_ea &= ea_mask;
switch (ea_mask) {
@@ -138,9 +188,7 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
kvmppc_mmu_pte_flush_page(vcpu, guest_ea);
break;
case 0x0ffff000:
- /* 32-bit flush w/o segment, go through all possible segments */
- for (i = 0; i < 0x100000000ULL; i += 0x10000000ULL)
- kvmppc_mmu_pte_flush(vcpu, guest_ea | i, ~0xfffUL);
+ kvmppc_mmu_pte_flush_long(vcpu, guest_ea);
break;
case 0:
/* Doing a complete flush -> start from scratch */
@@ -156,39 +204,46 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
{
struct hlist_head *list;
- struct hlist_node *node, *tmp;
+ struct hlist_node *node;
struct hpte_cache *pte;
u64 vp_mask = 0xfffffffffULL;
list = &vcpu->arch.hpte_hash_vpte[kvmppc_mmu_hash_vpte(guest_vp)];
+ rcu_read_lock();
+
/* Check the list for matching entries and invalidate */
- hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte)
+ hlist_for_each_entry_rcu(pte, node, list, list_vpte)
if ((pte->pte.vpage & vp_mask) == guest_vp)
invalidate_pte(vcpu, pte);
+
+ rcu_read_unlock();
}
/* Flush with mask 0xffffff000 */
static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
{
struct hlist_head *list;
- struct hlist_node *node, *tmp;
+ struct hlist_node *node;
struct hpte_cache *pte;
u64 vp_mask = 0xffffff000ULL;
list = &vcpu->arch.hpte_hash_vpte_long[
kvmppc_mmu_hash_vpte_long(guest_vp)];
+ rcu_read_lock();
+
/* Check the list for matching entries and invalidate */
- hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte_long)
+ hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
if ((pte->pte.vpage & vp_mask) == guest_vp)
invalidate_pte(vcpu, pte);
+
+ rcu_read_unlock();
}
void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
{
- dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n",
- vcpu->arch.hpte_cache_count, guest_vp, vp_mask);
+ trace_kvm_book3s_mmu_flush("v", vcpu, guest_vp, vp_mask);
guest_vp &= vp_mask;
switch(vp_mask) {
@@ -206,21 +261,24 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
{
- struct hlist_node *node, *tmp;
+ struct hlist_node *node;
struct hpte_cache *pte;
int i;
- dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%lx - 0x%lx\n",
- vcpu->arch.hpte_cache_count, pa_start, pa_end);
+ trace_kvm_book3s_mmu_flush("p", vcpu, pa_start, pa_end);
+
+ rcu_read_lock();
for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) {
struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i];
- hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte_long)
+ hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
if ((pte->pte.raddr >= pa_start) &&
(pte->pte.raddr < pa_end))
invalidate_pte(vcpu, pte);
}
+
+ rcu_read_unlock();
}
struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
@@ -254,11 +312,15 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
/* init hpte lookup hashes */
kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte,
ARRAY_SIZE(vcpu->arch.hpte_hash_pte));
+ kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte_long,
+ ARRAY_SIZE(vcpu->arch.hpte_hash_pte_long));
kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte,
ARRAY_SIZE(vcpu->arch.hpte_hash_vpte));
kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte_long,
ARRAY_SIZE(vcpu->arch.hpte_hash_vpte_long));
+ spin_lock_init(&vcpu->arch.mmu_lock);
+
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 35a701f..7b0ee96c 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -165,14 +165,15 @@ static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
{
u64 dsisr;
+ struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
- vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 36, 0);
- vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0);
- vcpu->arch.dear = eaddr;
+ shared->msr = kvmppc_set_field(shared->msr, 33, 36, 0);
+ shared->msr = kvmppc_set_field(shared->msr, 42, 47, 0);
