Merge tag 'kvm-s390-next-20150602' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into kvm-next
KVM: s390: Fix and cleanup for 4.2 (kvm/next)
One small fix for a commit targetted for 4.2 and one cleanup
regarding our printks.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 9fa2bf8..6955444 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -959,7 +959,8 @@
4.37 KVM_ENABLE_CAP
Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
-Architectures: ppc, s390
+Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM),
+ mips (only KVM_CAP_ENABLE_CAP), ppc, s390
Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
Parameters: struct kvm_enable_cap (in)
Returns: 0 on success; -1 on error
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 53838d9..c59bd9b 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -169,6 +169,10 @@
Contains the value of cr4.smep && !cr0.wp for which the page is valid
(pages for which this is true are different from other pages; see the
treatment of cr0.wp=0 below).
+ role.smap_andnot_wp:
+ Contains the value of cr4.smap && !cr0.wp for which the page is valid
+ (pages for which this is true are different from other pages; see the
+ treatment of cr0.wp=0 below).
gfn:
Either the guest page table containing the translations shadowed by this
page, or the base page frame for linear translations. See role.direct.
@@ -344,10 +348,16 @@
(user write faults generate a #PF)
-In the first case there is an additional complication if CR4.SMEP is
-enabled: since we've turned the page into a kernel page, the kernel may now
-execute it. We handle this by also setting spte.nx. If we get a user
-fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back.
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+ the kernel may now execute it. We handle this by also setting spte.nx.
+ If we get a user fetch or read fault, we'll change spte.u=1 and
+ spte.nx=gpte.nx back.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+ page, it can not be reused when CR4.SMAP is enabled. We set
+ CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+ here we do not care the case that CR4.SMAP is enabled since KVM will
+ directly inject #PF to guest due to failed permission check.
To prevent an spte that was converted into a kernel page with cr0.wp=0
from being written by the kernel after cr0.wp has changed to 1, we make
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d9631ec..e41cb11 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -553,13 +553,13 @@
* Enter the guest
*/
trace_kvm_entry(*vcpu_pc(vcpu));
- kvm_guest_enter();
+ __kvm_guest_enter();
vcpu->mode = IN_GUEST_MODE;
ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
- kvm_guest_exit();
+ __kvm_guest_exit();
trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
/*
* We may have taken a host interrupt in HYP mode (ie
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 1d5accb..7f473e6 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1155,7 +1155,8 @@
*/
void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
{
- struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot);
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+ struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
@@ -1718,8 +1719,9 @@
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
/*
@@ -1733,7 +1735,7 @@
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
hva_t hva = mem->userspace_addr;
@@ -1838,7 +1840,7 @@
return 0;
}
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
{
}
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 4c25823..e8c8d9d 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -839,7 +839,7 @@
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_free_memslot(struct kvm *kvm,
struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot) {}
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index bb68e8d..cd4c129 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -198,15 +198,16 @@
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
return 0;
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
unsigned long npages = 0;
@@ -393,7 +394,7 @@
kvm_mips_deliver_interrupts(vcpu,
kvm_read_c0_guest_cause(vcpu->arch.cop0));
- kvm_guest_enter();
+ __kvm_guest_enter();
/* Disable hardware page table walking while in guest */
htw_stop();
@@ -403,7 +404,7 @@
/* Re-enable HTW before enabling interrupts */
htw_start();
- kvm_guest_exit();
+ __kvm_guest_exit();
local_irq_enable();
if (vcpu->sigset_active)
@@ -968,6 +969,7 @@
/* Get (and clear) the dirty memory log for a memory slot. */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
unsigned long ga, ga_end;
int is_dirty = 0;
@@ -982,7 +984,8 @@
/* If nothing is dirty, don't bother messing with page tables. */
if (is_dirty) {
- memslot = &kvm->memslots->memslots[log->slot];
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
ga = memslot->base_gfn << PAGE_SHIFT;
ga_end = ga + (memslot->npages << PAGE_SHIFT);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index a193a13..d91f65b 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -698,7 +698,7 @@
static inline void kvm_arch_hardware_disable(void) {}
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_exit(void) {}
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index b8475da..c6ef05b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -182,10 +182,11 @@
unsigned long npages);
extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region *mem);
extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old);
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new);
extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
struct kvm_ppc_smmu_info *info);
extern void kvmppc_core_flush_memslot(struct kvm *kvm,
@@ -243,10 +244,11 @@
void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot);
int (*prepare_memory_region)(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region *mem);
void (*commit_memory_region)(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old);
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new);
int (*unmap_hva)(struct kvm *kvm, unsigned long hva);
int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
unsigned long end);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 453a8a47..05ea8fc 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -757,16 +757,17 @@
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem);
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
- kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old);
+ kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
}
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 1a4acf8..dab68b7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -650,7 +650,7 @@
int srcu_idx;
srcu_idx = srcu_read_lock(&kvm->srcu);
- slots = kvm->memslots;
+ slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
/*
* This assumes it is acceptable to lose reference and
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48d3c5d..68d067a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@
*/
static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu;
+ struct kvm_vcpu *vcpu, *vnext;
int i;
int srcu_idx;
@@ -1982,7 +1982,8 @@
*/
if ((threads_per_core > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+ 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);
@@ -2320,6 +2321,7 @@
static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
struct kvm_dirty_log *log)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int r;
unsigned long n;
@@ -2330,7 +2332,8 @@
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
@@ -2373,16 +2376,18 @@
static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return 0;
}
static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
if (npages && old->npages) {
@@ -2392,7 +2397,8 @@
* since the rmap array starts out as all zeroes,
* i.e. no pages are dirty.
*/
- memslot = id_to_memslot(kvm->memslots, mem->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, mem->slot);
kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
}
}
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index f573839..64891b0 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1530,6 +1530,7 @@
static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
struct kvm_dirty_log *log)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
struct kvm_vcpu *vcpu;
ulong ga, ga_end;
@@ -1545,7 +1546,8 @@
/* If nothing is dirty, don't bother messing with page tables. */
if (is_dirty) {
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
ga = memslot->base_gfn << PAGE_SHIFT;
ga_end = ga + (memslot->npages << PAGE_SHIFT);
@@ -1571,14 +1573,15 @@
static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return 0;
}
static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
return;
}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6c1316a..cc58426 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1004,10 +1004,10 @@
break;
}
- local_irq_enable();
-
trace_kvm_exit(exit_nr, vcpu);
- kvm_guest_exit();
+ __kvm_guest_exit();
+
+ local_irq_enable();
run->exit_reason = KVM_EXIT_UNKNOWN;
run->ready_for_interrupt_injection = 1;
@@ -1784,14 +1784,15 @@
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return 0;
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index ac3ddf1..e5dde32 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -115,7 +115,7 @@
continue;
}
- kvm_guest_enter();
+ __kvm_guest_enter();
return 1;
}
@@ -595,18 +595,19 @@
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
- kvmppc_core_commit_memory_region(kvm, mem, old);
+ kvmppc_core_commit_memory_region(kvm, mem, old, new);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 444c412..3024acb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -636,7 +636,7 @@
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_free_memslot(struct kvm *kvm,
struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot) {}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9cb6cfaa..71530a4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -240,6 +240,7 @@
{
int r;
unsigned long n;
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int is_dirty = 0;
@@ -249,7 +250,8 @@
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
@@ -2015,12 +2017,14 @@
* As PF_VCPU will be used in fault handler, between
* guest_enter and guest_exit should be no uaccess.
