leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ARM:

Browse Source 
- Move the arch-specific code into arch/arm64/kvm
 - Start the post-32bit cleanup
 - Cherry-pick a few non-invasive pre-NV patches
 
 x86:
 - Rework of TLB flushing
 - Rework of event injection, especially with respect to nested virtualization
 - Nested AMD event injection facelift, building on the rework of generic code
 and fixing a lot of corner cases
 - Nested AMD live migration support
 - Optimization for TSC deadline MSR writes and IPIs
 - Various cleanups
 - Asynchronous page fault cleanups (from tglx, common topic branch with tip tree)
 - Interrupt-based delivery of asynchronous "page ready" events (host side)
 - Hyper-V MSRs and hypercalls for guest debugging
 - VMX preemption timer fixes
 
 s390:
 - Cleanups
 
 Generic:
 - switch vCPU thread wakeup from swait to rcuwait
 
 The other architectures, and the guest side of the asynchronous page fault
 work, will come next week.
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAl7VJcYUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroPf6QgAq4wU5wdd1lTGz/i3DIhNVJNJgJlp
 ozLzRdMaJbdbn5RpAK6PEBd9+pt3+UlojpFB3gpJh2Nazv2OzV4yLQgXXXyyMEx1
 5Hg7b4UCJYDrbkCiegNRv7f/4FWDkQ9dx++RZITIbxeskBBCEI+I7GnmZhGWzuC4
 7kj4ytuKAySF2OEJu0VQF6u0CvrNYfYbQIRKBXjtOwuRK4Q6L63FGMJpYo159MBQ
 asg3B1jB5TcuGZ9zrjL5LkuzaP4qZZHIRs+4kZsH9I6MODHGUxKonrkablfKxyKy
 CFK+iaHCuEXXty5K0VmWM3nrTfvpEjVjbMc7e1QGBQ5oXsDM0pqn84syRg==
 =v7Wn
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Move the arch-specific code into arch/arm64/kvm

   - Start the post-32bit cleanup

   - Cherry-pick a few non-invasive pre-NV patches

  x86:
   - Rework of TLB flushing

   - Rework of event injection, especially with respect to nested
     virtualization

   - Nested AMD event injection facelift, building on the rework of
     generic code and fixing a lot of corner cases

   - Nested AMD live migration support

   - Optimization for TSC deadline MSR writes and IPIs

   - Various cleanups

   - Asynchronous page fault cleanups (from tglx, common topic branch
     with tip tree)

   - Interrupt-based delivery of asynchronous "page ready" events (host
     side)

   - Hyper-V MSRs and hypercalls for guest debugging

   - VMX preemption timer fixes

  s390:
   - Cleanups

  Generic:
   - switch vCPU thread wakeup from swait to rcuwait

  The other architectures, and the guest side of the asynchronous page
  fault work, will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
  KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
  KVM: check userspace_addr for all memslots
  KVM: selftests: update hyperv_cpuid with SynDBG tests
  x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
  x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
  x86/kvm/hyper-v: Add support for synthetic debugger interface
  x86/hyper-v: Add synthetic debugger definitions
  KVM: selftests: VMX preemption timer migration test
  KVM: nVMX: Fix VMX preemption timer migration
  x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
  KVM: x86/pmu: Support full width counting
  KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
  KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
  KVM: x86: acknowledgment mechanism for async pf page ready notifications
  KVM: x86: interrupt based APF 'page ready' event delivery
  KVM: introduce kvm_read_guest_offset_cached()
  KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
  KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
  Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
  KVM: VMX: Replace zero-length array with flexible-array
  ...
This commit is contained in:
Linus Torvalds 2020-06-03 15:13:47 -07:00
commit 039aeb9deb
155 changed files with 5318 additions and 3057 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
Documentation/virt/kvm/api.rst
View File

@ -4336,9 +4336,13 @@ Errors:
#define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002
#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
struct kvm_vmx_nested_state_hdr {
__u32 flags;
__u64 vmxon_pa;
__u64 vmcs12_pa;
__u64 preemption_timer_deadline;
struct {
__u16 flags;
@ -5068,10 +5072,13 @@ EOI was received.
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
#define KVM_EXIT_HYPERV_SYNDBG 3
__u32 type;
__u32 pad1;
union {
struct {
__u32 msr;
__u32 pad2;
__u64 control;
__u64 evt_page;
__u64 msg_page;
@ -5081,6 +5088,15 @@ EOI was received.
__u64 result;
__u64 params[2];
} hcall;
struct {
__u32 msr;
__u32 pad2;
__u64 control;
__u64 status;
__u64 send_page;
__u64 recv_page;
__u64 pending_page;
} syndbg;
} u;
};
/* KVM_EXIT_HYPERV */
@ -5097,6 +5113,12 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
event/message pages and to enable/disable SynIC messages/events processing
in userspace.
- KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about
Hyper-V Synthetic debugger state change. Notification is used to either update
the pending_page location or to send a control command (send the buffer located
in send_page or recv a buffer to recv_page).
::
/* KVM_EXIT_ARM_NISV */
@ -5779,7 +5801,7 @@ will be initialized to 1 when created. This also improves performance because
dirty logging can be enabled gradually in small chunks on the first call
to KVM_CLEAR_DIRTY_LOG. KVM_DIRTY_LOG_INITIALLY_SET depends on
KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on
x86 for now).
x86 and arm64 for now).
KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name
KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make
@ -5804,6 +5826,23 @@ If present, this capability can be enabled for a VM, meaning that KVM
will allow the transition to secure guest mode. Otherwise KVM will
veto the transition.
7.20 KVM_CAP_HALT_POLL
----------------------
:Architectures: all
:Target: VM
:Parameters: args[0] is the maximum poll time in nanoseconds
:Returns: 0 on success; -1 on error
This capability overrides the kvm module parameter halt_poll_ns for the
target VM.
VCPU polling allows a VCPU to poll for wakeup events instead of immediately
scheduling during guest halts. The maximum time a VCPU can spend polling is
controlled by the kvm module parameter halt_poll_ns. This capability allows
the maximum halt time to specified on a per-VM basis, effectively overriding
the module parameter for the target VM.
8. Other capabilities.
======================

8
Documentation/virt/kvm/cpuid.rst
View File

@ -50,8 +50,8 @@ KVM_FEATURE_NOP_IO_DELAY 1 not necessary to perform delays
KVM_FEATURE_MMU_OP 2 deprecated
KVM_FEATURE_CLOCKSOURCE2 3 kvmclock available at msrs
0x4b564d00 and 0x4b564d01
KVM_FEATURE_ASYNC_PF 4 async pf can be enabled by
writing to msr 0x4b564d02
@ -86,6 +86,12 @@ KVM_FEATURE_PV_SCHED_YIELD 13 guest checks this feature bit
before using paravirtualized
sched yield.
KVM_FEATURE_ASYNC_PF_INT 14 guest checks this feature bit
before using the second async
pf control msr 0x4b564d06 and
async pf acknowledgment msr
0x4b564d07.
KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24 host will warn if no guest-side
per-cpu warps are expeced in
kvmclock