+ shared->dar = eaddr;
/* Page Fault */
dsisr = kvmppc_set_field(0, 33, 33, 1);
if (is_store)
- to_book3s(vcpu)->dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
+ shared->dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
}
@@ -658,7 +659,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
if (!kvmppc_inst_is_paired_single(vcpu, inst))
return EMULATE_FAIL;
- if (!(vcpu->arch.msr & MSR_FP)) {
+ if (!(vcpu->arch.shared->msr & MSR_FP)) {
kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL);
return EMULATE_AGAIN;
}
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 506d5c3..2b9c908 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -202,8 +202,25 @@ _GLOBAL(kvmppc_rmcall)
#if defined(CONFIG_PPC_BOOK3S_32)
#define STACK_LR INT_FRAME_SIZE+4
+
+/* load_up_xxx have to run with MSR_DR=0 on Book3S_32 */
+#define MSR_EXT_START \
+ PPC_STL r20, _NIP(r1); \
+ mfmsr r20; \
+ LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \
+ andc r3,r20,r3; /* Disable DR,EE */ \
+ mtmsr r3; \
+ sync
+
+#define MSR_EXT_END \
+ mtmsr r20; /* Enable DR,EE */ \
+ sync; \
+ PPC_LL r20, _NIP(r1)
+
#elif defined(CONFIG_PPC_BOOK3S_64)
#define STACK_LR _LINK
+#define MSR_EXT_START
+#define MSR_EXT_END
#endif
/*
@@ -215,19 +232,12 @@ _GLOBAL(kvmppc_load_up_ ## what); \
PPC_STLU r1, -INT_FRAME_SIZE(r1); \
mflr r3; \
PPC_STL r3, STACK_LR(r1); \
- PPC_STL r20, _NIP(r1); \
- mfmsr r20; \
- LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \
- andc r3,r20,r3; /* Disable DR,EE */ \
- mtmsr r3; \
- sync; \
+ MSR_EXT_START; \
\
bl FUNC(load_up_ ## what); \
\
- mtmsr r20; /* Enable DR,EE */ \
- sync; \
+ MSR_EXT_END; \
PPC_LL r3, STACK_LR(r1); \
- PPC_LL r20, _NIP(r1); \
mtlr r3; \
addi r1, r1, INT_FRAME_SIZE; \
blr
@@ -242,10 +252,10 @@ define_load_up(vsx)
.global kvmppc_trampoline_lowmem
kvmppc_trampoline_lowmem:
- .long kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START
+ PPC_LONG kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START
.global kvmppc_trampoline_enter
kvmppc_trampoline_enter:
- .long kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START
+ PPC_LONG kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START
#include "book3s_segment.S"
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 8d4e35f..77575d0 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -62,9 +62,10 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
{
int i;
- printk("pc: %08lx msr: %08lx\n", vcpu->arch.pc, vcpu->arch.msr);
+ printk("pc: %08lx msr: %08llx\n", vcpu->arch.pc, vcpu->arch.shared->msr);
printk("lr: %08lx ctr: %08lx\n", vcpu->arch.lr, vcpu->arch.ctr);
- printk("srr0: %08lx srr1: %08lx\n", vcpu->arch.srr0, vcpu->arch.srr1);
+ printk("srr0: %08llx srr1: %08llx\n", vcpu->arch.shared->srr0,
+ vcpu->arch.shared->srr1);
printk("exceptions: %08lx\n", vcpu->arch.pending_exceptions);
@@ -130,13 +131,19 @@ void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
- kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_EXTERNAL);
+ unsigned int prio = BOOKE_IRQPRIO_EXTERNAL;
+
+ if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
+ prio = BOOKE_IRQPRIO_EXTERNAL_LEVEL;
+
+ kvmppc_booke_queue_irqprio(vcpu, prio);
}
void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
+ clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
}
/* Deliver the interrupt of the corresponding priority, if possible. */
@@ -146,6 +153,26 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
int allowed = 0;
ulong uninitialized_var(msr_mask);
bool update_esr = false, update_dear = false;
+ ulong crit_raw = vcpu->arch.shared->critical;
+ ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+ bool crit;
+ bool keep_irq = false;
+
+ /* Truncate crit indicators in 32 bit mode */
+ if (!(vcpu->arch.shared->msr & MSR_SF)) {