*/
- preempt_disable();
- kvm_guest_enter();
- preempt_enable();
+ local_irq_disable();
+ __kvm_guest_enter();
+ local_irq_enable();
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
- kvm_guest_exit();
+ local_irq_disable();
+ __kvm_guest_exit();
+ local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
rc = vcpu_post_run(vcpu, exit_reason);
@@ -2583,7 +2587,7 @@
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
/* A few sanity checks. We can have memory slots which have to be
@@ -2601,8 +2605,9 @@
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
int rc;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dea2e7e..7276107 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -207,6 +207,7 @@
unsigned nxe:1;
unsigned cr0_wp:1;
unsigned smep_andnot_wp:1;
+ unsigned smap_andnot_wp:1;
};
};
@@ -400,6 +401,7 @@
struct kvm_mmu_memory_cache mmu_page_header_cache;
struct fpu guest_fpu;
+ bool eager_fpu;
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
@@ -635,6 +637,8 @@
#endif
bool boot_vcpu_runs_old_kvmclock;
+
+ u64 disabled_quirks;
};
struct kvm_vm_stat {
@@ -687,12 +691,13 @@
struct kvm_lapic_irq {
u32 vector;
- u32 delivery_mode;
- u32 dest_mode;
- u32 level;
- u32 trig_mode;
+ u16 delivery_mode;
+ u16 dest_mode;
+ bool level;
+ u16 trig_mode;
u32 shorthand;
u32 dest_id;
+ bool msi_redir_hint;
};
struct kvm_x86_ops {
@@ -709,7 +714,7 @@
/* Create, but do not attach this VCPU */
struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
- void (*vcpu_reset)(struct kvm_vcpu *vcpu);
+ void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
@@ -743,6 +748,7 @@
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+ void (*fpu_activate)(struct kvm_vcpu *vcpu);
void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
void (*tlb_flush)(struct kvm_vcpu *vcpu);
@@ -868,7 +874,7 @@
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
struct kvm_memory_slot *memslot);
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
- struct kvm_memory_slot *memslot);
+ const struct kvm_memory_slot *memslot);
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot);
void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
@@ -999,7 +1005,7 @@
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
-int fx_init(struct kvm_vcpu *vcpu);
+int fx_init(struct kvm_vcpu *vcpu, bool init_event);
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
const u8 *new, int bytes);
@@ -1143,7 +1149,7 @@
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
unsigned long address);
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 6167fd7..655e07a 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,5 +41,6 @@
#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
#define PVCLOCK_GUEST_STOPPED (1 << 1)
+#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index d6b078e..628954c 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -86,7 +86,6 @@
offset = pvclock_get_nsec_offset(src);
ret = src->system_time + offset;
ret_flags = src->flags;
- rdtsc_barrier();
*cycles = ret;
*flags = ret_flags;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d7dcef5..2fec75e 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -345,4 +345,7 @@
struct kvm_sync_regs {
};
+#define KVM_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_QUIRK_CD_NW_CLEARED (1 << 1)
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 9435620..cc34cec 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -331,7 +331,7 @@
apic_write(APIC_EOI, APIC_EOI_ACK);
}
-void kvm_guest_cpu_init(void)
+static void kvm_guest_cpu_init(void)
{
if (!kvm_para_available())
return;
@@ -655,7 +655,7 @@
static struct dentry *d_spin_debug;
static struct dentry *d_kvm_debug;
-struct dentry *kvm_init_debugfs(void)
+static struct dentry *kvm_init_debugfs(void)
{
d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
if (!d_kvm_debug)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 42caaef..49487b4 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,6 +24,7 @@
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/memblock.h>
+#include <linux/sched.h>
#include <asm/x86_init.h>
#include <asm/reboot.h>
@@ -217,8 +218,10 @@
void __init kvmclock_init(void)
{
+ struct pvclock_vcpu_time_info *vcpu_time;
unsigned long mem;
- int size;
+ int size, cpu;
+ u8 flags;
size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
@@ -264,7 +267,14 @@
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
- pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+ pvclock_set_flags(~0);
+
+ cpu = get_cpu();
+ vcpu_time = &hv_clock[cpu].pvti;
+ flags = pvclock_read_flags(vcpu_time);
+ if (flags & PVCLOCK_COUNTS_FROM_ZERO)
+ set_sched_clock_stable();
+ put_cpu();
}
int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 59b69f6..9dadf8d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,8 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
+#include <asm/i387.h> /* For use_eager_fpu. Ugh! */
+#include <asm/fpu-internal.h> /* For use_eager_fpu. Ugh! */
#include <asm/user.h>
#include <asm/xsave.h>
#include "cpuid.h"
@@ -95,6 +97,8 @@
if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
+ vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+
/*
* The existing code assumes virtual address is 48-bit in the canonical
* address checks; exit if it is ever changed.
@@ -411,6 +415,12 @@
}
break;
}
+ case 6: /* Thermal management */
+ entry->eax = 0x4; /* allow ARAT */
+ entry->ebx = 0;
+ entry->ecx = 0;
+ entry->edx = 0;
+ break;
case 7: {
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* Mask ebx against host capability word 9 */
@@ -587,7 +597,6 @@
break;
case 3: /* Processor serial number */
case 5: /* MONITOR/MWAIT */
- case 6: /* Thermal management */
case 0xC0000002:
case 0xC0000003:
case 0xC0000004:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index c3b1ad9..496b369 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -117,4 +117,12 @@
best = kvm_find_cpuid_entry(vcpu, 7, 0);
return best && (best->ebx & bit(X86_FEATURE_RTM));
}
+
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 7, 0);
+ return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
#endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 630bcb0..9b655d1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
#include <linux/module.h>
#include <asm/kvm_emulate.h>
#include <linux/stringify.h>
+#include <asm/debugreg.h>
#include "x86.h"
#include "tss.h"
@@ -523,13 +524,9 @@
static inline void
register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
{
- ulong mask;
+ ulong *preg = reg_rmw(ctxt, reg);
- if (ctxt->ad_bytes == sizeof(unsigned long))
- mask = ~0UL;
- else
- mask = ad_mask(ctxt);
- masked_increment(reg_rmw(ctxt, reg), mask, inc);
+ assign_register(preg, *preg + inc, ctxt->ad_bytes);
}
static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -2573,6 +2570,30 @@
return true;
}
+static void string_registers_quirk(struct x86_emulate_ctxt *ctxt)
+{
+ /*
+ * Intel CPUs mask the counter and pointers in quite strange
+ * manner when ECX is zero due to REP-string optimizations.
+ */
+#ifdef CONFIG_X86_64
+ if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt))
+ return;
+
+ *reg_write(ctxt, VCPU_REGS_RCX) = 0;
+
+ switch (ctxt->b) {
+ case 0xa4: /* movsb */
+ case 0xa5: /* movsd/w */
+ *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1;
+ /* fall through */
+ case 0xaa: /* stosb */
+ case 0xab: /* stosd/w */
+ *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1;
+ }
+#endif
+}
+
static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
struct tss_segment_16 *tss)
{
@@ -2849,7 +2870,7 @@
ulong old_tss_base =
ops->get_cached_segment_base(ctxt, VCPU_SREG_TR);
u32 desc_limit;
- ulong desc_addr;
+ ulong desc_addr, dr7;
/* FIXME: old_tss_base == ~0 ? */
@@ -2934,6 +2955,9 @@
ret = em_push(ctxt);
}
+ ops->get_dr(ctxt, 7, &dr7);
+ ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN));
+
return ret;
}
@@ -3840,7 +3864,7 @@
F(DstMem | SrcNone | Lock, em_inc),
F(DstMem | SrcNone | Lock, em_dec),
I(SrcMem | NearBranch, em_call_near_abs),
- I(SrcMemFAddr | ImplicitOps | Stack, em_call_far),
+ I(SrcMemFAddr | ImplicitOps, em_call_far),
I(SrcMem | NearBranch, em_jmp_abs),
I(SrcMemFAddr | ImplicitOps, em_jmp_far),
I(SrcMem | Stack, em_push), D(Undefined),
@@ -4910,6 +4934,7 @@
if (ctxt->rep_prefix && (ctxt->d & String)) {
/* All REP prefixes have the same first termination condition */
if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
+ string_registers_quirk(ctxt);
ctxt->eip = ctxt->_eip;
ctxt->eflags &= ~X86_EFLAGS_RF;
goto done;
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 28146f0..856f791 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -349,6 +349,7 @@
irqe.delivery_mode = entry->fields.delivery_mode << 8;
irqe.level = 1;
irqe.shorthand = 0;
+ irqe.msi_redir_hint = false;
if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
ioapic->irr_delivered |= 1 << irq;
@@ -637,11 +638,9 @@
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
cancel_delayed_work_sync(&ioapic->eoi_inject);
- if (ioapic) {
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
- kvm->arch.vioapic = NULL;
- kfree(ioapic);
- }
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
+ kvm->arch.vioapic = NULL;
+ kfree(ioapic);
}
int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 72298b3..9efff9e 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -31,6 +31,8 @@
#include "ioapic.h"
+#include "lapic.h"
+
static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status)
@@ -48,11 +50,6 @@
line_status);
}
-inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
-{
- return irq->delivery_mode == APIC_DM_LOWEST;
-}
-
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, unsigned long *dest_map)
{
@@ -60,7 +57,7 @@
struct kvm_vcpu *vcpu, *lowest = NULL;
if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
- kvm_is_dm_lowest_prio(irq)) {
+ kvm_lowest_prio_delivery(irq)) {
printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
irq->delivery_mode = APIC_DM_FIXED;
}
@@ -76,7 +73,7 @@
irq->dest_id, irq->dest_mode))
continue;
- if (!kvm_is_dm_lowest_prio(irq)) {
+ if (!kvm_lowest_prio_delivery(irq)) {
if (r < 0)
r = 0;
r += kvm_apic_set_irq(vcpu, irq, dest_map);
@@ -106,9 +103,10 @@
irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
irq->delivery_mode = e->msi.data & 0x700;
+ irq->msi_redir_hint = ((e->msi.address_lo
+ & MSI_ADDR_REDIRECTION_LOWPRI) > 0);
irq->level = 1;
irq->shorthand = 0;
- /* TODO Deal with RH bit of MSI message address */
}
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 629af0f..c789e00 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -240,6 +240,15 @@
recalculate_apic_map(apic->vcpu->kvm);
}
+static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id)
+{
+ u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+
+ apic_set_reg(apic, APIC_ID, id << 24);
+ apic_set_reg(apic, APIC_LDR, ldr);
+ recalculate_apic_map(apic->vcpu->kvm);
+}
+
static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
{
return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
@@ -728,7 +737,7 @@
dst = map->logical_map[cid];
- if (irq->delivery_mode == APIC_DM_LOWEST) {
+ if (kvm_lowest_prio_delivery(irq)) {
int l = -1;
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
@@ -914,9 +923,10 @@
irq.vector = icr_low & APIC_VECTOR_MASK;
irq.delivery_mode = icr_low & APIC_MODE_MASK;