115
Documentation/virt/kvm/msr.rst
View File

@ -190,41 +190,72 @@ MSR_KVM_ASYNC_PF_EN:
0x4b564d02
data:
Bits 63-6 hold 64-byte aligned physical address of a
64 byte memory area which must be in guest RAM and must be
zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
when asynchronous page faults are enabled on the vcpu 0 when
disabled. Bit 1 is 1 if asynchronous page faults can be injected
when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
are delivered to L1 as #PF vmexits. Bit 2 can be set only if
KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID.
Asynchronous page fault (APF) control MSR.
First 4 byte of 64 byte memory location will be written to by
the hypervisor at the time of asynchronous page fault (APF)
injection to indicate type of asynchronous page fault. Value
of 1 means that the page referred to by the page fault is not
present. Value 2 means that the page is now available. Disabling
interrupt inhibits APFs. Guest must not enable interrupt
before the reason is read, or it may be overwritten by another
APF. Since APF uses the same exception vector as regular page
fault guest must reset the reason to 0 before it does
something that can generate normal page fault. If during page
fault APF reason is 0 it means that this is regular page
fault.
Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area
which must be in guest RAM and must be zeroed. This memory is expected
to hold a copy of the following structure::
During delivery of type 1 APF cr2 contains a token that will
be used to notify a guest when missing page becomes
available. When page becomes available type 2 APF is sent with
cr2 set to the token associated with the page. There is special
kind of token 0xffffffff which tells vcpu that it should wake
up all processes waiting for APFs and no individual type 2 APFs
will be sent.
struct kvm_vcpu_pv_apf_data {
/* Used for 'page not present' events delivered via #PF */
__u32 flags;
/* Used for 'page ready' events delivered via interrupt notification */
__u32 token;
__u8 pad[56];
__u32 enabled;
};
Bits 5-4 of the MSR are reserved and should be zero. Bit 0 is set to 1
when asynchronous page faults are enabled on the vcpu, 0 when disabled.
Bit 1 is 1 if asynchronous page faults can be injected when vcpu is in
cpl == 0. Bit 2 is 1 if asynchronous page faults are delivered to L1 as
#PF vmexits. Bit 2 can be set only if KVM_FEATURE_ASYNC_PF_VMEXIT is
present in CPUID. Bit 3 enables interrupt based delivery of 'page ready'
events. Bit 3 can only be set if KVM_FEATURE_ASYNC_PF_INT is present in
CPUID.
'Page not present' events are currently always delivered as synthetic
#PF exception. During delivery of these events APF CR2 register contains
a token that will be used to notify the guest when missing page becomes
available. Also, to make it possible to distinguish between real #PF and
APF, first 4 bytes of 64 byte memory location ('flags') will be written
to by the hypervisor at the time of injection. Only first bit of 'flags'
is currently supported, when set, it indicates that the guest is dealing
with asynchronous 'page not present' event. If during a page fault APF
'flags' is '0' it means that this is regular page fault. Guest is
supposed to clear 'flags' when it is done handling #PF exception so the
next event can be delivered.
Note, since APF 'page not present' events use the same exception vector
as regular page fault, guest must reset 'flags' to '0' before it does
something that can generate normal page fault.
Bytes 5-7 of 64 byte memory location ('token') will be written to by the
hypervisor at the time of APF 'page ready' event injection. The content
of these bytes is a token which was previously delivered as 'page not
present' event. The event indicates the page in now available. Guest is
supposed to write '0' to 'token' when it is done handling 'page ready'
event and to write 1' to MSR_KVM_ASYNC_PF_ACK after clearing the location;
writing to the MSR forces KVM to re-scan its queue and deliver the next
pending notification.
Note, MSR_KVM_ASYNC_PF_INT MSR specifying the interrupt vector for 'page
ready' APF delivery needs to be written to before enabling APF mechanism
in MSR_KVM_ASYNC_PF_EN or interrupt #0 can get injected. The MSR is
available if KVM_FEATURE_ASYNC_PF_INT is present in CPUID.
Note, previously, 'page ready' events were delivered via the same #PF
exception as 'page not present' events but this is now deprecated. If
bit 3 (interrupt based delivery) is not set APF events are not delivered.
If APF is disabled while there are outstanding APFs, they will
not be delivered.
Currently type 2 APF will be always delivered on the same vcpu as
type 1 was, but guest should not rely on that.
Currently 'page ready' APF events will be always delivered on the
same vcpu as 'page not present' event was, but guest should not rely on
that.
MSR_KVM_STEAL_TIME:
0x4b564d03
@ -319,3 +350,29 @@ data:
KVM guests can request the host not to poll on HLT, for example if
they are performing polling themselves.
MSR_KVM_ASYNC_PF_INT:
0x4b564d06
data:
Second asynchronous page fault (APF) control MSR.
Bits 0-7: APIC vector for delivery of 'page ready' APF events.
Bits 8-63: Reserved
Interrupt vector for asynchnonous 'page ready' notifications delivery.
The vector has to be set up before asynchronous page fault mechanism
is enabled in MSR_KVM_ASYNC_PF_EN. The MSR is only available if
KVM_FEATURE_ASYNC_PF_INT is present in CPUID.
MSR_KVM_ASYNC_PF_ACK:
0x4b564d07
data:
Asynchronous page fault (APF) acknowledgment.
When the guest is done processing 'page ready' APF event and 'token'
field in 'struct kvm_vcpu_pv_apf_data' is cleared it is supposed to
write '1' to bit 0 of the MSR, this causes the host to re-scan its queue
and check if there are more notifications pending. The MSR is available
if KVM_FEATURE_ASYNC_PF_INT is present in CPUID.

5
Documentation/virt/kvm/nested-vmx.rst
View File

@ -116,10 +116,7 @@ struct shadow_vmcs is ever changed.
natural_width cr4_guest_host_mask;
natural_width cr0_read_shadow;
natural_width cr4_read_shadow;
natural_width cr3_target_value0;
natural_width cr3_target_value1;
natural_width cr3_target_value2;
natural_width cr3_target_value3;
natural_width dead_space[4]; /* Last remnants of cr3_target_value[0-3]. */
natural_width exit_qualification;
natural_width guest_linear_address;
natural_width guest_cr0;

1
MAINTAINERS
View File

@ -9368,7 +9368,6 @@ F: arch/arm64/include/asm/kvm*
F: arch/arm64/include/uapi/asm/kvm*
F: arch/arm64/kvm/
F: include/kvm/arm_*
F: virt/kvm/arm/
KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
L: linux-mips@vger.kernel.org

4
arch/arm64/include/asm/kvm_asm.h
View File

@ -64,12 +64,14 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
extern void __kvm_timer_set_cntvoff(u64 cntvoff);
extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
extern void __kvm_enable_ssbs(void);
extern u64 __vgic_v3_get_ich_vtr_el2(void);
extern u64 __vgic_v3_read_vmcr(void);
extern void __vgic_v3_write_vmcr(u32 vmcr);

46
arch/arm64/include/asm/kvm_host.h
View File

@ -46,6 +46,9 @@
#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3)
#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4)
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
extern unsigned int kvm_sve_max_vl;
@ -112,12 +115,8 @@ struct kvm_vcpu_fault_info {
u64 disr_el1; /* Deferred [SError] Status Register */
};
/*
* 0 is reserved as an invalid value.
* Order should be kept in sync with the save/restore code.
*/
enum vcpu_sysreg {
__INVALID_SYSREG__,
__INVALID_SYSREG__, /* 0 is reserved as an invalid value */
MPIDR_EL1, /* MultiProcessor Affinity Register */
CSSELR_EL1, /* Cache Size Selection Register */
SCTLR_EL1, /* System Control Register */
@ -415,6 +414,8 @@ struct kvm_vm_stat {
struct kvm_vcpu_stat {
u64 halt_successful_poll;
u64 halt_attempted_poll;
u64 halt_poll_success_ns;
u64 halt_poll_fail_ns;
u64 halt_poll_invalid;
u64 halt_wakeup;
u64 hvc_exit_stat;
@ -530,39 +531,6 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
}
void __kvm_enable_ssbs(void);
static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
unsigned long hyp_stack_ptr,
unsigned long vector_ptr)
{
/*
* Calculate the raw per-cpu offset without a translation from the
* kernel's mapping to the linear mapping, and store it in tpidr_el2
* so that we can use adr_l to access per-cpu variables in EL2.
*/
u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_data) -
(u64)kvm_ksym_ref(kvm_host_data));
/*
* Call initialization code, and switch to the full blown HYP code.
* If the cpucaps haven't been finalized yet, something has gone very
* wrong, and hyp will crash and burn when it uses any
* cpus_have_const_cap() wrapper.
*/
BUG_ON(!system_capabilities_finalized());
__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
/*
* Disabling SSBD on a non-VHE system requires us to enable SSBS
* at EL2.
*/
if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) &&
arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
kvm_call_hyp(__kvm_enable_ssbs);
}
}
static inline bool kvm_arch_requires_vhe(void)
{
/*
@ -594,8 +562,6 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
static inline void __cpu_init_stage2(void) {}
/* Guest/host FPSIMD coordination helpers */
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);

12
arch/arm64/include/asm/kvm_hyp.h
View File

@ -55,12 +55,12 @@
int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu);
void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu);
void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu);
void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu);
void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if);
void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if);
void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if);
void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if);
void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
void __timer_enable_traps(struct kvm_vcpu *vcpu);

4
arch/arm64/include/asm/kvm_mmu.h
View File

@ -363,8 +363,6 @@ static inline void __kvm_flush_dcache_pud(pud_t pud)
}
}
#define kvm_virt_to_phys(x) __pa_symbol(x)
void kvm_set_way_flush(struct kvm_vcpu *vcpu);
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
@ -473,7 +471,7 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
extern void *__kvm_bp_vect_base;
extern int __kvm_harden_el2_vector_slot;
/* This is only called on a VHE system */
/* This is called on both VHE and !VHE systems */
static inline void *kvm_get_hyp_vector(void)
{
struct bp_hardening_data *data = arm64_get_bp_hardening_data();

2
arch/arm64/include/asm/ptrace.h
View File

@ -35,7 +35,7 @@
#define GIC_PRIO_PSR_I_SET (1 << 4)
/* Additional SPSR bits not exposed in the UABI */
#define PSR_MODE_THREAD_BIT (1 << 0)
#define PSR_IL_BIT (1 << 20)
/* AArch32-specific ptrace requests */

2
arch/arm64/include/asm/virt.h
View File

@ -85,7 +85,7 @@ static inline bool is_kernel_in_hyp_mode(void)
static __always_inline bool has_vhe(void)
{
if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN))
if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN))
return true;
return false;

2
arch/arm64/kernel/asm-offsets.c
View File

@ -97,7 +97,7 @@ int main(void)
DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack));
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
BLANK();
#ifdef CONFIG_KVM_ARM_HOST
#ifdef CONFIG_KVM
DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt));
DEFINE(VCPU_FAULT_DISR, offsetof(struct kvm_vcpu, arch.fault.disr_el1));
DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags));

2
arch/arm64/kernel/cpu_errata.c
View File

@ -234,7 +234,7 @@ static int detect_harden_bp_fw(void)
smccc_end = NULL;
break;
#if IS_ENABLED(CONFIG_KVM_ARM_HOST)
#if IS_ENABLED(CONFIG_KVM)
case SMCCC_CONDUIT_SMC:
cb = call_smc_arch_workaround_1;
smccc_start = __smccc_workaround_1_smc;

2
arch/arm64/kernel/smp.c
View File

@ -422,7 +422,7 @@ static void __init hyp_mode_check(void)
"CPU: CPUs started in inconsistent modes");
else
pr_info("CPU: All CPU(s) started at EL1\n");
if (IS_ENABLED(CONFIG_KVM_ARM_HOST))
if (IS_ENABLED(CONFIG_KVM))
kvm_compute_layout();
}