+ crit_raw &= 0xffffffff;
+ crit_r1 &= 0xffffffff;
+ }
+
+ /* Critical section when crit == r1 */
+ crit = (crit_raw == crit_r1);
+ /* ... and we're in supervisor mode */
+ crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
+
+ if (priority == BOOKE_IRQPRIO_EXTERNAL_LEVEL) {
+ priority = BOOKE_IRQPRIO_EXTERNAL;
+ keep_irq = true;
+ }
switch (priority) {
case BOOKE_IRQPRIO_DTLB_MISS:
@@ -169,36 +196,38 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
break;
case BOOKE_IRQPRIO_CRITICAL:
case BOOKE_IRQPRIO_WATCHDOG:
- allowed = vcpu->arch.msr & MSR_CE;
+ allowed = vcpu->arch.shared->msr & MSR_CE;
msr_mask = MSR_ME;
break;
case BOOKE_IRQPRIO_MACHINE_CHECK:
- allowed = vcpu->arch.msr & MSR_ME;
+ allowed = vcpu->arch.shared->msr & MSR_ME;
msr_mask = 0;
break;
case BOOKE_IRQPRIO_EXTERNAL:
case BOOKE_IRQPRIO_DECREMENTER:
case BOOKE_IRQPRIO_FIT:
- allowed = vcpu->arch.msr & MSR_EE;
+ allowed = vcpu->arch.shared->msr & MSR_EE;
+ allowed = allowed && !crit;
msr_mask = MSR_CE|MSR_ME|MSR_DE;
break;
case BOOKE_IRQPRIO_DEBUG:
- allowed = vcpu->arch.msr & MSR_DE;
+ allowed = vcpu->arch.shared->msr & MSR_DE;
msr_mask = MSR_ME;
break;
}
if (allowed) {
- vcpu->arch.srr0 = vcpu->arch.pc;
- vcpu->arch.srr1 = vcpu->arch.msr;
+ vcpu->arch.shared->srr0 = vcpu->arch.pc;
+ vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
if (update_esr == true)
vcpu->arch.esr = vcpu->arch.queued_esr;
if (update_dear == true)
- vcpu->arch.dear = vcpu->arch.queued_dear;
- kvmppc_set_msr(vcpu, vcpu->arch.msr & msr_mask);
+ vcpu->arch.shared->dar = vcpu->arch.queued_dear;
+ kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
- clear_bit(priority, &vcpu->arch.pending_exceptions);
+ if (!keep_irq)
+ clear_bit(priority, &vcpu->arch.pending_exceptions);
}
return allowed;
@@ -208,6 +237,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
{
unsigned long *pending = &vcpu->arch.pending_exceptions;
+ unsigned long old_pending = vcpu->arch.pending_exceptions;
unsigned int priority;
priority = __ffs(*pending);
@@ -219,6 +249,12 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
BITS_PER_BYTE * sizeof(*pending),
priority + 1);
}
+
+ /* Tell the guest about our interrupt status */
+ if (*pending)
+ vcpu->arch.shared->int_pending = 1;
+ else if (old_pending)
+ vcpu->arch.shared->int_pending = 0;
}
/**
@@ -265,7 +301,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
case BOOKE_INTERRUPT_PROGRAM:
- if (vcpu->arch.msr & MSR_PR) {
+ if (vcpu->arch.shared->msr & MSR_PR) {
/* Program traps generated by user-level software must be handled
* by the guest kernel. */
kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
@@ -337,7 +373,15 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
case BOOKE_INTERRUPT_SYSCALL:
- kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SYSCALL);
+ if (!(vcpu->arch.shared->msr & MSR_PR) &&
+ (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
+ /* KVM PV hypercalls */
+ kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+ r = RESUME_GUEST;
+ } else {
+ /* Guest syscalls */
+ kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SYSCALL);
+ }
kvmppc_account_exit(vcpu, SYSCALL_EXITS);
r = RESUME_GUEST;
break;
@@ -466,15 +510,19 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
+ int i;
+
vcpu->arch.pc = 0;
- vcpu->arch.msr = 0;
+ vcpu->arch.shared->msr = 0;
kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
vcpu->arch.shadow_pid = 1;
- /* Eye-catching number so we know if the guest takes an interrupt
- * before it's programmed its own IVPR. */
+ /* Eye-catching numbers so we know if the guest takes an interrupt
+ * before it's programmed its own IVPR/IVORs. */
vcpu->arch.ivpr = 0x55550000;
+ for (i = 0; i < BOOKE_IRQPRIO_MAX; i++)
+ vcpu->arch.ivor[i] = 0x7700 | i * 4;
kvmppc_init_timing_stats(vcpu);