irq.dest_mode = icr_low & APIC_DEST_MASK;
- irq.level = icr_low & APIC_INT_ASSERT;
+ irq.level = (icr_low & APIC_INT_ASSERT) != 0;
irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
irq.shorthand = icr_low & APIC_SHORT_MASK;
+ irq.msi_redir_hint = false;
if (apic_x2apic_mode(apic))
irq.dest_id = icr_high;
else
@@ -926,10 +936,11 @@
apic_debug("icr_high 0x%x, icr_low 0x%x, "
"short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
- "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n",
+ "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, "
+ "msi_redir_hint 0x%x\n",
icr_high, icr_low, irq.shorthand, irq.dest_id,
irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
- irq.vector);
+ irq.vector, irq.msi_redir_hint);
kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL);
}
@@ -1536,9 +1547,7 @@
if ((old_value ^ value) & X2APIC_ENABLE) {
if (value & X2APIC_ENABLE) {
- u32 id = kvm_apic_id(apic);
- u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
- kvm_apic_set_ldr(apic, ldr);
+ kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
} else
kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
@@ -1557,7 +1566,7 @@
}
-void kvm_lapic_reset(struct kvm_vcpu *vcpu)
+void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct kvm_lapic *apic;
int i;
@@ -1571,19 +1580,22 @@
/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
- kvm_apic_set_id(apic, vcpu->vcpu_id);
+ if (!init_event)
+ kvm_apic_set_id(apic, vcpu->vcpu_id);
kvm_apic_set_version(apic->vcpu);
for (i = 0; i < APIC_LVT_NUM; i++)
apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
apic->lapic_timer.timer_mode = 0;
- apic_set_reg(apic, APIC_LVT0,
- SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
+ if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+ apic_set_reg(apic, APIC_LVT0,
+ SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_set_reg(apic, APIC_DFR, 0xffffffffU);
apic_set_spiv(apic, 0xff);
apic_set_reg(apic, APIC_TASKPRI, 0);
- kvm_apic_set_ldr(apic, 0);
+ if (!apic_x2apic_mode(apic))
+ kvm_apic_set_ldr(apic, 0);
apic_set_reg(apic, APIC_ESR, 0);
apic_set_reg(apic, APIC_ICR, 0);
apic_set_reg(apic, APIC_ICR2, 0);
@@ -1712,7 +1724,7 @@
APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
- kvm_lapic_reset(vcpu);
+ kvm_lapic_reset(vcpu, false);
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
return 0;
@@ -2046,8 +2058,8 @@
pe = xchg(&apic->pending_events, 0);
if (test_bit(KVM_APIC_INIT, &pe)) {
- kvm_lapic_reset(vcpu);
- kvm_vcpu_reset(vcpu);
+ kvm_lapic_reset(vcpu, true);
+ kvm_vcpu_reset(vcpu, true);
if (kvm_vcpu_is_bsp(apic->vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 9d28383..71b150c 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -48,7 +48,7 @@
int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
void kvm_apic_accept_events(struct kvm_vcpu *vcpu);
-void kvm_lapic_reset(struct kvm_vcpu *vcpu);
+void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
@@ -153,6 +153,12 @@
return vcpu->arch.apic->pending_events;
}
+static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
+{
+ return (irq->delivery_mode == APIC_DM_LOWEST ||
+ irq->msi_redir_hint);
+}
+
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
void wait_lapic_expire(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d43867c..a65ce12 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -804,30 +804,32 @@
return &slot->arch.lpage_info[level - 2][idx];
}
-static void account_shadowed(struct kvm *kvm, gfn_t gfn)
+static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memory_slot *slot;
struct kvm_lpage_info *linfo;
+ gfn_t gfn;
int i;
+ gfn = sp->gfn;
slot = gfn_to_memslot(kvm, gfn);
- for (i = PT_DIRECTORY_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
linfo->write_count += 1;
}
kvm->arch.indirect_shadow_pages++;
}
-static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
+static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memory_slot *slot;
struct kvm_lpage_info *linfo;
+ gfn_t gfn;
int i;
+ gfn = sp->gfn;
slot = gfn_to_memslot(kvm, gfn);
- for (i = PT_DIRECTORY_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
linfo->write_count -= 1;
WARN_ON(linfo->write_count < 0);
@@ -858,8 +860,7 @@
page_size = kvm_host_page_size(kvm, gfn);
- for (i = PT_PAGE_TABLE_LEVEL;
- i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) {
+ for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
if (page_size >= KVM_HPAGE_SIZE(i))
ret = i;
else
@@ -1142,6 +1143,11 @@
return NULL;
}
+#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \
+ for (_spte_ = rmap_get_first(*_rmap_, _iter_); \
+ _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \
+ _spte_ = rmap_get_next(_iter_))
+
static void drop_spte(struct kvm *kvm, u64 *sptep)
{
if (mmu_spte_clear_track_bits(sptep))
@@ -1205,12 +1211,8 @@
struct rmap_iterator iter;
bool flush = false;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
flush |= spte_write_protect(kvm, sptep, pt_protect);
- sptep = rmap_get_next(&iter);
- }
return flush;
}
@@ -1232,12 +1234,8 @@
struct rmap_iterator iter;
bool flush = false;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
flush |= spte_clear_dirty(kvm, sptep);
- sptep = rmap_get_next(&iter);
- }
return flush;
}
@@ -1259,12 +1257,8 @@
struct rmap_iterator iter;
bool flush = false;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
flush |= spte_set_dirty(kvm, sptep);
- sptep = rmap_get_next(&iter);
- }
return flush;
}
@@ -1351,8 +1345,7 @@
slot = gfn_to_memslot(kvm, gfn);
- for (i = PT_PAGE_TABLE_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
rmapp = __gfn_to_rmap(gfn, i, slot);
write_protected |= __rmap_write_protect(kvm, rmapp, true);
}
@@ -1360,24 +1353,28 @@
return write_protected;
}
+static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ bool flush = false;
+
+ while ((sptep = rmap_get_first(*rmapp, &iter))) {
+ BUG_ON(!(*sptep & PT_PRESENT_MASK));
+ rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
+
+ drop_spte(kvm, sptep);
+ flush = true;
+ }
+
+ return flush;
+}
+
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
struct kvm_memory_slot *slot, gfn_t gfn, int level,
unsigned long data)
{
- u64 *sptep;
- struct rmap_iterator iter;
- int need_tlb_flush = 0;
-
- while ((sptep = rmap_get_first(*rmapp, &iter))) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
- rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
- sptep, *sptep, gfn, level);
-
- drop_spte(kvm, sptep);
- need_tlb_flush = 1;
- }
-
- return need_tlb_flush;
+ return kvm_zap_rmapp(kvm, rmapp);
}
static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
@@ -1394,8 +1391,8 @@
WARN_ON(pte_huge(*ptep));
new_pfn = pte_pfn(*ptep);
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!is_shadow_present_pte(*sptep));
+restart:
+ for_each_rmap_spte(rmapp, &iter, sptep) {
rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
sptep, *sptep, gfn, level);
@@ -1403,7 +1400,7 @@
if (pte_write(*ptep)) {
drop_spte(kvm, sptep);
- sptep = rmap_get_first(*rmapp, &iter);
+ goto restart;
} else {
new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
new_spte |= (u64)new_pfn << PAGE_SHIFT;
@@ -1414,7 +1411,6 @@
mmu_spte_clear_track_bits(sptep);
mmu_spte_set(sptep, new_spte);
- sptep = rmap_get_next(&iter);
}
}
@@ -1424,6 +1420,74 @@
return 0;
}
+struct slot_rmap_walk_iterator {
+ /* input fields. */
+ struct kvm_memory_slot *slot;
+ gfn_t start_gfn;
+ gfn_t end_gfn;
+ int start_level;
+ int end_level;
+
+ /* output fields. */
+ gfn_t gfn;
+ unsigned long *rmap;
+ int level;
+
+ /* private field. */
+ unsigned long *end_rmap;
+};
+
+static void
+rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
+{
+ iterator->level = level;
+ iterator->gfn = iterator->start_gfn;
+ iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot);
+ iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level,
+ iterator->slot);
+}
+
+static void
+slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
+ struct kvm_memory_slot *slot, int start_level,
+ int end_level, gfn_t start_gfn, gfn_t end_gfn)
+{
+ iterator->slot = slot;
+ iterator->start_level = start_level;
+ iterator->end_level = end_level;
+ iterator->start_gfn = start_gfn;
+ iterator->end_gfn = end_gfn;
+
+ rmap_walk_init_level(iterator, iterator->start_level);
+}
+
+static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
+{
+ return !!iterator->rmap;
+}
+
+static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
+{
+ if (++iterator->rmap <= iterator->end_rmap) {
+ iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
+ return;
+ }
+
+ if (++iterator->level > iterator->end_level) {
+ iterator->rmap = NULL;
+ return;
+ }
+
+ rmap_walk_init_level(iterator, iterator->level);
+}
+
+#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \
+ _start_gfn, _end_gfn, _iter_) \
+ for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \
+ _end_level_, _start_gfn, _end_gfn); \
+ slot_rmap_walk_okay(_iter_); \
+ slot_rmap_walk_next(_iter_))
+
static int kvm_handle_hva_range(struct kvm *kvm,
unsigned long start,
unsigned long end,
@@ -1435,10 +1499,10 @@
int level,
unsigned long data))
{
- int j;
- int ret = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
+ struct slot_rmap_walk_iterator iterator;
+ int ret = 0;
slots = kvm_memslots(kvm);
@@ -1458,26 +1522,11 @@
gfn_start = hva_to_gfn_memslot(hva_start, memslot);
gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
- for (j = PT_PAGE_TABLE_LEVEL;
- j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
- unsigned long idx, idx_end;
- unsigned long *rmapp;
- gfn_t gfn = gfn_start;
-
- /*
- * {idx(page_j) | page_j intersects with
- * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
- */
- idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
- idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
-
- rmapp = __gfn_to_rmap(gfn_start, j, memslot);
-
- for (; idx <= idx_end;
- ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
- ret |= handler(kvm, rmapp++, memslot,
- gfn, j, data);
- }
+ for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL,
+ PT_MAX_HUGEPAGE_LEVEL, gfn_start, gfn_end - 1,
+ &iterator)
+ ret |= handler(kvm, iterator.rmap, memslot,
+ iterator.gfn, iterator.level, data);
}
return ret;
@@ -1518,16 +1567,13 @@
BUG_ON(!shadow_accessed_mask);
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;
- sptep = rmap_get_next(&iter)) {
- BUG_ON(!is_shadow_present_pte(*sptep));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
if (*sptep & shadow_accessed_mask) {
young = 1;
clear_bit((ffs(shadow_accessed_mask) - 1),
(unsigned long *)sptep);
}
- }
+
trace_kvm_age_page(gfn, level, slot, young);
return young;
}
@@ -1548,15 +1594,11 @@
if (!shadow_accessed_mask)
goto out;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;
- sptep = rmap_get_next(&iter)) {
- BUG_ON(!is_shadow_present_pte(*sptep));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
if (*sptep & shadow_accessed_mask) {
young = 1;
break;
}
- }
out:
return young;
}
@@ -2093,7 +2135,7 @@
if (level > PT_PAGE_TABLE_LEVEL && need_sync)
kvm_sync_pages(vcpu, gfn);
- account_shadowed(vcpu->kvm, gfn);
+ account_shadowed(vcpu->kvm, sp);
}
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
init_shadow_page_table(sp);
@@ -2274,7 +2316,7 @@
kvm_mmu_unlink_parents(kvm, sp);
if (!sp->role.invalid && !sp->role.direct)
- unaccount_shadowed(kvm, sp->gfn);
+ unaccount_shadowed(kvm, sp);