22
arch/arm64/kvm/Kconfig
View File

@ -3,7 +3,6 @@
# KVM configuration
#
source "virt/kvm/Kconfig"
source "virt/lib/Kconfig"
menuconfig VIRTUALIZATION
@ -18,7 +17,7 @@ menuconfig VIRTUALIZATION
if VIRTUALIZATION
config KVM
menuconfig KVM
bool "Kernel-based Virtual Machine (KVM) support"
depends on OF
# for TASKSTATS/TASK_DELAY_ACCT:
@ -28,13 +27,11 @@ config KVM
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
select KVM_MMIO
select KVM_ARM_HOST
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select SRCU
select KVM_VFIO
select HAVE_KVM_EVENTFD
select HAVE_KVM_IRQFD
select KVM_ARM_PMU if HW_PERF_EVENTS
select HAVE_KVM_MSI
select HAVE_KVM_IRQCHIP
select HAVE_KVM_IRQ_ROUTING
@ -45,23 +42,24 @@ config KVM
select TASK_DELAY_ACCT
---help---
Support hosting virtualized guest machines.
We don't support KVM with 16K page tables yet, due to the multiple
levels of fake page tables.
If unsure, say N.
config KVM_ARM_HOST
bool
---help---
Provides host support for ARM processors.
if KVM
source "virt/kvm/Kconfig"
config KVM_ARM_PMU
bool
bool "Virtual Performance Monitoring Unit (PMU) support"
depends on HW_PERF_EVENTS
default y
---help---
Adds support for a virtual Performance Monitoring Unit (PMU) in
virtual machines.
config KVM_INDIRECT_VECTORS
def_bool KVM && (HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS)
def_bool HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS
endif # KVM
endif # VIRTUALIZATION

46
arch/arm64/kvm/Makefile
View File

@ -3,37 +3,25 @@
# Makefile for Kernel-based Virtual Machine module
#
ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic
ccflags-y += -I $(srctree)/$(src)
KVM=../../../virt/kvm
obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp/
obj-$(CONFIG_KVM) += kvm.o
obj-$(CONFIG_KVM) += hyp/
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o
kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
$(KVM)/vfio.o $(KVM)/irqchip.o \
arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
vgic-sys-reg-v3.o fpsimd.o pmu.o \
aarch32.o arch_timer.o \
vgic/vgic.o vgic/vgic-init.o \
vgic/vgic-irqfd.o vgic/vgic-v2.o \
vgic/vgic-v3.o vgic/vgic-v4.o \
vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \
vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
vgic/vgic-its.o vgic/vgic-debug.o
kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o
kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o fpsimd.o pmu.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v3.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v4.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-debug.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/irqchip.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
kvm-$(CONFIG_KVM_ARM_PMU) += pmu-emul.o

0
virt/kvm/arm/aarch32.c → arch/arm64/kvm/aarch32.c
View File

15
virt/kvm/arm/arch_timer.c → arch/arm64/kvm/arch_timer.c
View File

@ -451,17 +451,7 @@ out:
static void set_cntvoff(u64 cntvoff)
{
u32 low = lower_32_bits(cntvoff);
u32 high = upper_32_bits(cntvoff);
/*
* Since kvm_call_hyp doesn't fully support the ARM PCS especially on
* 32-bit systems, but rather passes register by register shifted one
* place (we put the function address in r0/x0), we cannot simply pass
* a 64-bit value as an argument, but have to split the value in two
* 32-bit halves.
*/
kvm_call_hyp(__kvm_timer_set_cntvoff, low, high);
kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff);
}
static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active)
@ -571,6 +561,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
struct timer_map map;
struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
if (unlikely(!timer->enabled))
return;
@ -593,7 +584,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
if (map.emul_ptimer)
soft_timer_cancel(&map.emul_ptimer->hrtimer);
if (swait_active(kvm_arch_vcpu_wq(vcpu)))
if (rcuwait_active(wait))
kvm_timer_blocking(vcpu);
/*

75
virt/kvm/arm/arm.c → arch/arm64/kvm/arm.c
View File

@ -22,7 +22,7 @@
#include <trace/events/kvm.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
#include "trace_arm.h"
#include <linux/uaccess.h>
#include <asm/ptrace.h>
@ -95,6 +95,11 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
return r;
}
static int kvm_arm_default_max_vcpus(void)
{
return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
}
/**
* kvm_arch_init_vm - initializes a VM data structure
* @kvm: pointer to the KVM struct
@ -128,8 +133,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.vmid.vmid_gen = 0;
/* The maximum number of VCPUs is limited by the host's GIC model */
kvm->arch.max_vcpus = vgic_present ?
kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
return ret;
out_free_stage2_pgd:
@ -204,10 +208,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = num_online_cpus();
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
case KVM_CAP_MAX_VCPU_ID:
r = KVM_MAX_VCPU_ID;
if (kvm)
r = kvm->arch.max_vcpus;
else
r = kvm_arm_default_max_vcpus();
break;
case KVM_CAP_MSI_DEVID:
if (!kvm)
@ -455,9 +460,9 @@ void force_vm_exit(const cpumask_t *mask)
*
* The hardware supports a limited set of values with the value zero reserved
* for the host, so we check if an assigned value belongs to a previous
* generation, which which requires us to assign a new value. If we're the
* first to use a VMID for the new generation, we must flush necessary caches
* and TLBs on all CPUs.
* generation, which requires us to assign a new value. If we're the first to
* use a VMID for the new generation, we must flush necessary caches and TLBs
* on all CPUs.
*/
static bool need_new_vmid_gen(struct kvm_vmid *vmid)
{
@ -579,16 +584,17 @@ void kvm_arm_resume_guest(struct kvm *kvm)
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.pause = false;
swake_up_one(kvm_arch_vcpu_wq(vcpu));
rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu));
}
}
static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
{
struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
(!vcpu->arch.pause)));
rcuwait_wait_event(wait,
(!vcpu->arch.power_off) &&(!vcpu->arch.pause),
TASK_INTERRUPTIBLE);
if (vcpu->arch.power_off || vcpu->arch.pause) {
/* Awaken to handle a signal, request we sleep again later. */
@ -639,7 +645,6 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
/**
* kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
* @vcpu: The VCPU pointer
* @run: The kvm_run structure pointer used for userspace state exchange
*
* This function is called through the VCPU_RUN ioctl called from user space. It
* will execute VM code in a loop until the time slice for the process is used
@ -647,8 +652,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
* return with return value 0 and with the kvm_run structure filled in with the
* required data for the requested emulation.
*/
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
int ret;
if (unlikely(!kvm_vcpu_initialized(vcpu)))
@ -659,7 +665,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
return ret;
if (run->exit_reason == KVM_EXIT_MMIO) {
ret = kvm_handle_mmio_return(vcpu, vcpu->run);
ret = kvm_handle_mmio_return(vcpu, run);
if (ret)
return ret;
}
@ -983,8 +989,11 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
/*
* Ensure a rebooted VM will fault in RAM pages and detect if the
* guest MMU is turned off and flush the caches as needed.
*
* S2FWB enforces all memory accesses to RAM being cacheable, we
* ensure that the cache is always coherent.
*/
if (vcpu->arch.has_run_once)
if (vcpu->arch.has_run_once && !cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
stage2_unmap_vm(vcpu->kvm);
vcpu_reset_hcr(vcpu);
@ -1265,19 +1274,41 @@ static void cpu_init_hyp_mode(void)
{
phys_addr_t pgd_ptr;
unsigned long hyp_stack_ptr;
unsigned long stack_page;
unsigned long vector_ptr;
unsigned long tpidr_el2;
/* Switch from the HYP stub to our own HYP init vector */
__hyp_set_vectors(kvm_get_idmap_vector());
/*
* Calculate the raw per-cpu offset without a translation from the
* kernel's mapping to the linear mapping, and store it in tpidr_el2
* so that we can use adr_l to access per-cpu variables in EL2.
*/
tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) -
(unsigned long)kvm_ksym_ref(kvm_host_data));
pgd_ptr = kvm_mmu_get_httbr();
stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
hyp_stack_ptr = stack_page + PAGE_SIZE;
hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
vector_ptr = (unsigned long)kvm_get_hyp_vector();
__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
__cpu_init_stage2();
/*
* Call initialization code, and switch to the full blown HYP code.
* If the cpucaps haven't been finalized yet, something has gone very
* wrong, and hyp will crash and burn when it uses any
* cpus_have_const_cap() wrapper.
*/
BUG_ON(!system_capabilities_finalized());
__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
/*
* Disabling SSBD on a non-VHE system requires us to enable SSBS
* at EL2.
*/
if (this_cpu_has_cap(ARM64_SSBS) &&
arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
kvm_call_hyp(__kvm_enable_ssbs);
}
}
static void cpu_hyp_reset(void)