@@ -490,14 +538,14 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
regs->ctr = vcpu->arch.ctr;
regs->lr = vcpu->arch.lr;
regs->xer = kvmppc_get_xer(vcpu);
- regs->msr = vcpu->arch.msr;
- regs->srr0 = vcpu->arch.srr0;
- regs->srr1 = vcpu->arch.srr1;
+ regs->msr = vcpu->arch.shared->msr;
+ regs->srr0 = vcpu->arch.shared->srr0;
+ regs->srr1 = vcpu->arch.shared->srr1;
regs->pid = vcpu->arch.pid;
- regs->sprg0 = vcpu->arch.sprg0;
- regs->sprg1 = vcpu->arch.sprg1;
- regs->sprg2 = vcpu->arch.sprg2;
- regs->sprg3 = vcpu->arch.sprg3;
+ regs->sprg0 = vcpu->arch.shared->sprg0;
+ regs->sprg1 = vcpu->arch.shared->sprg1;
+ regs->sprg2 = vcpu->arch.shared->sprg2;
+ regs->sprg3 = vcpu->arch.shared->sprg3;
regs->sprg5 = vcpu->arch.sprg4;
regs->sprg6 = vcpu->arch.sprg5;
regs->sprg7 = vcpu->arch.sprg6;
@@ -518,12 +566,12 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
vcpu->arch.lr = regs->lr;
kvmppc_set_xer(vcpu, regs->xer);
kvmppc_set_msr(vcpu, regs->msr);
- vcpu->arch.srr0 = regs->srr0;
- vcpu->arch.srr1 = regs->srr1;
- vcpu->arch.sprg0 = regs->sprg0;
- vcpu->arch.sprg1 = regs->sprg1;
- vcpu->arch.sprg2 = regs->sprg2;
- vcpu->arch.sprg3 = regs->sprg3;
+ vcpu->arch.shared->srr0 = regs->srr0;
+ vcpu->arch.shared->srr1 = regs->srr1;
+ vcpu->arch.shared->sprg0 = regs->sprg0;
+ vcpu->arch.shared->sprg1 = regs->sprg1;
+ vcpu->arch.shared->sprg2 = regs->sprg2;
+ vcpu->arch.shared->sprg3 = regs->sprg3;
vcpu->arch.sprg5 = regs->sprg4;
vcpu->arch.sprg6 = regs->sprg5;
vcpu->arch.sprg7 = regs->sprg6;
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index d59bcca..492bb70 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -46,7 +46,9 @@
#define BOOKE_IRQPRIO_FIT 17
#define BOOKE_IRQPRIO_DECREMENTER 18
#define BOOKE_IRQPRIO_PERFORMANCE_MONITOR 19
-#define BOOKE_IRQPRIO_MAX 19
+/* Internal pseudo-irqprio for level triggered externals */
+#define BOOKE_IRQPRIO_EXTERNAL_LEVEL 20
+#define BOOKE_IRQPRIO_MAX 20
extern unsigned long kvmppc_booke_handlers;
@@ -54,12 +56,12 @@ extern unsigned long kvmppc_booke_handlers;
* changing. */
static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
{
- if ((new_msr & MSR_PR) != (vcpu->arch.msr & MSR_PR))
+ if ((new_msr & MSR_PR) != (vcpu->arch.shared->msr & MSR_PR))
kvmppc_mmu_priv_switch(vcpu, new_msr & MSR_PR);
- vcpu->arch.msr = new_msr;
+ vcpu->arch.shared->msr = new_msr;
- if (vcpu->arch.msr & MSR_WE) {
+ if (vcpu->arch.shared->msr & MSR_WE) {
kvm_vcpu_block(vcpu);
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
};
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index cbc790e..1260f5f 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -31,8 +31,8 @@
static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
{
- vcpu->arch.pc = vcpu->arch.srr0;
- kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+ vcpu->arch.pc = vcpu->arch.shared->srr0;
+ kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
}
int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
@@ -62,7 +62,7 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
case OP_31_XOP_MFMSR:
rt = get_rt(inst);
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.msr);
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->msr);
kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
break;
@@ -74,13 +74,13 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
case OP_31_XOP_WRTEE:
rs = get_rs(inst);
- vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+ vcpu->arch.shared->msr = (vcpu->arch.shared->msr & ~MSR_EE)
| (kvmppc_get_gpr(vcpu, rs) & MSR_EE);
kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
break;
case OP_31_XOP_WRTEEI:
- vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+ vcpu->arch.shared->msr = (vcpu->arch.shared->msr & ~MSR_EE)
| (inst & MSR_EE);
kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