if (sp->unsync)
kvm_unlink_unsync_page(kvm, sp);
@@ -2393,19 +2435,20 @@
static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
u64 start, u64 end)
{
- int i;
u64 base, mask;
u8 prev_match, curr_match;
- int num_var_ranges = KVM_NR_VAR_MTRR;
+ int i, num_var_ranges = KVM_NR_VAR_MTRR;
- if (!mtrr_state->enabled)
- return 0xFF;
+ /* MTRR is completely disabled, use UC for all of physical memory. */
+ if (!(mtrr_state->enabled & 0x2))
+ return MTRR_TYPE_UNCACHABLE;
/* Make end inclusive end, instead of exclusive */
end--;
/* Look in fixed ranges. Just return the type as per start */
- if (mtrr_state->have_fixed && (start < 0x100000)) {
+ if (mtrr_state->have_fixed && (mtrr_state->enabled & 0x1) &&
+ (start < 0x100000)) {
int idx;
if (start < 0x80000) {
@@ -2428,9 +2471,6 @@
* Look of multiple ranges matching this address and pick type
* as per MTRR precedence
*/
- if (!(mtrr_state->enabled & 2))
- return mtrr_state->def_type;
-
prev_match = 0xFF;
for (i = 0; i < num_var_ranges; ++i) {
unsigned short start_state, end_state;
@@ -2692,15 +2732,17 @@
u64 *start, u64 *end)
{
struct page *pages[PTE_PREFETCH_NUM];
+ struct kvm_memory_slot *slot;
unsigned access = sp->role.access;
int i, ret;
gfn_t gfn;
gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
- if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK))
+ slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
+ if (!slot)
return -1;
- ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start);
+ ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
if (ret <= 0)
return -1;
@@ -3475,10 +3517,12 @@
static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
gva_t gva, pfn_t *pfn, bool write, bool *writable)
{
+ struct kvm_memory_slot *slot;
bool async;
- *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable);
-
+ slot = gfn_to_memslot(vcpu->kvm, gfn);
+ async = false;
+ *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
if (!async)
return false; /* *pfn has correct page already */
@@ -3492,8 +3536,7 @@
return true;
}
- *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable);
-
+ *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
return false;
}
@@ -3736,8 +3779,8 @@
}
}
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
- struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu, bool ept)
{
unsigned bit, byte, pfec;
u8 map;
@@ -3918,6 +3961,7 @@
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
struct kvm_mmu *context = &vcpu->arch.mmu;
MMU_WARN_ON(VALID_PAGE(context->root_hpa));
@@ -3936,6 +3980,8 @@
context->base_role.cr0_wp = is_write_protection(vcpu);
context->base_role.smep_andnot_wp
= smep && !is_write_protection(vcpu);
+ context->base_role.smap_andnot_wp
+ = smap && !is_write_protection(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
@@ -4207,12 +4253,18 @@
const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
- union kvm_mmu_page_role mask = { .word = 0 };
struct kvm_mmu_page *sp;
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
bool remote_flush, local_flush, zap_page;
+ union kvm_mmu_page_role mask = { };
+
+ mask.cr0_wp = 1;
+ mask.cr4_pae = 1;
+ mask.nxe = 1;
+ mask.smep_andnot_wp = 1;
+ mask.smap_andnot_wp = 1;
/*
* If we don't have indirect shadow pages, it means no page is
@@ -4238,7 +4290,6 @@
++vcpu->kvm->stat.mmu_pte_write;
kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
- mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
detect_write_flooding(sp)) {
@@ -4412,35 +4463,112 @@
init_kvm_mmu(vcpu);
}
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
- struct kvm_memory_slot *memslot)
+/* The return value indicates if tlb flush on all vcpus is needed. */
+typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
+
+/* The caller should hold mmu-lock before calling this function. */
+static bool
+slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, int start_level, int end_level,
+ gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)
{
- gfn_t last_gfn;
- int i;
+ struct slot_rmap_walk_iterator iterator;
bool flush = false;
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
+ end_gfn, &iterator) {
+ if (iterator.rmap)
+ flush |= fn(kvm, iterator.rmap);
- spin_lock(&kvm->mmu_lock);
-
- for (i = PT_PAGE_TABLE_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- unsigned long *rmapp;
- unsigned long last_index, index;
-
- rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_write_protect(kvm, rmapp,
- false);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ if (flush && lock_flush_tlb) {
+ kvm_flush_remote_tlbs(kvm);
+ flush = false;
+ }
+ cond_resched_lock(&kvm->mmu_lock);
}
}
+ if (flush && lock_flush_tlb) {
+ kvm_flush_remote_tlbs(kvm);
+ flush = false;
+ }
+
+ return flush;
+}
+
+static bool
+slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, int start_level, int end_level,
+ bool lock_flush_tlb)
+{
+ return slot_handle_level_range(kvm, memslot, fn, start_level,
+ end_level, memslot->base_gfn,
+ memslot->base_gfn + memslot->npages - 1,
+ lock_flush_tlb);
+}
+
+static bool
+slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool lock_flush_tlb)
+{
+ return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+ PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
+}
+
+static bool
+slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool lock_flush_tlb)
+{
+ return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1,
+ PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
+}
+
+static bool
+slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool lock_flush_tlb)
+{
+ return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+ PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
+}
+
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+
+ slots = kvm_memslots(kvm);
+
+ spin_lock(&kvm->mmu_lock);
+ kvm_for_each_memslot(memslot, slots) {
+ gfn_t start, end;
+
+ start = max(gfn_start, memslot->base_gfn);
+ end = min(gfn_end, memslot->base_gfn + memslot->npages);
+ if (start >= end)
+ continue;
+
+ slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
+ PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL,
+ start, end - 1, true);
+ }
+
+ spin_unlock(&kvm->mmu_lock);
+}
+
+static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp)
+{
+ return __rmap_write_protect(kvm, rmapp, false);
+}
+
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+ struct kvm_memory_slot *memslot)
+{
+ bool flush;
+
+ spin_lock(&kvm->mmu_lock);
+ flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect,
+ false);
spin_unlock(&kvm->mmu_lock);
/*
@@ -4474,9 +4602,8 @@
pfn_t pfn;
struct kvm_mmu_page *sp;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+restart:
+ for_each_rmap_spte(rmapp, &iter, sptep) {
sp = page_header(__pa(sptep));
pfn = spte_to_pfn(*sptep);
@@ -4491,71 +4618,31 @@
!kvm_is_reserved_pfn(pfn) &&
PageTransCompound(pfn_to_page(pfn))) {
drop_spte(kvm, sptep);
- sptep = rmap_get_first(*rmapp, &iter);
need_tlb_flush = 1;
- } else
- sptep = rmap_get_next(&iter);
+ goto restart;
+ }
}
return need_tlb_flush;
}
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
- struct kvm_memory_slot *memslot)
+ const struct kvm_memory_slot *memslot)
{
- bool flush = false;
- unsigned long *rmapp;
- unsigned long last_index, index;
-
+ /* FIXME: const-ify all uses of struct kvm_memory_slot. */
spin_lock(&kvm->mmu_lock);
-
- rmapp = memslot->arch.rmap[0];
- last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1,
- memslot->base_gfn, PT_PAGE_TABLE_LEVEL);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
- if (flush) {
- kvm_flush_remote_tlbs(kvm);
- flush = false;
- }
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
-
- if (flush)
- kvm_flush_remote_tlbs(kvm);
-
+ slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
+ kvm_mmu_zap_collapsible_spte, true);
spin_unlock(&kvm->mmu_lock);
}
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
- gfn_t last_gfn;
- unsigned long *rmapp;
- unsigned long last_index, index;
- bool flush = false;
-
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ bool flush;
spin_lock(&kvm->mmu_lock);
-
- rmapp = memslot->arch.rmap[PT_PAGE_TABLE_LEVEL - 1];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn,
- PT_PAGE_TABLE_LEVEL);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_clear_dirty(kvm, rmapp);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
- }
-
+ flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
spin_unlock(&kvm->mmu_lock);
lockdep_assert_held(&kvm->slots_lock);
@@ -4574,31 +4661,11 @@
void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
- gfn_t last_gfn;
- int i;
- bool flush = false;
-
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ bool flush;
spin_lock(&kvm->mmu_lock);
-
- for (i = PT_PAGE_TABLE_LEVEL + 1; /* skip rmap for 4K page */
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- unsigned long *rmapp;
- unsigned long last_index, index;
-
- rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_write_protect(kvm, rmapp,
- false);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
+ flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
+ false);
spin_unlock(&kvm->mmu_lock);
/* see kvm_mmu_slot_remove_write_access */
@@ -4612,31 +4679,10 @@
void kvm_mmu_slot_set_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
- gfn_t last_gfn;
- int i;
- bool flush = false;
-
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ bool flush;
spin_lock(&kvm->mmu_lock);
-
- for (i = PT_PAGE_TABLE_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- unsigned long *rmapp;
- unsigned long last_index, index;
-
- rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_set_dirty(kvm, rmapp);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
-
+ flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
spin_unlock(&kvm->mmu_lock);
lockdep_assert_held(&kvm->slots_lock);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index c7d6563..398d21c 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,6 +43,7 @@
#define PT_PDPE_LEVEL 3
#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1
+#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1)
static inline u64 rsvd_bits(int s, int e)
{
@@ -71,8 +72,6 @@
int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- bool ept);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
@@ -166,8 +165,11 @@
int index = (pfec >> 1) +
(smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+ WARN_ON(pfec & PFERR_RSVD_MASK);
+
return (mmu->permissions[index] >> pte_access) & 1;
}
void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
#endif
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 9ade5cf..368d534 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -197,13 +197,11 @@
rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL);
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;
- sptep = rmap_get_next(&iter)) {
+ for_each_rmap_spte(rmapp, &iter, sptep)
if (is_writable_pte(*sptep))
audit_printk(kvm, "shadow page has writable "
"mappings: gfn %llx role %x\n",
sp->gfn, sp->role.word);
- }
}
static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index fd49c86..6e6d115 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -718,6 +718,13 @@
mmu_is_nested(vcpu));
if (likely(r != RET_MMIO_PF_INVALID))
return r;
+
+ /*
+ * page fault with PFEC.RSVD = 1 is caused by shadow
+ * page fault, should not be used to walk guest page
+ * table.