29
arch/arm64/kvm/guest.c
View File

@ -29,20 +29,19 @@
#include "trace.h"
#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM }
#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
struct kvm_stats_debugfs_item debugfs_entries[] = {
VCPU_STAT(halt_successful_poll),
VCPU_STAT(halt_attempted_poll),
VCPU_STAT(halt_poll_invalid),
VCPU_STAT(halt_wakeup),
VCPU_STAT(hvc_exit_stat),
VCPU_STAT(wfe_exit_stat),
VCPU_STAT(wfi_exit_stat),
VCPU_STAT(mmio_exit_user),
VCPU_STAT(mmio_exit_kernel),
VCPU_STAT(exits),
VCPU_STAT("halt_successful_poll", halt_successful_poll),
VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
VCPU_STAT("halt_wakeup", halt_wakeup),
VCPU_STAT("hvc_exit_stat", hvc_exit_stat),
VCPU_STAT("wfe_exit_stat", wfe_exit_stat),
VCPU_STAT("wfi_exit_stat", wfi_exit_stat),
VCPU_STAT("mmio_exit_user", mmio_exit_user),
VCPU_STAT("mmio_exit_kernel", mmio_exit_kernel),
VCPU_STAT("exits", exits),
VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
{ NULL }
};
@ -267,7 +266,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
/*
* Vector lengths supported by the host can't currently be
* hidden from the guest individually: instead we can only set a
* maxmium via ZCR_EL2.LEN. So, make sure the available vector
* maximum via ZCR_EL2.LEN. So, make sure the available vector
* lengths match the set requested exactly up to the requested
* maximum:
*/
@ -337,7 +336,7 @@ static int sve_reg_to_region(struct sve_state_reg_region *region,
unsigned int reg_num;
unsigned int reqoffset, reqlen; /* User-requested offset and length */
unsigned int maxlen; /* Maxmimum permitted length */
unsigned int maxlen; /* Maximum permitted length */
size_t sve_state_size;

2
arch/arm64/kvm/handle_exit.c
View File

@ -23,7 +23,7 @@
#include <kvm/arm_hypercalls.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
#include "trace_handle_exit.h"
typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);

16
arch/arm64/kvm/hyp/Makefile
View File

@ -6,20 +6,10 @@
ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
$(DISABLE_STACKLEAK_PLUGIN)
KVM=../../../../virt/kvm
obj-$(CONFIG_KVM) += hyp.o
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o
obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-cpuif-proxy.o
obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += entry.o
obj-$(CONFIG_KVM_ARM_HOST) += switch.o
obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o
obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
# KVM code is run at a different exception code with a different map, so
# compiler instrumentation that inserts callbacks or checks into the code may

0
virt/kvm/arm/hyp/aarch32.c → arch/arm64/kvm/hyp/aarch32.c
View File

8
arch/arm64/kvm/hyp/switch.c
View File

@ -270,8 +270,8 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
{
if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
__vgic_v3_save_state(vcpu);
__vgic_v3_deactivate_traps(vcpu);
__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
}
}
@ -279,8 +279,8 @@ static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
{
if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
__vgic_v3_activate_traps(vcpu);
__vgic_v3_restore_state(vcpu);
__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
}
}

3
virt/kvm/arm/hyp/timer-sr.c → arch/arm64/kvm/hyp/timer-sr.c
View File

@ -10,9 +10,8 @@
#include <asm/kvm_hyp.h>
void __hyp_text __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high)
void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
{
u64 cntvoff = (u64)cntvoff_high << 32 | cntvoff_low;
write_sysreg(cntvoff, cntvoff_el2);
}

39
virt/kvm/arm/hyp/vgic-v3-sr.c → arch/arm64/kvm/hyp/vgic-v3-sr.c
View File

@ -194,10 +194,9 @@ static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
return val;
}
void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
u64 used_lrs = cpu_if->used_lrs;
/*
* Make sure stores to the GIC via the memory mapped interface
@ -230,10 +229,9 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
}
}
void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
u64 used_lrs = cpu_if->used_lrs;
int i;
if (used_lrs || cpu_if->its_vpe.its_vm) {
@ -257,10 +255,8 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
}
}
void __hyp_text __vgic_v3_activate_traps(struct kvm_vcpu *vcpu)
void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
/*
* VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
* Group0 interrupt (as generated in GICv2 mode) to be
@ -306,9 +302,8 @@ void __hyp_text __vgic_v3_activate_traps(struct kvm_vcpu *vcpu)
write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
}
void __hyp_text __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu)
void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
u64 val;
if (!cpu_if->vgic_sre) {
@ -333,15 +328,11 @@ void __hyp_text __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu)
write_gicreg(0, ICH_HCR_EL2);
}
void __hyp_text __vgic_v3_save_aprs(struct kvm_vcpu *vcpu)
void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
{
struct vgic_v3_cpu_if *cpu_if;
u64 val;
u32 nr_pre_bits;
vcpu = kern_hyp_va(vcpu);
cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
val = read_gicreg(ICH_VTR_EL2);
nr_pre_bits = vtr_to_nr_pre_bits(val);
@ -370,15 +361,11 @@ void __hyp_text __vgic_v3_save_aprs(struct kvm_vcpu *vcpu)
}
}
void __hyp_text __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu)
void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
{
struct vgic_v3_cpu_if *cpu_if;
u64 val;
u32 nr_pre_bits;
vcpu = kern_hyp_va(vcpu);
cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
val = read_gicreg(ICH_VTR_EL2);
nr_pre_bits = vtr_to_nr_pre_bits(val);
@ -431,8 +418,6 @@ void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
write_gicreg(vmcr, ICH_VMCR_EL2);
}
#ifdef CONFIG_ARM64
static int __hyp_text __vgic_v3_bpr_min(void)
{
/* See Pseudocode for VPriorityGroup */
@ -453,7 +438,7 @@ static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
u32 vmcr,
u64 *lr_val)
{
unsigned int used_lrs = vcpu->arch.vgic_cpu.used_lrs;
unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
u8 priority = GICv3_IDLE_PRIORITY;
int i, lr = -1;
@ -492,7 +477,7 @@ static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
int intid, u64 *lr_val)
{
unsigned int used_lrs = vcpu->arch.vgic_cpu.used_lrs;
unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
int i;
for (i = 0; i < used_lrs; i++) {
@ -579,7 +564,7 @@ static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
/*
* The priority value is independent of any of the BPR values, so we
* normalize it using the minumal BPR value. This guarantees that no
* normalize it using the minimal BPR value. This guarantees that no
* matter what the guest does with its BPR, we can always set/get the
* same value of a priority.
*/
@ -1126,5 +1111,3 @@ int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
return 1;
}
#endif

0
virt/kvm/arm/hypercalls.c → arch/arm64/kvm/hypercalls.c
View File

75
arch/arm64/kvm/inject_fault.c
View File

@ -26,28 +26,12 @@ enum exception_type {
except_type_serror = 0x180,
};
static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
{
u64 exc_offset;
switch (*vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT)) {
case PSR_MODE_EL1t:
exc_offset = CURRENT_EL_SP_EL0_VECTOR;
break;
case PSR_MODE_EL1h:
exc_offset = CURRENT_EL_SP_ELx_VECTOR;
break;
case PSR_MODE_EL0t:
exc_offset = LOWER_EL_AArch64_VECTOR;
break;
default:
exc_offset = LOWER_EL_AArch32_VECTOR;
}
return vcpu_read_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
}
/*
* This performs the exception entry at a given EL (@target_mode), stashing PC
* and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE.
* The EL passed to this function *must* be a non-secure, privileged mode with
* bit 0 being set (PSTATE.SP == 1).
*
* When an exception is taken, most PSTATE fields are left unchanged in the
* handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
* of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
@ -59,10 +43,35 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
* Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
* MSB to LSB.
*/
static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu)
static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
enum exception_type type)
{
unsigned long sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
unsigned long old, new;
unsigned long sctlr, vbar, old, new, mode;
u64 exc_offset;
mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
if (mode == target_mode)
exc_offset = CURRENT_EL_SP_ELx_VECTOR;
else if ((mode | PSR_MODE_THREAD_BIT) == target_mode)
exc_offset = CURRENT_EL_SP_EL0_VECTOR;
else if (!(mode & PSR_MODE32_BIT))
exc_offset = LOWER_EL_AArch64_VECTOR;
else
exc_offset = LOWER_EL_AArch32_VECTOR;
switch (target_mode) {
case PSR_MODE_EL1h:
vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1);
sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
break;
default:
/* Don't do that */
BUG();
}
*vcpu_pc(vcpu) = vbar + exc_offset + type;
old = *vcpu_cpsr(vcpu);
new = 0;
@ -105,9 +114,10 @@ static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu)
new |= PSR_I_BIT;
new |= PSR_F_BIT;
new |= PSR_MODE_EL1h;
new |= target_mode;
return new;
*vcpu_cpsr(vcpu) = new;
vcpu_write_spsr(vcpu, old);
}
static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
@ -116,11 +126,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
u32 esr = 0;
vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
vcpu_write_spsr(vcpu, cpsr);
enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
@ -148,14 +154,9 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
static void inject_undef64(struct kvm_vcpu *vcpu)
{
unsigned long cpsr = *vcpu_cpsr(vcpu);
u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
vcpu_write_spsr(vcpu, cpsr);
enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
/*
* Build an unknown exception, depending on the instruction

2
virt/kvm/arm/mmio.c → arch/arm64/kvm/mmio.c
View File

@ -131,7 +131,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
/*
* No valid syndrome? Ask userspace for help if it has
* voluntered to do so, and bail out otherwise.
* volunteered to do so, and bail out otherwise.
*/
if (!kvm_vcpu_dabt_isvalid(vcpu)) {
if (vcpu->kvm->arch.return_nisv_io_abort_to_user) {