break;
@@ -105,7 +105,7 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
switch (sprn) {
case SPRN_DEAR:
- vcpu->arch.dear = spr_val; break;
+ vcpu->arch.shared->dar = spr_val; break;
case SPRN_ESR:
vcpu->arch.esr = spr_val; break;
case SPRN_DBCR0:
@@ -200,7 +200,7 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
case SPRN_IVPR:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break;
case SPRN_DEAR:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar); break;
case SPRN_ESR:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break;
case SPRN_DBCR0:
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 380a78c..0498469 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -415,7 +415,8 @@ lightweight_exit:
lwz r8, VCPU_GPR(r8)(r4)
lwz r3, VCPU_PC(r4)
mtsrr0 r3
- lwz r3, VCPU_MSR(r4)
+ lwz r3, VCPU_SHARED(r4)
+ lwz r3, VCPU_SHARED_MSR(r3)
oris r3, r3, KVMPPC_MSR_MASK@h
ori r3, r3, KVMPPC_MSR_MASK@l
mtsrr1 r3
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index e8a00b0..71750f2 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -117,8 +117,14 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
if (err)
goto uninit_vcpu;
+ vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+ if (!vcpu->arch.shared)
+ goto uninit_tlb;
+
return vcpu;
+uninit_tlb:
+ kvmppc_e500_tlb_uninit(vcpu_e500);
uninit_vcpu:
kvm_vcpu_uninit(vcpu);
free_vcpu:
@@ -131,6 +137,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ free_page((unsigned long)vcpu->arch.shared);
kvmppc_e500_tlb_uninit(vcpu_e500);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 21011e1..d6d6d47 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -226,8 +226,7 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
stlbe->mas1 = 0;
- trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
- stlbe->mas3, stlbe->mas7);
+ trace_kvm_stlb_inval(index_of(tlbsel, esel));
}
static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -298,7 +297,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
/* Get reference to new page. */
new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn);
if (is_error_page(new_page)) {
- printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn);
+ printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n",
+ (long)gfn);
kvm_release_page_clean(new_page);
return;
}
@@ -314,10 +314,10 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
stlbe->mas2 = (gvaddr & MAS2_EPN)
| e500_shadow_mas2_attrib(gtlbe->mas2,
- vcpu_e500->vcpu.arch.msr & MSR_PR);
+ vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
stlbe->mas3 = (hpaddr & MAS3_RPN)
| e500_shadow_mas3_attrib(gtlbe->mas3,
- vcpu_e500->vcpu.arch.msr & MSR_PR);
+ vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
@@ -576,28 +576,28 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
- unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+ unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
}
int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
- unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+ unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);
return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
}
void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
{
- unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+ unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
}
void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
{
- unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+ unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);
kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.fault_dear, as);
}
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
index d28e301..458946b 100644
--- a/arch/powerpc/kvm/e500_tlb.h
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -171,7 +171,7 @@ static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