+ */
+ error_code &= ~PFERR_RSVD_MASK;
};
r = mmu_topup_memory_caches(vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ce741b8..b9f9e10 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1082,7 +1082,7 @@
return target_tsc - tsc;
}
-static void init_vmcb(struct vcpu_svm *svm)
+static void init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
@@ -1153,17 +1153,17 @@
init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
- svm_set_efer(&svm->vcpu, 0);
+ if (!init_event)
+ svm_set_efer(&svm->vcpu, 0);
save->dr6 = 0xffff0ff0;
kvm_set_rflags(&svm->vcpu, 2);
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
/*
- * This is the guest-visible cr0 value.
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
+ * It also updates the guest-visible cr0 value.
*/
- svm->vcpu.arch.cr0 = 0;
(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
save->cr4 = X86_CR4_PAE;
@@ -1176,7 +1176,7 @@
clr_exception_intercept(svm, PF_VECTOR);
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
- save->g_pat = 0x0007040600070406ULL;
+ save->g_pat = svm->vcpu.arch.pat;
save->cr3 = 0;
save->cr4 = 0;
}
@@ -1195,13 +1195,19 @@
enable_gif(svm);
}
-static void svm_vcpu_reset(struct kvm_vcpu *vcpu)
+static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 dummy;
u32 eax = 1;
- init_vmcb(svm);
+ if (!init_event) {
+ svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
+ if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
+ svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ }
+ init_vmcb(svm, init_event);
kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
@@ -1257,12 +1263,7 @@
clear_page(svm->vmcb);
svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
svm->asid_generation = 0;
- init_vmcb(svm);
-
- svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
- MSR_IA32_APICBASE_ENABLE;
- if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
- svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ init_vmcb(svm, false);
svm_init_osvw(&svm->vcpu);
@@ -1575,7 +1576,8 @@
* does not do it - this results in some delay at
* reboot
*/
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+ if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
update_cr0_intercept(svm);
@@ -1883,7 +1885,7 @@
* so reinitialize it.
*/
clear_page(svm->vmcb);
- init_vmcb(svm);
+ init_vmcb(svm, false);
kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
return 0;
@@ -4381,6 +4383,7 @@
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
+ .fpu_activate = svm_fpu_activate,
.fpu_deactivate = svm_fpu_deactivate,
.tlb_flush = svm_flush_tlb,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b6168..9cf5030 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2170,8 +2170,7 @@
if (is_guest_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_nested;
- else if (irqchip_in_kernel(vcpu->kvm) &&
- apic_x2apic_mode(vcpu->arch.apic)) {
+ else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
if (is_long_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
else
@@ -4667,16 +4666,8 @@
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
- if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
- u32 msr_low, msr_high;
- u64 host_pat;
- rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
- host_pat = msr_low | ((u64) msr_high << 32);
- /* Write the default value follow host pat */
- vmcs_write64(GUEST_IA32_PAT, host_pat);
- /* Keep arch.pat sync with GUEST_IA32_PAT */
- vmx->vcpu.arch.pat = host_pat;
- }
+ if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+ vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
u32 index = vmx_msr_index[i];
@@ -4708,22 +4699,27 @@
return 0;
}
-static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
+static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct msr_data apic_base_msr;
+ u64 cr0;
vmx->rmode.vm86_active = 0;
vmx->soft_vnmi_blocked = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
- kvm_set_cr8(&vmx->vcpu, 0);
- apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
- if (kvm_vcpu_is_reset_bsp(&vmx->vcpu))
- apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
- apic_base_msr.host_initiated = true;
- kvm_set_apic_base(&vmx->vcpu, &apic_base_msr);
+ kvm_set_cr8(vcpu, 0);
+
+ if (!init_event) {
+ apic_base_msr.data = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
+ if (kvm_vcpu_is_reset_bsp(vcpu))
+ apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
+ apic_base_msr.host_initiated = true;
+ kvm_set_apic_base(vcpu, &apic_base_msr);
+ }
vmx_segment_cache_clear(vmx);
@@ -4747,9 +4743,12 @@
vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
- vmcs_write32(GUEST_SYSENTER_CS, 0);
- vmcs_writel(GUEST_SYSENTER_ESP, 0);
- vmcs_writel(GUEST_SYSENTER_EIP, 0);
+ if (!init_event) {
+ vmcs_write32(GUEST_SYSENTER_CS, 0);
+ vmcs_writel(GUEST_SYSENTER_ESP, 0);
+ vmcs_writel(GUEST_SYSENTER_EIP, 0);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+ }
vmcs_writel(GUEST_RFLAGS, 0x02);
kvm_rip_write(vcpu, 0xfff0);
@@ -4764,18 +4763,15 @@
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
- /* Special registers */
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
-
setup_msrs(vmx);
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */
- if (cpu_has_vmx_tpr_shadow()) {
+ if (cpu_has_vmx_tpr_shadow() && !init_event) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
- if (vm_need_tpr_shadow(vmx->vcpu.kvm))
+ if (vm_need_tpr_shadow(vcpu->kvm))
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
- __pa(vmx->vcpu.arch.apic->regs));
+ __pa(vcpu->arch.apic->regs));
vmcs_write32(TPR_THRESHOLD, 0);
}
@@ -4787,12 +4783,14 @@
if (vmx->vpid != 0)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
- vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
- vmx_set_cr4(&vmx->vcpu, 0);
- vmx_set_efer(&vmx->vcpu, 0);
- vmx_fpu_activate(&vmx->vcpu);
- update_exception_bitmap(&vmx->vcpu);
+ cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+ vmx_set_cr0(vcpu, cr0); /* enter rmode */
+ vmx->vcpu.arch.cr0 = cr0;
+ vmx_set_cr4(vcpu, 0);
+ if (!init_event)
+ vmx_set_efer(vcpu, 0);
+ vmx_fpu_activate(vcpu);
+ update_exception_bitmap(vcpu);
vpid_sync_context(vmx);
}
@@ -5710,9 +5708,6 @@
return 0;
}
- /* clear all local breakpoint enable flags */
- vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155);
-
/*
* TODO: What about debug traps on tss switch?
* Are we supposed to inject them and update dr6?