148
virt/kvm/arm/mmu.c → arch/arm64/kvm/mmu.c
View File

@ -422,6 +422,9 @@ static void stage2_flush_memslot(struct kvm *kvm,
next = stage2_pgd_addr_end(kvm, addr, end);
if (!stage2_pgd_none(kvm, *pgd))
stage2_flush_puds(kvm, pgd, addr, next);
if (next != end)
cond_resched_lock(&kvm->mmu_lock);
} while (pgd++, addr = next, addr != end);
}
@ -784,7 +787,7 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
mutex_lock(&kvm_hyp_pgd_mutex);
/*
* This assumes that we we have enough space below the idmap
* This assumes that we have enough space below the idmap
* page to allocate our VAs. If not, the check below will
* kick. A potential alternative would be to detect that
* overflow and switch to an allocation above the idmap.
@ -964,7 +967,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
* stage2_unmap_vm - Unmap Stage-2 RAM mappings
* @kvm: The struct kvm pointer
*
* Go through the memregions and unmap any reguler RAM
* Go through the memregions and unmap any regular RAM
* backing memory already mapped to the VM.
*/
void stage2_unmap_vm(struct kvm *kvm)
@ -1372,47 +1375,6 @@ out:
return ret;
}
static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
{
kvm_pfn_t pfn = *pfnp;
gfn_t gfn = *ipap >> PAGE_SHIFT;
if (kvm_is_transparent_hugepage(pfn)) {
unsigned long mask;
/*
* The address we faulted on is backed by a transparent huge
* page. However, because we map the compound huge page and
* not the individual tail page, we need to transfer the
* refcount to the head page. We have to be careful that the
* THP doesn't start to split while we are adjusting the
* refcounts.
*
* We are sure this doesn't happen, because mmu_notifier_retry
* was successful and we are holding the mmu_lock, so if this
* THP is trying to split, it will be blocked in the mmu
* notifier before touching any of the pages, specifically
* before being able to call __split_huge_page_refcount().
*
* We can therefore safely transfer the refcount from PG_tail
* to PG_head and switch the pfn from a tail page to the head
* page accordingly.
*/
mask = PTRS_PER_PMD - 1;
VM_BUG_ON((gfn & mask) != (pfn & mask));
if (pfn & mask) {
*ipap &= PMD_MASK;
kvm_release_pfn_clean(pfn);
pfn &= ~mask;
kvm_get_pfn(pfn);
*pfnp = pfn;
}
return true;
}
return false;
}
/**
* stage2_wp_ptes - write protect PMD range
* @pmd: pointer to pmd entry
@ -1607,6 +1569,10 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
hva_t uaddr_start, uaddr_end;
size_t size;
/* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */
if (map_size == PAGE_SIZE)
return true;
size = memslot->npages * PAGE_SIZE;
gpa_start = memslot->base_gfn << PAGE_SHIFT;
@ -1626,7 +1592,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
* |abcde|fgh Stage-1 block | Stage-1 block tv|xyz|
* +-----+--------------------+--------------------+---+
*
* memslot->base_gfn << PAGE_SIZE:
* memslot->base_gfn << PAGE_SHIFT:
* +---+--------------------+--------------------+-----+
* |abc|def Stage-2 block | Stage-2 block |tvxyz|
* +---+--------------------+--------------------+-----+
@ -1656,6 +1622,59 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
(hva & ~(map_size - 1)) + map_size <= uaddr_end;
}
/*
* Check if the given hva is backed by a transparent huge page (THP) and
* whether it can be mapped using block mapping in stage2. If so, adjust
* the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently
* supported. This will need to be updated to support other THP sizes.
*
* Returns the size of the mapping.
*/
static unsigned long
transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
unsigned long hva, kvm_pfn_t *pfnp,
phys_addr_t *ipap)
{
kvm_pfn_t pfn = *pfnp;
/*
* Make sure the adjustment is done only for THP pages. Also make
* sure that the HVA and IPA are sufficiently aligned and that the
* block map is contained within the memslot.
*/
if (kvm_is_transparent_hugepage(pfn) &&
fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
/*
* The address we faulted on is backed by a transparent huge
* page. However, because we map the compound huge page and
* not the individual tail page, we need to transfer the
* refcount to the head page. We have to be careful that the
* THP doesn't start to split while we are adjusting the
* refcounts.
*
* We are sure this doesn't happen, because mmu_notifier_retry
* was successful and we are holding the mmu_lock, so if this
* THP is trying to split, it will be blocked in the mmu
* notifier before touching any of the pages, specifically
* before being able to call __split_huge_page_refcount().
*
* We can therefore safely transfer the refcount from PG_tail
* to PG_head and switch the pfn from a tail page to the head
* page accordingly.
*/
*ipap &= PMD_MASK;
kvm_release_pfn_clean(pfn);
pfn &= ~(PTRS_PER_PMD - 1);
kvm_get_pfn(pfn);
*pfnp = pfn;
return PMD_SIZE;
}
/* Use page mapping if we cannot use block mapping. */
return PAGE_SIZE;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_memory_slot *memslot, unsigned long hva,
unsigned long fault_status)
@ -1769,20 +1788,13 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
if (vma_pagesize == PAGE_SIZE && !force_pte) {
/*
* Only PMD_SIZE transparent hugepages(THP) are
* currently supported. This code will need to be
* updated to support other THP sizes.
*
* Make sure the host VA and the guest IPA are sufficiently
* aligned and that the block is contained within the memslot.
*/
if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
transparent_hugepage_adjust(&pfn, &fault_ipa))
vma_pagesize = PMD_SIZE;
}
/*
* If we are not forced to use page mapping, check if we are
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !force_pte)
vma_pagesize = transparent_hugepage_adjust(memslot, hva,
&pfn, &fault_ipa);
if (writable)
kvm_set_pfn_dirty(pfn);
@ -2185,11 +2197,11 @@ int kvm_mmu_init(void)
{
int err;
hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start);
hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start);
hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end);
hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE);
hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);
hyp_idmap_vector = __pa_symbol(__kvm_hyp_init);
/*
* We rely on the linker script to ensure at build time that the HYP
@ -2262,11 +2274,19 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
{
/*
* At this point memslot has been committed and there is an
* allocated dirty_bitmap[], dirty pages will be be tracked while the
* allocated dirty_bitmap[], dirty pages will be tracked while the
* memory slot is write protected.
*/
if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES)
kvm_mmu_wp_memory_region(kvm, mem->slot);
if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
/*
* If we're with initial-all-set, we don't need to write
* protect any pages because they're all reported as dirty.
* Huge pages and normal pages will be write protect gradually.
*/
if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) {
kvm_mmu_wp_memory_region(kvm, mem->slot);
}
}
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,

0
virt/kvm/arm/perf.c → arch/arm64/kvm/perf.c
View File

0
virt/kvm/arm/pmu.c → arch/arm64/kvm/pmu-emul.c
View File

6
virt/kvm/arm/psci.c → arch/arm64/kvm/psci.c
View File

@ -94,7 +94,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
/*
* NOTE: We always update r0 (or x0) because for PSCI v0.1
* the general puspose registers are undefined upon CPU_ON.
* the general purpose registers are undefined upon CPU_ON.
*/
reset_state->r0 = smccc_get_arg3(source_vcpu);
@ -265,10 +265,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
case PSCI_0_2_FN_SYSTEM_OFF:
kvm_psci_system_off(vcpu);
/*
* We should'nt be going back to guest VCPU after
* We shouldn't be going back to guest VCPU after
* receiving SYSTEM_OFF request.
*
* If user space accidently/deliberately resumes
* If user space accidentally/deliberately resumes
* guest VCPU after SYSTEM_OFF request then guest
* VCPU should see internal failure from PSCI return
* value. To achieve this, we preload r0 (or x0) with

0
virt/kvm/arm/pvtime.c → arch/arm64/kvm/pvtime.c
View File

27
arch/arm64/kvm/reset.c
View File

@ -36,15 +36,11 @@ static u32 kvm_ipa_limit;
/*
* ARMv8 Reset Values
*/
static const struct kvm_regs default_regs_reset = {
.regs.pstate = (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT |
PSR_F_BIT | PSR_D_BIT),
};
#define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
PSR_F_BIT | PSR_D_BIT)
static const struct kvm_regs default_regs_reset32 = {
.regs.pstate = (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT |
PSR_AA32_I_BIT | PSR_AA32_F_BIT),
};
#define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
PSR_AA32_I_BIT | PSR_AA32_F_BIT)
/**
* kvm_arch_vm_ioctl_check_extension
@ -155,7 +151,7 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
vl = vcpu->arch.sve_max_vl;
/*
* Resposibility for these properties is shared between
* Responsibility for these properties is shared between
* kvm_arm_init_arch_resources(), kvm_vcpu_enable_sve() and
* set_sve_vls(). Double-check here just to be sure:
*/
@ -241,7 +237,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
* ioctl or as part of handling a request issued by another VCPU in the PSCI
* handling code. In the first case, the VCPU will not be loaded, and in the
* second case the VCPU will be loaded. Because this function operates purely
* on the memory-backed valus of system registers, we want to do a full put if
* on the memory-backed values of system registers, we want to do a full put if
* we were loaded (handling a request) and load the values back at the end of
* the function. Otherwise we leave the state alone. In both cases, we
* disable preemption around the vcpu reset as we would otherwise race with
@ -249,9 +245,9 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
*/
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
const struct kvm_regs *cpu_reset;
int ret = -EINVAL;
bool loaded;
u32 pstate;
/* Reset PMU outside of the non-preemptible section */
kvm_pmu_vcpu_reset(vcpu);
@ -282,16 +278,17 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
goto out;
cpu_reset = &default_regs_reset32;
pstate = VCPU_RESET_PSTATE_SVC;
} else {
cpu_reset = &default_regs_reset;
pstate = VCPU_RESET_PSTATE_EL1;
}
break;
}
/* Reset core registers */
memcpy(vcpu_gp_regs(vcpu), cpu_reset, sizeof(*cpu_reset));
memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
vcpu_gp_regs(vcpu)->regs.pstate = pstate;
/* Reset system registers */
kvm_reset_sys_regs(vcpu);
@ -388,7 +385,7 @@ int kvm_set_ipa_limit(void)
*
* So clamp the ipa limit further down to limit the number of levels.
* Since we can concatenate upto 16 tables at entry level, we could
* go upto 4bits above the maximum VA addressible with the current
* go upto 4bits above the maximum VA addressable with the current
* number of levels.
*/
va_max = PGDIR_SHIFT + PAGE_SHIFT - 3;