/* Does it match current guest AS? */
/* XXX what about IS != DS? */
- if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+ if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
return 0;
gpa = get_tlb_raddr(tlbe);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index b83ba58..c64fd29 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -242,9 +242,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
switch (sprn) {
case SPRN_SRR0:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr0); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr0);
+ break;
case SPRN_SRR1:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr1); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr1);
+ break;
case SPRN_PVR:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.pvr); break;
case SPRN_PIR:
@@ -261,13 +263,17 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
kvmppc_set_gpr(vcpu, rt, get_tb()); break;
case SPRN_SPRG0:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg0); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg0);
+ break;
case SPRN_SPRG1:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg1); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg1);
+ break;
case SPRN_SPRG2:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg2); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg2);
+ break;
case SPRN_SPRG3:
- kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg3); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg3);
+ break;
/* Note: SPRG4-7 are user-readable, so we don't get
* a trap. */
@@ -320,9 +326,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
rs = get_rs(inst);
switch (sprn) {
case SPRN_SRR0:
- vcpu->arch.srr0 = kvmppc_get_gpr(vcpu, rs); break;
+ vcpu->arch.shared->srr0 = kvmppc_get_gpr(vcpu, rs);
+ break;
case SPRN_SRR1:
- vcpu->arch.srr1 = kvmppc_get_gpr(vcpu, rs); break;
+ vcpu->arch.shared->srr1 = kvmppc_get_gpr(vcpu, rs);
+ break;
/* XXX We need to context-switch the timebase for
* watchdog and FIT. */
@@ -337,13 +345,17 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
break;
case SPRN_SPRG0:
- vcpu->arch.sprg0 = kvmppc_get_gpr(vcpu, rs); break;
+ vcpu->arch.shared->sprg0 = kvmppc_get_gpr(vcpu, rs);
+ break;
case SPRN_SPRG1:
- vcpu->arch.sprg1 = kvmppc_get_gpr(vcpu, rs); break;
+ vcpu->arch.shared->sprg1 = kvmppc_get_gpr(vcpu, rs);
+ break;
case SPRN_SPRG2:
- vcpu->arch.sprg2 = kvmppc_get_gpr(vcpu, rs); break;
+ vcpu->arch.shared->sprg2 = kvmppc_get_gpr(vcpu, rs);
+ break;
case SPRN_SPRG3:
- vcpu->arch.sprg3 = kvmppc_get_gpr(vcpu, rs); break;
+ vcpu->arch.shared->sprg3 = kvmppc_get_gpr(vcpu, rs);
+ break;
default:
emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, rs);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 72a4ad8..2f87a16 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -38,9 +38,56 @@
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
- return !(v->arch.msr & MSR_WE) || !!(v->arch.pending_exceptions);
+ return !(v->arch.shared->msr & MSR_WE) ||
+ !!(v->arch.pending_exceptions);
}
+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 (!(vcpu->arch.shared->msr & MSR_SF)) {
+ /* 32 bit mode */
+ param1 &= 0xffffffff;
+ param2 &= 0xffffffff;
+ param3 &= 0xffffffff;
+ param4 &= 0xffffffff;
+ }
+
+ switch (nr) {
+ case HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE:
+ {
+ vcpu->arch.magic_page_pa = param1;
+ vcpu->arch.magic_page_ea = param2;
+
+ r2 = KVM_MAGIC_FEAT_SR;
+
+ r = HC_EV_SUCCESS;
+ break;
+ }
+ case HC_VENDOR_KVM | KVM_HC_FEATURES:
+ r = HC_EV_SUCCESS;
+#if defined(CONFIG_PPC_BOOK3S) /* XXX Missing magic page on BookE */
+ r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
+#endif
+
+ /* Second return value is in r4 */
+ break;
+ default:
+ r = HC_EV_UNIMPLEMENTED;
+ break;
+ }
+
+ kvmppc_set_gpr(vcpu, 4, r2);
+
+ return r;
+}
int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
@@ -145,8 +192,10 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_PPC_SEGSTATE:
case KVM_CAP_PPC_PAIRED_SINGLES:
case KVM_CAP_PPC_UNSET_IRQ:
+ case KVM_CAP_PPC_IRQ_LEVEL:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_PPC_OSI:
+ case KVM_CAP_PPC_GET_PVINFO:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -534,16 +583,53 @@ out:
return r;
}
+static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
+{
+ u32 inst_lis = 0x3c000000;
+ u32 inst_ori = 0x60000000;
+ u32 inst_nop = 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] = inst_lis | ((KVM_SC_MAGIC_R0 >> 16) & inst_imm_mask);
+ pvinfo->hcall[1] = inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask);
+ pvinfo->hcall[2] = inst_sc;
+ pvinfo->hcall[3] = inst_nop;
+
+ return 0;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
+ void __user *argp = (void __user *)arg;
long r;
switch (ioctl) {
+ case KVM_PPC_GET_PVINFO: {
+ struct kvm_ppc_pvinfo pvinfo;
+ r = kvm_vm_ioctl_get_pvinfo(&pvinfo);
+ if (copy_to_user(argp, &pvinfo, sizeof(pvinfo))) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ break;
+ }
default:
r = -ENOTTY;
}
+out:
return r;
}
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index a8e8400..3aca1b0 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -98,6 +98,245 @@ TRACE_EVENT(kvm_gtlb_write,
__entry->word1, __entry->word2)
);
+
+/*************************************************************************
+ * Book3S trace points *
+ *************************************************************************/
+
+#ifdef CONFIG_PPC_BOOK3S
+
+TRACE_EVENT(kvm_book3s_exit,
+ TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+ TP_ARGS(exit_nr, vcpu),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, exit_nr )
+ __field( unsigned long, pc )
+ __field( unsigned long, msr )
+ __field( unsigned long, dar )
+ __field( unsigned long, srr1 )
+ ),
+
+ TP_fast_assign(
+ __entry->exit_nr = exit_nr;
+ __entry->pc = kvmppc_get_pc(vcpu);
+ __entry->dar = kvmppc_get_fault_dar(vcpu);
+ __entry->msr = vcpu->arch.shared->msr;
+ __entry->srr1 = to_svcpu(vcpu)->shadow_srr1;
+ ),
+
+ TP_printk("exit=0x%x | pc=0x%lx | msr=0x%lx | dar=0x%lx | srr1=0x%lx",
+ __entry->exit_nr, __entry->pc, __entry->msr, __entry->dar,
+ __entry->srr1)
+);
+
+TRACE_EVENT(kvm_book3s_reenter,
+ TP_PROTO(int r, struct kvm_vcpu *vcpu),
+ TP_ARGS(r, vcpu),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, r )
+ __field( unsigned long, pc )
+ ),
+
+ TP_fast_assign(
+ __entry->r = r;
+ __entry->pc = kvmppc_get_pc(vcpu);
+ ),
+
+ TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
+);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+
+TRACE_EVENT(kvm_book3s_64_mmu_map,
+ TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr,
+ struct kvmppc_pte *orig_pte),
+ TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte),
+
+ TP_STRUCT__entry(
+ __field( unsigned char, flag_w )
+ __field( unsigned char, flag_x )
+ __field( unsigned long, eaddr )
+ __field( unsigned long, hpteg )
+ __field( unsigned long, va )
+ __field( unsigned long long, vpage )
+ __field( unsigned long, hpaddr )
+ ),
+
+ TP_fast_assign(
+ __entry->flag_w = ((rflags & HPTE_R_PP) == 3) ? '-' : 'w';
+ __entry->flag_x = (rflags & HPTE_R_N) ? '-' : 'x';
+ __entry->eaddr = orig_pte->eaddr;
+ __entry->hpteg = hpteg;
+ __entry->va = va;
+ __entry->vpage = orig_pte->vpage;
+ __entry->hpaddr = hpaddr;
+ ),
+
+ TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx",
+ __entry->flag_w, __entry->flag_x, __entry->eaddr,
+ __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr)
+);
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+TRACE_EVENT(kvm_book3s_mmu_map,