@@ -7691,6 +7686,158 @@
kvm_vcpu_kick(vcpu);
}
+static void vmx_dump_sel(char *name, uint32_t sel)
+{
+ pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
+ name, vmcs_read32(sel),
+ vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
+ vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
+ vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
+}
+
+static void vmx_dump_dtsel(char *name, uint32_t limit)
+{
+ pr_err("%s limit=0x%08x, base=0x%016lx\n",
+ name, vmcs_read32(limit),
+ vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
+}
+
+static void dump_vmcs(void)
+{
+ u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+ u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+ u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+ u32 secondary_exec_control = 0;
+ unsigned long cr4 = vmcs_readl(GUEST_CR4);
+ u64 efer = vmcs_readl(GUEST_IA32_EFER);
+ int i, n;
+
+ if (cpu_has_secondary_exec_ctrls())
+ secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+ pr_err("*** Guest State ***\n");
+ pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+ vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW),
+ vmcs_readl(CR0_GUEST_HOST_MASK));
+ pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+ cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
+ pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
+ if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
+ (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
+ {
+ pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n",
+ vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1));
+ pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n",
+ vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3));
+ }
+ pr_err("RSP = 0x%016lx RIP = 0x%016lx\n",
+ vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
+ pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n",
+ vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7));
+ pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+ vmcs_readl(GUEST_SYSENTER_ESP),
+ vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP));
+ vmx_dump_sel("CS: ", GUEST_CS_SELECTOR);
+ vmx_dump_sel("DS: ", GUEST_DS_SELECTOR);
+ vmx_dump_sel("SS: ", GUEST_SS_SELECTOR);
+ vmx_dump_sel("ES: ", GUEST_ES_SELECTOR);
+ vmx_dump_sel("FS: ", GUEST_FS_SELECTOR);
+ vmx_dump_sel("GS: ", GUEST_GS_SELECTOR);
+ vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT);
+ vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
+ vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
+ vmx_dump_sel("TR: ", GUEST_TR_SELECTOR);
+ if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
+ (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
+ pr_err("EFER = 0x%016llx PAT = 0x%016lx\n",
+ efer, vmcs_readl(GUEST_IA32_PAT));
+ pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n",
+ vmcs_readl(GUEST_IA32_DEBUGCTL),
+ vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
+ if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+ pr_err("PerfGlobCtl = 0x%016lx\n",
+ vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL));
+ if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
+ pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS));
+ pr_err("Interruptibility = %08x ActivityState = %08x\n",
+ vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
+ vmcs_read32(GUEST_ACTIVITY_STATE));
+ if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
+ pr_err("InterruptStatus = %04x\n",
+ vmcs_read16(GUEST_INTR_STATUS));
+
+ pr_err("*** Host State ***\n");
+ pr_err("RIP = 0x%016lx RSP = 0x%016lx\n",
+ vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
+ pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n",
+ vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR),
+ vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR),
+ vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR),
+ vmcs_read16(HOST_TR_SELECTOR));
+ pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n",
+ vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE),
+ vmcs_readl(HOST_TR_BASE));
+ pr_err("GDTBase=%016lx IDTBase=%016lx\n",
+ vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE));
+ pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n",
+ vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3),
+ vmcs_readl(HOST_CR4));
+ pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+ vmcs_readl(HOST_IA32_SYSENTER_ESP),
+ vmcs_read32(HOST_IA32_SYSENTER_CS),
+ vmcs_readl(HOST_IA32_SYSENTER_EIP));
+ if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
+ pr_err("EFER = 0x%016lx PAT = 0x%016lx\n",
+ vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT));
+ if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ pr_err("PerfGlobCtl = 0x%016lx\n",
+ vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL));
+
+ pr_err("*** Control State ***\n");
+ pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
+ pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control);
+ pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl);
+ pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n",
+ vmcs_read32(EXCEPTION_BITMAP),
+ vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK),
+ vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH));
+ pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n",
+ vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
+ vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE),
+ vmcs_read32(VM_ENTRY_INSTRUCTION_LEN));
+ pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n",
+ vmcs_read32(VM_EXIT_INTR_INFO),
+ vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
+ pr_err(" reason=%08x qualification=%016lx\n",
+ vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION));
+ pr_err("IDTVectoring: info=%08x errcode=%08x\n",
+ vmcs_read32(IDT_VECTORING_INFO_FIELD),
+ vmcs_read32(IDT_VECTORING_ERROR_CODE));
+ pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET));
+ if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
+ pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
+ if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
+ pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
+ if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
+ pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER));
+ n = vmcs_read32(CR3_TARGET_COUNT);
+ for (i = 0; i + 1 < n; i += 4)
+ pr_err("CR3 target%u=%016lx target%u=%016lx\n",
+ i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2),
+ i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2));
+ if (i < n)
+ pr_err("CR3 target%u=%016lx\n",
+ i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2));
+ if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+ pr_err("PLE Gap=%08x Window=%08x\n",
+ vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW));
+ if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
+ pr_err("Virtual processor ID = 0x%04x\n",
+ vmcs_read16(VIRTUAL_PROCESSOR_ID));
+}
+
/*
* The guest has exited. See if we can fix it or if we need userspace
* assistance.
@@ -7723,6 +7870,7 @@
}
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
+ dump_vmcs();
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->run->fail_entry.hardware_entry_failure_reason
= exit_reason;
@@ -8924,7 +9072,7 @@
struct vmx_msr_entry *e)
{
/* x2APIC MSR accesses are not allowed */
- if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8)
+ if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
return -EINVAL;
if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
e->index == MSR_IA32_UCODE_REV)
@@ -10185,6 +10333,7 @@
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
+ .fpu_activate = vmx_fpu_activate,
.fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c73efcd..79dde16 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -99,6 +99,9 @@
unsigned int min_timer_period_us = 500;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
+static bool __read_mostly kvmclock_periodic_sync = true;
+module_param(kvmclock_periodic_sync, bool, S_IRUGO);
+
bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32 kvm_max_guest_tsc_khz;
@@ -572,8 +575,7 @@
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
unsigned long old_cr0 = kvm_read_cr0(vcpu);
- unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
- X86_CR0_CD | X86_CR0_NW;
+ unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
cr0 |= X86_CR0_ET;
@@ -702,8 +704,9 @@
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
- unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
- X86_CR4_PAE | X86_CR4_SMEP;
+ unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+ X86_CR4_SMEP | X86_CR4_SMAP;
+
if (cr4 & CR4_RESERVED_BITS)
return 1;
@@ -744,9 +747,6 @@
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
- if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
- update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
kvm_update_cpuid(vcpu);
@@ -1700,6 +1700,8 @@
vcpu->pvclock_set_guest_stopped_request = false;
}
+ pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
+
/* If the host uses TSC clocksource, then it is stable */
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -1770,6 +1772,9 @@
kvmclock_sync_work);
struct kvm *kvm = container_of(ka, struct kvm, arch);
+ if (!kvmclock_periodic_sync)
+ return;
+
schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
KVMCLOCK_SYNC_PERIOD);
@@ -1854,6 +1859,63 @@
}
EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
+static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct mtrr_state_type *mtrr_state = &vcpu->arch.mtrr_state;
+ unsigned char mtrr_enabled = mtrr_state->enabled;
+ gfn_t start, end, mask;
+ int index;
+ bool is_fixed = true;
+
+ if (msr == MSR_IA32_CR_PAT || !tdp_enabled ||
+ !kvm_arch_has_noncoherent_dma(vcpu->kvm))
+ return;
+
+ if (!(mtrr_enabled & 0x2) && msr != MSR_MTRRdefType)
+ return;
+
+ switch (msr) {
+ case MSR_MTRRfix64K_00000:
+ start = 0x0;
+ end = 0x80000;
+ break;
+ case MSR_MTRRfix16K_80000:
+ start = 0x80000;
+ end = 0xa0000;
+ break;
+ case MSR_MTRRfix16K_A0000:
+ start = 0xa0000;
+ end = 0xc0000;
+ break;
+ case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
+ index = msr - MSR_MTRRfix4K_C0000;
+ start = 0xc0000 + index * (32 << 10);
+ end = start + (32 << 10);
+ break;
+ case MSR_MTRRdefType:
+ is_fixed = false;
+ start = 0x0;
+ end = ~0ULL;
+ break;
+ default:
+ /* variable range MTRRs. */
+ is_fixed = false;
+ index = (msr - 0x200) / 2;
+ start = (((u64)mtrr_state->var_ranges[index].base_hi) << 32) +
+ (mtrr_state->var_ranges[index].base_lo & PAGE_MASK);
+ mask = (((u64)mtrr_state->var_ranges[index].mask_hi) << 32) +
+ (mtrr_state->var_ranges[index].mask_lo & PAGE_MASK);
+ mask |= ~0ULL << cpuid_maxphyaddr(vcpu);
+
+ end = ((start & mask) | ~mask) + 1;
+ }
+
+ if (is_fixed && !(mtrr_enabled & 0x1))
+ return;
+
+ kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end));
+}
+
static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
@@ -1887,7 +1949,7 @@
*pt = data;
}
- kvm_mmu_reset_context(vcpu);
+ update_mtrr(vcpu, msr);
return 0;
}
@@ -2222,6 +2284,8 @@
&vcpu->requests);
ka->boot_vcpu_runs_old_kvmclock = tmp;
+
+ ka->kvmclock_offset = -get_kernel_ns();
}
vcpu->arch.time = data;
@@ -2800,6 +2864,8 @@
case KVM_CAP_HYPERV_TIME:
case KVM_CAP_IOAPIC_POLARITY_IGNORED:
case KVM_CAP_TSC_DEADLINE_TIMER:
+ case KVM_CAP_ENABLE_CAP_VM:
+ case KVM_CAP_DISABLE_QUIRKS:
#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_PCI_2_3:
@@ -3847,6 +3913,26 @@
return 0;
}
+static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+ struct kvm_enable_cap *cap)
+{
+ int r;
+
+ if (cap->flags)
+ return -EINVAL;
+
+ switch (cap->cap) {
+ case KVM_CAP_DISABLE_QUIRKS:
+ kvm->arch.disabled_quirks = cap->args[0];
+ r = 0;
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -4099,7 +4185,15 @@
r = 0;
break;
}
+ case KVM_ENABLE_CAP: {
+ struct kvm_enable_cap cap;
+ r = -EFAULT;
+ if (copy_from_user(&cap, argp, sizeof(cap)))
+ goto out;
+ r = kvm_vm_ioctl_enable_cap(kvm, &cap);
+ break;
+ }
default:
r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
}
@@ -5954,6 +6048,7 @@
lapic_irq.shorthand = 0;
lapic_irq.dest_mode = 0;
lapic_irq.dest_id = apicid;
+ lapic_irq.msi_redir_hint = false;
lapic_irq.delivery_mode = APIC_DM_REMRD;
kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
@@ -6197,6 +6292,8 @@
return;
page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+ if (is_error_page(page))
+ return;
kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
/*
@@ -6347,7 +6444,7 @@
if (req_immediate_exit)
smp_send_reschedule(vcpu->cpu);
- kvm_guest_enter();
+ __kvm_guest_enter();
if (unlikely(vcpu->arch.switch_db_regs)) {
set_debugreg(0, 7);
@@ -7003,7 +7100,7 @@
return 0;
}
-int fx_init(struct kvm_vcpu *vcpu)
+int fx_init(struct kvm_vcpu *vcpu, bool init_event)
{
int err;
@@ -7011,7 +7108,9 @@
if (err)
return err;
- fpu_finit(&vcpu->arch.guest_fpu);
+ if (!init_event)
+ fpu_finit(&vcpu->arch.guest_fpu);
+
if (cpu_has_xsaves)
vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
host_xcr0 | XSTATE_COMPACTION_ENABLED;
@@ -7053,14 +7152,25 @@
{
kvm_put_guest_xcr0(vcpu);
- if (!vcpu->guest_fpu_loaded)
+ if (!vcpu->guest_fpu_loaded) {
+ vcpu->fpu_counter = 0;
return;
+ }
vcpu->guest_fpu_loaded = 0;
fpu_save_init(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+ /*
+ * If using eager FPU mode, or if the guest is a frequent user
+ * of the FPU, just leave the FPU active for next time.