212
arch/arm64/kvm/sys_regs.c
View File

@ -34,7 +34,7 @@
#include "trace.h"
/*
* All of this file is extremly similar to the ARM coproc.c, but the
* All of this file is extremely similar to the ARM coproc.c, but the
* types are different. My gut feeling is that it should be pretty
* easy to merge, but that would be an ABI breakage -- again. VFP
* would also need to be abstracted.
@ -64,11 +64,8 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
return false;
}
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
{
if (!vcpu->arch.sysregs_loaded_on_cpu)
goto immediate_read;
/*
* System registers listed in the switch are not saved on every
* exit from the guest but are only saved on vcpu_put.
@ -79,75 +76,92 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
* thread when emulating cross-VCPU communication.
*/
switch (reg) {
case CSSELR_EL1: return read_sysreg_s(SYS_CSSELR_EL1);
case SCTLR_EL1: return read_sysreg_s(SYS_SCTLR_EL12);
case ACTLR_EL1: return read_sysreg_s(SYS_ACTLR_EL1);
case CPACR_EL1: return read_sysreg_s(SYS_CPACR_EL12);
case TTBR0_EL1: return read_sysreg_s(SYS_TTBR0_EL12);
case TTBR1_EL1: return read_sysreg_s(SYS_TTBR1_EL12);
case TCR_EL1: return read_sysreg_s(SYS_TCR_EL12);
case ESR_EL1: return read_sysreg_s(SYS_ESR_EL12);
case AFSR0_EL1: return read_sysreg_s(SYS_AFSR0_EL12);
case AFSR1_EL1: return read_sysreg_s(SYS_AFSR1_EL12);
case FAR_EL1: return read_sysreg_s(SYS_FAR_EL12);
case MAIR_EL1: return read_sysreg_s(SYS_MAIR_EL12);
case VBAR_EL1: return read_sysreg_s(SYS_VBAR_EL12);
case CONTEXTIDR_EL1: return read_sysreg_s(SYS_CONTEXTIDR_EL12);
case TPIDR_EL0: return read_sysreg_s(SYS_TPIDR_EL0);
case TPIDRRO_EL0: return read_sysreg_s(SYS_TPIDRRO_EL0);
case TPIDR_EL1: return read_sysreg_s(SYS_TPIDR_EL1);
case AMAIR_EL1: return read_sysreg_s(SYS_AMAIR_EL12);
case CNTKCTL_EL1: return read_sysreg_s(SYS_CNTKCTL_EL12);
case PAR_EL1: return read_sysreg_s(SYS_PAR_EL1);
case DACR32_EL2: return read_sysreg_s(SYS_DACR32_EL2);
case IFSR32_EL2: return read_sysreg_s(SYS_IFSR32_EL2);
case DBGVCR32_EL2: return read_sysreg_s(SYS_DBGVCR32_EL2);
case CSSELR_EL1: *val = read_sysreg_s(SYS_CSSELR_EL1); break;
case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break;
case ACTLR_EL1: *val = read_sysreg_s(SYS_ACTLR_EL1); break;
case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break;
case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break;
case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break;
case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break;
case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break;
case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break;
case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break;
case FAR_EL1: *val = read_sysreg_s(SYS_FAR_EL12); break;
case MAIR_EL1: *val = read_sysreg_s(SYS_MAIR_EL12); break;
case VBAR_EL1: *val = read_sysreg_s(SYS_VBAR_EL12); break;
case CONTEXTIDR_EL1: *val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
case TPIDR_EL0: *val = read_sysreg_s(SYS_TPIDR_EL0); break;
case TPIDRRO_EL0: *val = read_sysreg_s(SYS_TPIDRRO_EL0); break;
case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break;
case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break;
case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break;
case PAR_EL1: *val = read_sysreg_s(SYS_PAR_EL1); break;
case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break;
case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break;
case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break;
default: return false;
}
immediate_read:
return __vcpu_sys_reg(vcpu, reg);
return true;
}
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
{
if (!vcpu->arch.sysregs_loaded_on_cpu)
goto immediate_write;
/*
* System registers listed in the switch are not restored on every
* entry to the guest but are only restored on vcpu_load.
*
* Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
* should never be listed below, because the the MPIDR should only be
* set once, before running the VCPU, and never changed later.
* should never be listed below, because the MPIDR should only be set
* once, before running the VCPU, and never changed later.
*/
switch (reg) {
case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); return;
case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); return;
case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); return;
case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); return;
case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); return;
case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); return;
case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); return;
case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); return;
case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); return;
case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); return;
case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); return;
case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); return;
case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); return;
case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12); return;
case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); return;
case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); return;
case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); return;
case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); return;
case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); return;
case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); return;
case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); return;
case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); return;
case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); return;
case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); break;
case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break;
case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); break;
case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break;
case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break;
case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break;
case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break;
case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break;
case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break;
case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break;
case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break;
case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break;
case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break;
case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break;
case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break;
case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break;
case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break;
case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break;
case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break;
case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break;
case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break;
case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break;
default: return false;
}
immediate_write:
return true;
}
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
{
u64 val = 0x8badf00d8badf00d;
if (vcpu->arch.sysregs_loaded_on_cpu &&
__vcpu_read_sys_reg_from_cpu(reg, &val))
return val;
return __vcpu_sys_reg(vcpu, reg);
}
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
{
if (vcpu->arch.sysregs_loaded_on_cpu &&
__vcpu_write_sys_reg_to_cpu(val, reg))
return;
__vcpu_sys_reg(vcpu, reg) = val;
}
@ -1532,7 +1546,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
{ SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
{ SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, NULL, PMINTENSET_EL1 },
{ SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
@ -1571,8 +1585,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 },
{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
{ SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 },
{ SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 },
{ SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
{ SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
{ SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 },
{ SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 },
{ SYS_DESC(SYS_PMCEID0_EL0), access_pmceid },
@ -2073,12 +2087,37 @@ static const struct sys_reg_desc cp15_64_regs[] = {
{ SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer },
};
static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
bool is_32)
{
unsigned int i;
for (i = 0; i < n; i++) {
if (!is_32 && table[i].reg && !table[i].reset) {
kvm_err("sys_reg table %p entry %d has lacks reset\n",
table, i);
return 1;
}
if (i && cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
return 1;
}
}
return 0;
}
/* Target specific emulation tables */
static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS];
void kvm_register_target_sys_reg_table(unsigned int target,
struct kvm_sys_reg_target_table *table)
{
if (check_sysreg_table(table->table64.table, table->table64.num, false) ||
check_sysreg_table(table->table32.table, table->table32.num, true))
return;
target_tables[target] = table;
}
@ -2364,19 +2403,13 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
}
static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *table, size_t num,
unsigned long *bmap)
const struct sys_reg_desc *table, size_t num)
{
unsigned long i;
for (i = 0; i < num; i++)
if (table[i].reset) {
int reg = table[i].reg;
if (table[i].reset)
table[i].reset(vcpu, &table[i]);
if (reg > 0 && reg < NR_SYS_REGS)
set_bit(reg, bmap);
}
}
/**
@ -2832,32 +2865,18 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
return write_demux_regids(uindices);
}
static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
{
unsigned int i;
for (i = 1; i < n; i++) {
if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
return 1;
}
}
return 0;
}
void kvm_sys_reg_table_init(void)
{
unsigned int i;
struct sys_reg_desc clidr;
/* Make sure tables are unique and in order. */
BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false));
BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs), true));
BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), true));
BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true));
BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true));
BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false));
/* We abuse the reset function to overwrite the table itself. */
for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
@ -2893,17 +2912,10 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
{
size_t num;
const struct sys_reg_desc *table;
DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, };
/* Generic chip reset first (so target could override). */
reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap);
reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
table = get_target_table(vcpu->arch.target, true, &num);
reset_sys_reg_descs(vcpu, table, num, bmap);
for (num = 1; num < NR_SYS_REGS; num++) {
if (WARN(!test_bit(num, bmap),
"Didn't reset __vcpu_sys_reg(%zi)\n", num))
break;
}
reset_sys_reg_descs(vcpu, table, num);
}