+ TP_PROTO(struct hpte_cache *pte),
+ TP_ARGS(pte),
+
+ TP_STRUCT__entry(
+ __field( u64, host_va )
+ __field( u64, pfn )
+ __field( ulong, eaddr )
+ __field( u64, vpage )
+ __field( ulong, raddr )
+ __field( int, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->host_va = pte->host_va;
+ __entry->pfn = pte->pfn;
+ __entry->eaddr = pte->pte.eaddr;
+ __entry->vpage = pte->pte.vpage;
+ __entry->raddr = pte->pte.raddr;
+ __entry->flags = (pte->pte.may_read ? 0x4 : 0) |
+ (pte->pte.may_write ? 0x2 : 0) |
+ (pte->pte.may_execute ? 0x1 : 0);
+ ),
+
+ TP_printk("Map: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+ __entry->host_va, __entry->pfn, __entry->eaddr,
+ __entry->vpage, __entry->raddr, __entry->flags)
+);
+
+TRACE_EVENT(kvm_book3s_mmu_invalidate,
+ TP_PROTO(struct hpte_cache *pte),
+ TP_ARGS(pte),
+
+ TP_STRUCT__entry(
+ __field( u64, host_va )
+ __field( u64, pfn )
+ __field( ulong, eaddr )
+ __field( u64, vpage )
+ __field( ulong, raddr )
+ __field( int, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->host_va = pte->host_va;
+ __entry->pfn = pte->pfn;
+ __entry->eaddr = pte->pte.eaddr;
+ __entry->vpage = pte->pte.vpage;
+ __entry->raddr = pte->pte.raddr;
+ __entry->flags = (pte->pte.may_read ? 0x4 : 0) |
+ (pte->pte.may_write ? 0x2 : 0) |
+ (pte->pte.may_execute ? 0x1 : 0);
+ ),
+
+ TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+ __entry->host_va, __entry->pfn, __entry->eaddr,
+ __entry->vpage, __entry->raddr, __entry->flags)
+);
+
+TRACE_EVENT(kvm_book3s_mmu_flush,
+ TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1,
+ unsigned long long p2),
+ TP_ARGS(type, vcpu, p1, p2),
+
+ TP_STRUCT__entry(
+ __field( int, count )
+ __field( unsigned long long, p1 )
+ __field( unsigned long long, p2 )
+ __field( const char *, type )
+ ),
+
+ TP_fast_assign(
+ __entry->count = vcpu->arch.hpte_cache_count;
+ __entry->p1 = p1;
+ __entry->p2 = p2;
+ __entry->type = type;
+ ),
+
+ TP_printk("Flush %d %sPTEs: %llx - %llx",
+ __entry->count, __entry->type, __entry->p1, __entry->p2)
+);
+
+TRACE_EVENT(kvm_book3s_slb_found,
+ TP_PROTO(unsigned long long gvsid, unsigned long long hvsid),
+ TP_ARGS(gvsid, hvsid),
+
+ TP_STRUCT__entry(
+ __field( unsigned long long, gvsid )
+ __field( unsigned long long, hvsid )
+ ),
+
+ TP_fast_assign(
+ __entry->gvsid = gvsid;
+ __entry->hvsid = hvsid;
+ ),
+
+ TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_fail,
+ TP_PROTO(u16 sid_map_mask, unsigned long long gvsid),
+ TP_ARGS(sid_map_mask, gvsid),
+
+ TP_STRUCT__entry(
+ __field( unsigned short, sid_map_mask )
+ __field( unsigned long long, gvsid )
+ ),
+
+ TP_fast_assign(
+ __entry->sid_map_mask = sid_map_mask;
+ __entry->gvsid = gvsid;
+ ),
+
+ TP_printk("%x/%x: %llx", __entry->sid_map_mask,
+ SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_map,
+ TP_PROTO(u16 sid_map_mask, unsigned long long gvsid,
+ unsigned long long hvsid),
+ TP_ARGS(sid_map_mask, gvsid, hvsid),
+
+ TP_STRUCT__entry(
+ __field( unsigned short, sid_map_mask )
+ __field( unsigned long long, guest_vsid )
+ __field( unsigned long long, host_vsid )
+ ),
+
+ TP_fast_assign(
+ __entry->sid_map_mask = sid_map_mask;
+ __entry->guest_vsid = gvsid;
+ __entry->host_vsid = hvsid;
+ ),
+
+ TP_printk("%x: %llx -> %llx", __entry->sid_map_mask,
+ __entry->guest_vsid, __entry->host_vsid)
+);
+
+TRACE_EVENT(kvm_book3s_slbmte,
+ TP_PROTO(u64 slb_vsid, u64 slb_esid),
+ TP_ARGS(slb_vsid, slb_esid),
+
+ TP_STRUCT__entry(
+ __field( u64, slb_vsid )
+ __field( u64, slb_esid )
+ ),
+
+ TP_fast_assign(
+ __entry->slb_vsid = slb_vsid;
+ __entry->slb_esid = slb_esid;
+ ),
+
+ TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid)
+);
+
+#endif /* CONFIG_PPC_BOOK3S */
+
#endif /* _TRACE_KVM_H */
/* This part must be outside protection */