+ * Every 255 times fpu_counter rolls over to 0; a guest that uses
+ * the FPU in bursts will revert to loading it on demand.
+ */
+ if (!vcpu->arch.eager_fpu) {
+ if (++vcpu->fpu_counter < 5)
+ kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+ }
trace_kvm_fpu(0);
}
@@ -7076,11 +7186,21 @@
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
unsigned int id)
{
+ struct kvm_vcpu *vcpu;
+
if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
printk_once(KERN_WARNING
"kvm: SMP vm created on host with unstable TSC; "
"guest TSC will not be reliable\n");
- return kvm_x86_ops->vcpu_create(kvm, id);
+
+ vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+
+ /*
+ * Activate fpu unconditionally in case the guest needs eager FPU. It will be
+ * deactivated soon if it doesn't.
+ */
+ kvm_x86_ops->fpu_activate(vcpu);
+ return vcpu;
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -7091,7 +7211,7 @@
r = vcpu_load(vcpu);
if (r)
return r;
- kvm_vcpu_reset(vcpu);
+ kvm_vcpu_reset(vcpu, false);
kvm_mmu_setup(vcpu);
vcpu_put(vcpu);
@@ -7111,6 +7231,9 @@
kvm_write_tsc(vcpu, &msr);
vcpu_put(vcpu);
+ if (!kvmclock_periodic_sync)
+ return;
+
schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
KVMCLOCK_SYNC_PERIOD);
}
@@ -7129,7 +7252,7 @@
kvm_x86_ops->vcpu_free(vcpu);
}
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
@@ -7156,13 +7279,14 @@
kvm_async_pf_hash_reset(vcpu);
vcpu->arch.apf.halted = false;
- kvm_pmu_reset(vcpu);
+ if (!init_event)
+ kvm_pmu_reset(vcpu);
memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
- kvm_x86_ops->vcpu_reset(vcpu);
+ kvm_x86_ops->vcpu_reset(vcpu, init_event);
}
void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
@@ -7351,7 +7475,7 @@
goto fail_free_mce_banks;
}
- r = fx_init(vcpu);
+ r = fx_init(vcpu, false);
if (r)
goto fail_free_wbinvd_dirty_mask;
@@ -7363,6 +7487,8 @@
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+ vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
+
kvm_async_pf_hash_reset(vcpu);
kvm_pmu_init(vcpu);
@@ -7576,7 +7702,7 @@
return -ENOMEM;
}
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
{
/*
* memslots->generation has been incremented.
@@ -7587,7 +7713,7 @@
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
/*
@@ -7665,14 +7791,14 @@
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
- struct kvm_memory_slot *new;
int nr_mmu_pages = 0;
- if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) {
+ if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) {
int ret;
ret = vm_munmap(old->userspace_addr,
@@ -7689,9 +7815,6 @@
if (nr_mmu_pages)
kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
- /* It's OK to get 'new' slot here as it has already been installed */
- new = id_to_memslot(kvm->memslots, mem->slot);
-
/*
* Dirty logging tracks sptes in 4k granularity, meaning that large
* sptes have to be split. If live migration is successful, the guest
@@ -7716,9 +7839,11 @@
* been zapped so no dirty logging staff is needed for old slot. For
* KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the
* new and it's also covered when dealing with the new slot.
+ *
+ * FIXME: const-ify all uses of struct kvm_memory_slot.
*/
if (change != KVM_MR_DELETE)
- kvm_mmu_slot_apply_flags(kvm, new);
+ kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new);
}
void kvm_arch_flush_shadow_all(struct kvm *kvm)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f5fef18..01a1d01 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -4,6 +4,8 @@
#include <linux/kvm_host.h>
#include "kvm_cache_regs.h"
+#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL
+
static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
vcpu->arch.exception.pending = false;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ad45054..a8bcbc9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -230,6 +230,7 @@
int fpu_active;
int guest_fpu_loaded, guest_xcr0_loaded;
+ unsigned char fpu_counter;
wait_queue_head_t wq;
struct pid *pid;
int sigset_active;
@@ -500,21 +501,22 @@
};
int kvm_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region *mem);
int __kvm_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region *mem);
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned long npages);
-void kvm_arch_memslots_updated(struct kvm *kvm);
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change);
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change);
bool kvm_largepages_enabled(void);
void kvm_disable_largepages(void);
@@ -524,8 +526,8 @@
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot);
-int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
- int nr_pages);
+int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct page **pages, int nr_pages);
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
@@ -538,13 +540,13 @@
void kvm_set_page_accessed(struct page *page);
pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
-pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
- bool write_fault, bool *writable);
pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable);
pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
+pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
+ bool *async, bool write_fault, bool *writable);
void kvm_release_pfn_clean(pfn_t pfn);
void kvm_set_pfn_dirty(pfn_t pfn);
@@ -762,16 +764,10 @@
}
#endif
-static inline void kvm_guest_enter(void)
+/* must be called with irqs disabled */
+static inline void __kvm_guest_enter(void)
{
- unsigned long flags;
-
- BUG_ON(preemptible());
-
- local_irq_save(flags);
guest_enter();
- local_irq_restore(flags);
-
/* KVM does not hold any references to rcu protected data when it
* switches CPU into a guest mode. In fact switching to a guest mode
* is very similar to exiting to userspace from rcu point of view. In
@@ -783,12 +779,27 @@
rcu_virt_note_context_switch(smp_processor_id());
}
+/* must be called with irqs disabled */
+static inline void __kvm_guest_exit(void)
+{
+ guest_exit();
+}
+
+static inline void kvm_guest_enter(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __kvm_guest_enter();
+ local_irq_restore(flags);
+}
+
static inline void kvm_guest_exit(void)
{
unsigned long flags;
local_irq_save(flags);
- guest_exit();
+ __kvm_guest_exit();
local_irq_restore(flags);
}
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 931da7e..1b47a18 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -28,6 +28,7 @@
struct kvm_userspace_memory_region;
struct kvm_vcpu;
struct kvm_vcpu_init;
+struct kvm_memslots;
enum kvm_mr_change;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 4b60056..75bd9f7 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -814,6 +814,7 @@
#define KVM_CAP_S390_INJECT_IRQ 113
#define KVM_CAP_S390_IRQ_STATE 114
#define KVM_CAP_PPC_HWRNG 115
+#define KVM_CAP_DISABLE_QUIRKS 116
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9097741..6c8e124 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -103,8 +103,7 @@
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
static void kvm_release_pfn_dirty(pfn_t pfn);
-static void mark_page_dirty_in_slot(struct kvm *kvm,
- struct kvm_memory_slot *memslot, gfn_t gfn);
+static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
__visible bool kvm_rebooting;
EXPORT_SYMBOL_GPL(kvm_rebooting);
@@ -440,13 +439,60 @@
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
-static void kvm_init_memslots_id(struct kvm *kvm)
+static struct kvm_memslots *kvm_alloc_memslots(void)
{
int i;
- struct kvm_memslots *slots = kvm->memslots;
+ struct kvm_memslots *slots;
+ slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
+ if (!slots)
+ return NULL;
+
+ /*
+ * Init kvm generation close to the maximum to easily test the
+ * code of handling generation number wrap-around.
+ */
+ slots->generation = -150;
for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
slots->id_to_index[i] = slots->memslots[i].id = i;
+
+ return slots;
+}
+
+static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+ if (!memslot->dirty_bitmap)
+ return;
+
+ kvfree(memslot->dirty_bitmap);
+ memslot->dirty_bitmap = NULL;
+}
+
+/*
+ * Free any memory in @free but not in @dont.
+ */
+static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont)
+{
+ if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
+ kvm_destroy_dirty_bitmap(free);
+
+ kvm_arch_free_memslot(kvm, free, dont);
+
+ free->npages = 0;
+}
+
+static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
+{
+ struct kvm_memory_slot *memslot;
+
+ if (!slots)
+ return;
+
+ kvm_for_each_memslot(memslot, slots)
+ kvm_free_memslot(kvm, memslot, NULL);
+
+ kvfree(slots);
}
static struct kvm *kvm_create_vm(unsigned long type)
@@ -472,17 +518,10 @@
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
r = -ENOMEM;
- kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots));
+ kvm->memslots = kvm_alloc_memslots();
if (!kvm->memslots)
goto out_err_no_srcu;
- /*
- * Init kvm generation close to the maximum to easily test the
- * code of handling generation number wrap-around.