216
arch/arm64/kvm/trace.h
View File

@ -1,216 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0 */
#if !defined(_TRACE_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
#ifndef _TRACE_ARM64_KVM_H
#define _TRACE_ARM64_KVM_H
#include <linux/tracepoint.h>
#include "sys_regs.h"
#include "trace_arm.h"
#include "trace_handle_exit.h"
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
TRACE_EVENT(kvm_wfx_arm64,
TP_PROTO(unsigned long vcpu_pc, bool is_wfe),
TP_ARGS(vcpu_pc, is_wfe),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(bool, is_wfe)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->is_wfe = is_wfe;
),
TP_printk("guest executed wf%c at: 0x%08lx",
__entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
);
TRACE_EVENT(kvm_hvc_arm64,
TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
TP_ARGS(vcpu_pc, r0, imm),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(unsigned long, r0)
__field(unsigned long, imm)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->r0 = r0;
__entry->imm = imm;
),
TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
__entry->vcpu_pc, __entry->r0, __entry->imm)
);
TRACE_EVENT(kvm_arm_setup_debug,
TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
TP_ARGS(vcpu, guest_debug),
TP_STRUCT__entry(
__field(struct kvm_vcpu *, vcpu)
__field(__u32, guest_debug)
),
TP_fast_assign(
__entry->vcpu = vcpu;
__entry->guest_debug = guest_debug;
),
TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug)
);
TRACE_EVENT(kvm_arm_clear_debug,
TP_PROTO(__u32 guest_debug),
TP_ARGS(guest_debug),
TP_STRUCT__entry(
__field(__u32, guest_debug)
),
TP_fast_assign(
__entry->guest_debug = guest_debug;
),
TP_printk("flags: 0x%08x", __entry->guest_debug)
);
TRACE_EVENT(kvm_arm_set_dreg32,
TP_PROTO(const char *name, __u32 value),
TP_ARGS(name, value),
TP_STRUCT__entry(
__field(const char *, name)
__field(__u32, value)
),
TP_fast_assign(
__entry->name = name;
__entry->value = value;
),
TP_printk("%s: 0x%08x", __entry->name, __entry->value)
);
TRACE_DEFINE_SIZEOF(__u64);
TRACE_EVENT(kvm_arm_set_regset,
TP_PROTO(const char *type, int len, __u64 *control, __u64 *value),
TP_ARGS(type, len, control, value),
TP_STRUCT__entry(
__field(const char *, name)
__field(int, len)
__array(u64, ctrls, 16)
__array(u64, values, 16)
),
TP_fast_assign(
__entry->name = type;
__entry->len = len;
memcpy(__entry->ctrls, control, len << 3);
memcpy(__entry->values, value, len << 3);
),
TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name,
__print_array(__entry->ctrls, __entry->len, sizeof(__u64)),
__print_array(__entry->values, __entry->len, sizeof(__u64)))
);
TRACE_EVENT(trap_reg,
TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value),
TP_ARGS(fn, reg, is_write, write_value),
TP_STRUCT__entry(
__field(const char *, fn)
__field(int, reg)
__field(bool, is_write)
__field(u64, write_value)
),
TP_fast_assign(
__entry->fn = fn;
__entry->reg = reg;
__entry->is_write = is_write;
__entry->write_value = write_value;
),
TP_printk("%s %s reg %d (0x%08llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
);
TRACE_EVENT(kvm_handle_sys_reg,
TP_PROTO(unsigned long hsr),
TP_ARGS(hsr),
TP_STRUCT__entry(
__field(unsigned long, hsr)
),
TP_fast_assign(
__entry->hsr = hsr;
),
TP_printk("HSR 0x%08lx", __entry->hsr)
);
TRACE_EVENT(kvm_sys_access,
TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg),
TP_ARGS(vcpu_pc, params, reg),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(bool, is_write)
__field(const char *, name)
__field(u8, Op0)
__field(u8, Op1)
__field(u8, CRn)
__field(u8, CRm)
__field(u8, Op2)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->is_write = params->is_write;
__entry->name = reg->name;
__entry->Op0 = reg->Op0;
__entry->Op0 = reg->Op0;
__entry->Op1 = reg->Op1;
__entry->CRn = reg->CRn;
__entry->CRm = reg->CRm;
__entry->Op2 = reg->Op2;
),
TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s",
__entry->vcpu_pc, __entry->name ?: "UNKN",
__entry->Op0, __entry->Op1, __entry->CRn,
__entry->CRm, __entry->Op2,
__entry->is_write ? "write" : "read")
);
TRACE_EVENT(kvm_set_guest_debug,
TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
TP_ARGS(vcpu, guest_debug),
TP_STRUCT__entry(
__field(struct kvm_vcpu *, vcpu)
__field(__u32, guest_debug)
),
TP_fast_assign(
__entry->vcpu = vcpu;
__entry->guest_debug = guest_debug;
),
TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug)
);
#endif /* _TRACE_ARM64_KVM_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace
/* This part must be outside protection */
#include <trace/define_trace.h>
#endif /* _TRACE_ARM64_KVM_H */

11
virt/kvm/arm/trace.h → arch/arm64/kvm/trace_arm.h
View File

@ -1,10 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_KVM_H
#if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_ARM_ARM64_KVM_H
#include <kvm/arm_arch_timer.h>
#include <linux/tracepoint.h>
#include <asm/kvm_arm.h>
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
@ -368,12 +367,12 @@ TRACE_EVENT(kvm_timer_emulate,
__entry->timer_idx, __entry->should_fire)
);
#endif /* _TRACE_KVM_H */
#endif /* _TRACE_ARM_ARM64_KVM_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH ../../virt/kvm/arm
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace
#define TRACE_INCLUDE_FILE trace_arm
/* This part must be outside protection */
#include <trace/define_trace.h>

215
arch/arm64/kvm/trace_handle_exit.h Normal file
View File

@ -0,0 +1,215 @@
/* SPDX-License-Identifier: GPL-2.0 */
#if !defined(_TRACE_HANDLE_EXIT_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_HANDLE_EXIT_ARM64_KVM_H
#include <linux/tracepoint.h>
#include "sys_regs.h"
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
TRACE_EVENT(kvm_wfx_arm64,
TP_PROTO(unsigned long vcpu_pc, bool is_wfe),
TP_ARGS(vcpu_pc, is_wfe),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(bool, is_wfe)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->is_wfe = is_wfe;
),
TP_printk("guest executed wf%c at: 0x%08lx",
__entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
);
TRACE_EVENT(kvm_hvc_arm64,
TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
TP_ARGS(vcpu_pc, r0, imm),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(unsigned long, r0)
__field(unsigned long, imm)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->r0 = r0;
__entry->imm = imm;
),
TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
__entry->vcpu_pc, __entry->r0, __entry->imm)
);
TRACE_EVENT(kvm_arm_setup_debug,
TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
TP_ARGS(vcpu, guest_debug),
TP_STRUCT__entry(
__field(struct kvm_vcpu *, vcpu)
__field(__u32, guest_debug)
),
TP_fast_assign(
__entry->vcpu = vcpu;
__entry->guest_debug = guest_debug;
),
TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug)
);
TRACE_EVENT(kvm_arm_clear_debug,
TP_PROTO(__u32 guest_debug),
TP_ARGS(guest_debug),
TP_STRUCT__entry(
__field(__u32, guest_debug)
),
TP_fast_assign(
__entry->guest_debug = guest_debug;
),
TP_printk("flags: 0x%08x", __entry->guest_debug)
);
TRACE_EVENT(kvm_arm_set_dreg32,
TP_PROTO(const char *name, __u32 value),
TP_ARGS(name, value),
TP_STRUCT__entry(
__field(const char *, name)
__field(__u32, value)
),
TP_fast_assign(
__entry->name = name;
__entry->value = value;
),
TP_printk("%s: 0x%08x", __entry->name, __entry->value)
);
TRACE_DEFINE_SIZEOF(__u64);
TRACE_EVENT(kvm_arm_set_regset,
TP_PROTO(const char *type, int len, __u64 *control, __u64 *value),
TP_ARGS(type, len, control, value),
TP_STRUCT__entry(
__field(const char *, name)
__field(int, len)
__array(u64, ctrls, 16)
__array(u64, values, 16)
),
TP_fast_assign(
__entry->name = type;
__entry->len = len;
memcpy(__entry->ctrls, control, len << 3);
memcpy(__entry->values, value, len << 3);
),
TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name,
__print_array(__entry->ctrls, __entry->len, sizeof(__u64)),
__print_array(__entry->values, __entry->len, sizeof(__u64)))
);
TRACE_EVENT(trap_reg,
TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value),
TP_ARGS(fn, reg, is_write, write_value),
TP_STRUCT__entry(
__field(const char *, fn)
__field(int, reg)
__field(bool, is_write)
__field(u64, write_value)
),
TP_fast_assign(
__entry->fn = fn;
__entry->reg = reg;
__entry->is_write = is_write;
__entry->write_value = write_value;
),
TP_printk("%s %s reg %d (0x%08llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
);
TRACE_EVENT(kvm_handle_sys_reg,
TP_PROTO(unsigned long hsr),
TP_ARGS(hsr),
TP_STRUCT__entry(
__field(unsigned long, hsr)
),
TP_fast_assign(
__entry->hsr = hsr;
),
TP_printk("HSR 0x%08lx", __entry->hsr)
);
TRACE_EVENT(kvm_sys_access,
TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg),
TP_ARGS(vcpu_pc, params, reg),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(bool, is_write)
__field(const char *, name)
__field(u8, Op0)
__field(u8, Op1)
__field(u8, CRn)
__field(u8, CRm)
__field(u8, Op2)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->is_write = params->is_write;
__entry->name = reg->name;
__entry->Op0 = reg->Op0;
__entry->Op0 = reg->Op0;
__entry->Op1 = reg->Op1;
__entry->CRn = reg->CRn;
__entry->CRm = reg->CRm;
__entry->Op2 = reg->Op2;
),
TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s",
__entry->vcpu_pc, __entry->name ?: "UNKN",
__entry->Op0, __entry->Op1, __entry->CRn,
__entry->CRm, __entry->Op2,
__entry->is_write ? "write" : "read")
);
TRACE_EVENT(kvm_set_guest_debug,
TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
TP_ARGS(vcpu, guest_debug),
TP_STRUCT__entry(
__field(struct kvm_vcpu *, vcpu)
__field(__u32, guest_debug)
),
TP_fast_assign(
__entry->vcpu = vcpu;
__entry->guest_debug = guest_debug;
),
TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug)
);
#endif /* _TRACE_HANDLE_EXIT_ARM64_KVM_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace_handle_exit
/* This part must be outside protection */
#include <trace/define_trace.h>