- */
- kvm->memslots->generation = -150;
-
- kvm_init_memslots_id(kvm);
if (init_srcu_struct(&kvm->srcu))
goto out_err_no_srcu;
if (init_srcu_struct(&kvm->irq_srcu))
@@ -523,7 +562,7 @@
out_err_no_disable:
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm->buses[i]);
- kvfree(kvm->memslots);
+ kvm_free_memslots(kvm, kvm->memslots);
kvm_arch_free_vm(kvm);
return ERR_PTR(r);
}
@@ -540,40 +579,6 @@
return kzalloc(size, GFP_KERNEL);
}
-static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
-{
- if (!memslot->dirty_bitmap)
- return;
-
- kvfree(memslot->dirty_bitmap);
- memslot->dirty_bitmap = NULL;
-}
-
-/*
- * Free any memory in @free but not in @dont.
- */
-static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free,
- struct kvm_memory_slot *dont)
-{
- if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
- kvm_destroy_dirty_bitmap(free);
-
- kvm_arch_free_memslot(kvm, free, dont);
-
- free->npages = 0;
-}
-
-static void kvm_free_physmem(struct kvm *kvm)
-{
- struct kvm_memslots *slots = kvm->memslots;
- struct kvm_memory_slot *memslot;
-
- kvm_for_each_memslot(memslot, slots)
- kvm_free_physmem_slot(kvm, memslot, NULL);
-
- kvfree(kvm->memslots);
-}
-
static void kvm_destroy_devices(struct kvm *kvm)
{
struct list_head *node, *tmp;
@@ -607,7 +612,7 @@
#endif
kvm_arch_destroy_vm(kvm);
kvm_destroy_devices(kvm);
- kvm_free_physmem(kvm);
+ kvm_free_memslots(kvm, kvm->memslots);
cleanup_srcu_struct(&kvm->irq_srcu);
cleanup_srcu_struct(&kvm->srcu);
kvm_arch_free_vm(kvm);
@@ -670,8 +675,6 @@
WARN_ON(mslots[i].id != id);
if (!new->npages) {
WARN_ON(!mslots[i].npages);
- new->base_gfn = 0;
- new->flags = 0;
if (mslots[i].npages)
slots->used_slots--;
} else {
@@ -711,7 +714,7 @@
slots->id_to_index[mslots[i].id] = i;
}
-static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
+static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
@@ -728,7 +731,7 @@
static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
struct kvm_memslots *slots)
{
- struct kvm_memslots *old_memslots = kvm->memslots;
+ struct kvm_memslots *old_memslots = kvm_memslots(kvm);
/*
* Set the low bit in the generation, which disables SPTE caching
@@ -747,7 +750,7 @@
*/
slots->generation++;
- kvm_arch_memslots_updated(kvm);
+ kvm_arch_memslots_updated(kvm, slots);
return old_memslots;
}
@@ -761,7 +764,7 @@
* Must be called holding kvm->slots_lock for write.
*/
int __kvm_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
int r;
gfn_t base_gfn;
@@ -793,16 +796,13 @@
if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
goto out;
- slot = id_to_memslot(kvm->memslots, mem->slot);
+ slot = id_to_memslot(kvm_memslots(kvm), mem->slot);
base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
npages = mem->memory_size >> PAGE_SHIFT;
if (npages > KVM_MEM_MAX_NR_PAGES)
goto out;
- if (!npages)
- mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
-
new = old = *slot;
new.id = mem->slot;
@@ -828,15 +828,19 @@
goto out;
}
}
- } else if (old.npages) {
+ } else {
+ if (!old.npages)
+ goto out;
+
change = KVM_MR_DELETE;
- } else /* Modify a non-existent slot: disallowed. */
- goto out;
+ new.base_gfn = 0;
+ new.flags = 0;
+ }
if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
/* Check for overlaps */
r = -EEXIST;
- kvm_for_each_memslot(slot, kvm->memslots) {
+ kvm_for_each_memslot(slot, kvm_memslots(kvm)) {
if ((slot->id >= KVM_USER_MEM_SLOTS) ||
(slot->id == mem->slot))
continue;
@@ -867,7 +871,7 @@
slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
if (!slots)
goto out_free;
- memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
+ memcpy(slots, kvm_memslots(kvm), sizeof(struct kvm_memslots));
if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
slot = id_to_memslot(slots, mem->slot);
@@ -898,7 +902,7 @@
if (r)
goto out_slots;
- /* actual memory is freed via old in kvm_free_physmem_slot below */
+ /* actual memory is freed via old in kvm_free_memslot below */
if (change == KVM_MR_DELETE) {
new.dirty_bitmap = NULL;
memset(&new.arch, 0, sizeof(new.arch));
@@ -907,9 +911,9 @@
update_memslots(slots, &new);
old_memslots = install_new_memslots(kvm, slots);
- kvm_arch_commit_memory_region(kvm, mem, &old, change);
+ kvm_arch_commit_memory_region(kvm, mem, &old, &new, change);
- kvm_free_physmem_slot(kvm, &old, &new);
+ kvm_free_memslot(kvm, &old, &new);
kvfree(old_memslots);
/*
@@ -931,14 +935,14 @@
out_slots:
kvfree(slots);
out_free:
- kvm_free_physmem_slot(kvm, &new, &old);
+ kvm_free_memslot(kvm, &new, &old);
out:
return r;
}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
int kvm_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
int r;
@@ -954,12 +958,14 @@
{
if (mem->slot >= KVM_USER_MEM_SLOTS)
return -EINVAL;
+
return kvm_set_memory_region(kvm, mem);
}
int kvm_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log, int *is_dirty)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int r, i;
unsigned long n;
@@ -969,7 +975,8 @@
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
@@ -1018,6 +1025,7 @@
int kvm_get_dirty_log_protect(struct kvm *kvm,
struct kvm_dirty_log *log, bool *is_dirty)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int r, i;
unsigned long n;
@@ -1028,7 +1036,8 @@
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
dirty_bitmap = memslot->dirty_bitmap;
r = -ENOENT;
@@ -1355,9 +1364,8 @@
return pfn;
}
-static pfn_t
-__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
- bool *async, bool write_fault, bool *writable)
+pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
+ bool *async, bool write_fault, bool *writable)
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
@@ -1376,44 +1384,13 @@
return hva_to_pfn(addr, atomic, async, write_fault,
writable);
}
-
-static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async,
- bool write_fault, bool *writable)
-{
- struct kvm_memory_slot *slot;
-
- if (async)
- *async = false;
-
- slot = gfn_to_memslot(kvm, gfn);
-
- return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault,
- writable);
-}
-
-pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
-{
- return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL);
-}
-EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
-
-pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
- bool write_fault, bool *writable)
-{
- return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable);
-}
-EXPORT_SYMBOL_GPL(gfn_to_pfn_async);
-
-pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
-{
- return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL);
-}
-EXPORT_SYMBOL_GPL(gfn_to_pfn);
+EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable)
{
- return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable);
+ return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
+ write_fault, writable);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
@@ -1421,6 +1398,7 @@
{
return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
{
@@ -1428,13 +1406,25 @@
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
-int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
- int nr_pages)
+pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
+
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn);
+
+int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct page **pages, int nr_pages)
{
unsigned long addr;
gfn_t entry;
- addr = gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, &entry);
+ addr = gfn_to_hva_many(slot, gfn, &entry);
if (kvm_is_error_hva(addr))
return -1;
@@ -1590,15 +1580,17 @@
int offset, int len)
{
int r;
+ struct kvm_memory_slot *memslot;
unsigned long addr;
- addr = gfn_to_hva(kvm, gfn);
+ memslot = gfn_to_memslot(kvm, gfn);
+ addr = gfn_to_hva_memslot(memslot, gfn);
if (kvm_is_error_hva(addr))
return -EFAULT;
r = __copy_to_user((void __user *)addr + offset, data, len);
if (r)
return -EFAULT;
- mark_page_dirty(kvm, gfn);
+ mark_page_dirty_in_slot(memslot, gfn);
return 0;
}
EXPORT_SYMBOL_GPL(kvm_write_guest_page);
@@ -1681,7 +1673,7 @@
r = __copy_to_user((void __user *)ghc->hva, data, len);
if (r)
return -EFAULT;
- mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT);
+ mark_page_dirty_in_slot(ghc->memslot, ghc->gpa >> PAGE_SHIFT);
return 0;
}
@@ -1739,8 +1731,7 @@
}
EXPORT_SYMBOL_GPL(kvm_clear_guest);
-static void mark_page_dirty_in_slot(struct kvm *kvm,
- struct kvm_memory_slot *memslot,
+static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
gfn_t gfn)
{
if (memslot && memslot->dirty_bitmap) {
@@ -1755,7 +1746,7 @@
struct kvm_memory_slot *memslot;
memslot = gfn_to_memslot(kvm, gfn);
- mark_page_dirty_in_slot(kvm, memslot, gfn);
+ mark_page_dirty_in_slot(memslot, gfn);
}
EXPORT_SYMBOL_GPL(mark_page_dirty);
@@ -2882,18 +2873,12 @@
static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
void *v)
{
- int cpu = (long)v;
-
val &= ~CPU_TASKS_FROZEN;
switch (val) {
case CPU_DYING:
- pr_info("kvm: disabling virtualization on CPU%d\n",
- cpu);
hardware_disable();
break;
case CPU_STARTING:
- pr_info("kvm: enabling virtualization on CPU%d\n",
- cpu);
hardware_enable();
break;
}