2
arch/arm64/kvm/vgic-sys-reg-v3.c
View File

@ -7,7 +7,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include "vgic.h"
#include "vgic/vgic.h"
#include "sys_regs.h"
static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,

2
virt/kvm/arm/vgic/trace.h → arch/arm64/kvm/vgic/trace.h
View File

@ -30,7 +30,7 @@ TRACE_EVENT(vgic_update_irq_pending,
#endif /* _TRACE_VGIC_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH ../../virt/kvm/arm/vgic
#define TRACE_INCLUDE_PATH ../../arch/arm64/kvm/vgic
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace

0
virt/kvm/arm/vgic/vgic-debug.c → arch/arm64/kvm/vgic/vgic-debug.c
View File

0
virt/kvm/arm/vgic/vgic-init.c → arch/arm64/kvm/vgic/vgic-init.c
View File

0
virt/kvm/arm/vgic/vgic-irqfd.c → arch/arm64/kvm/vgic/vgic-irqfd.c
View File

0
virt/kvm/arm/vgic/vgic-its.c → arch/arm64/kvm/vgic/vgic-its.c
View File

0
virt/kvm/arm/vgic/vgic-kvm-device.c → arch/arm64/kvm/vgic/vgic-kvm-device.c
View File

0
virt/kvm/arm/vgic/vgic-mmio-v2.c → arch/arm64/kvm/vgic/vgic-mmio-v2.c
View File

0
virt/kvm/arm/vgic/vgic-mmio-v3.c → arch/arm64/kvm/vgic/vgic-mmio-v3.c
View File

0
virt/kvm/arm/vgic/vgic-mmio.c → arch/arm64/kvm/vgic/vgic-mmio.c
View File

0
virt/kvm/arm/vgic/vgic-mmio.h → arch/arm64/kvm/vgic/vgic-mmio.h
View File

10
virt/kvm/arm/vgic/vgic-v2.c → arch/arm64/kvm/vgic/vgic-v2.c
View File

@ -56,7 +56,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
cpuif->vgic_hcr &= ~GICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
for (lr = 0; lr < vgic_cpu->vgic_v2.used_lrs; lr++) {
u32 val = cpuif->vgic_lr[lr];
u32 cpuid, intid = val & GICH_LR_VIRTUALID;
struct vgic_irq *irq;
@ -120,7 +120,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
vgic_put_irq(vcpu->kvm, irq);
}
vgic_cpu->used_lrs = 0;
cpuif->used_lrs = 0;
}
/*
@ -427,7 +427,7 @@ out:
static void save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
u64 used_lrs = cpu_if->used_lrs;
u64 elrsr;
int i;
@ -448,7 +448,7 @@ static void save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
void vgic_v2_save_state(struct kvm_vcpu *vcpu)
{
void __iomem *base = kvm_vgic_global_state.vctrl_base;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
u64 used_lrs = vcpu->arch.vgic_cpu.vgic_v2.used_lrs;
if (!base)
return;
@ -463,7 +463,7 @@ void vgic_v2_restore_state(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
void __iomem *base = kvm_vgic_global_state.vctrl_base;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
u64 used_lrs = cpu_if->used_lrs;
int i;
if (!base)

18
virt/kvm/arm/vgic/vgic-v3.c → arch/arm64/kvm/vgic/vgic-v3.c
View File

@ -39,7 +39,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
cpuif->vgic_hcr &= ~ICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
for (lr = 0; lr < cpuif->used_lrs; lr++) {
u64 val = cpuif->vgic_lr[lr];
u32 intid, cpuid;
struct vgic_irq *irq;
@ -111,7 +111,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
vgic_put_irq(vcpu->kvm, irq);
}
vgic_cpu->used_lrs = 0;
cpuif->used_lrs = 0;
}
/* Requires the irq to be locked already */
@ -587,7 +587,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
int ret;
/*
* The ListRegs field is 5 bits, but there is a architectural
* The ListRegs field is 5 bits, but there is an architectural
* maximum of 16 list registers. Just ignore bit 4...
*/
kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1;
@ -630,12 +630,10 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
if (kvm_vgic_global_state.vcpu_base == 0)
kvm_info("disabling GICv2 emulation\n");
#ifdef CONFIG_ARM64
if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) {
group0_trap = true;
group1_trap = true;
}
#endif
if (group0_trap || group1_trap || common_trap) {
kvm_info("GICv3 sysreg trapping enabled ([%s%s%s], reduced performance)\n",
@ -664,10 +662,10 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
if (likely(cpu_if->vgic_sre))
kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr);
kvm_call_hyp(__vgic_v3_restore_aprs, vcpu);
kvm_call_hyp(__vgic_v3_restore_aprs, kern_hyp_va(cpu_if));
if (has_vhe())
__vgic_v3_activate_traps(vcpu);
__vgic_v3_activate_traps(cpu_if);
WARN_ON(vgic_v4_load(vcpu));
}
@ -682,12 +680,14 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
void vgic_v3_put(struct kvm_vcpu *vcpu)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
WARN_ON(vgic_v4_put(vcpu, false));
vgic_v3_vmcr_sync(vcpu);
kvm_call_hyp(__vgic_v3_save_aprs, vcpu);
kvm_call_hyp(__vgic_v3_save_aprs, kern_hyp_va(cpu_if));
if (has_vhe())
__vgic_v3_deactivate_traps(vcpu);
__vgic_v3_deactivate_traps(cpu_if);
}

0
virt/kvm/arm/vgic/vgic-v4.c → arch/arm64/kvm/vgic/vgic-v4.c
View File

25
virt/kvm/arm/vgic/vgic.c → arch/arm64/kvm/vgic/vgic.c
View File

@ -786,6 +786,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
int count;
bool multi_sgi;
u8 prio = 0xff;
int i = 0;
lockdep_assert_held(&vgic_cpu->ap_list_lock);
@ -827,11 +828,14 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
}
}
vcpu->arch.vgic_cpu.used_lrs = count;
/* Nuke remaining LRs */
for ( ; count < kvm_vgic_global_state.nr_lr; count++)
vgic_clear_lr(vcpu, count);
for (i = count ; i < kvm_vgic_global_state.nr_lr; i++)
vgic_clear_lr(vcpu, i);
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vcpu->arch.vgic_cpu.vgic_v2.used_lrs = count;
else
vcpu->arch.vgic_cpu.vgic_v3.used_lrs = count;
}
static inline bool can_access_vgic_from_kernel(void)
@ -849,13 +853,13 @@ static inline void vgic_save_state(struct kvm_vcpu *vcpu)
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_save_state(vcpu);
else
__vgic_v3_save_state(vcpu);
__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
}
/* Sync back the hardware VGIC state into our emulation after a guest's run. */
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
int used_lrs;
/* An empty ap_list_head implies used_lrs == 0 */
if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
@ -864,7 +868,12 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
if (can_access_vgic_from_kernel())
vgic_save_state(vcpu);
if (vgic_cpu->used_lrs)
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
used_lrs = vcpu->arch.vgic_cpu.vgic_v2.used_lrs;
else
used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
if (used_lrs)
vgic_fold_lr_state(vcpu);
vgic_prune_ap_list(vcpu);
}
@ -874,7 +883,7 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_restore_state(vcpu);
else
__vgic_v3_restore_state(vcpu);
__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
}
/* Flush our emulation state into the GIC hardware before entering the guest. */

0
virt/kvm/arm/vgic/vgic.h → arch/arm64/kvm/vgic/vgic.h
View File

2
arch/mips/include/asm/kvm_host.h
View File

@ -174,6 +174,8 @@ struct kvm_vcpu_stat {
#endif
u64 halt_successful_poll;
u64 halt_attempted_poll;
u64 halt_poll_success_ns;
u64 halt_poll_fail_ns;
u64 halt_poll_invalid;
u64 halt_wakeup;
};

72
arch/mips/kvm/mips.c
View File

@ -39,40 +39,41 @@
#define VECTORSPACING 0x100 /* for EI/VI mode */
#endif
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x)
struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "wait", VCPU_STAT(wait_exits), KVM_STAT_VCPU },
{ "cache", VCPU_STAT(cache_exits), KVM_STAT_VCPU },
{ "signal", VCPU_STAT(signal_exits), KVM_STAT_VCPU },
{ "interrupt", VCPU_STAT(int_exits), KVM_STAT_VCPU },
{ "cop_unusable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
{ "tlbmod", VCPU_STAT(tlbmod_exits), KVM_STAT_VCPU },
{ "tlbmiss_ld", VCPU_STAT(tlbmiss_ld_exits), KVM_STAT_VCPU },
{ "tlbmiss_st", VCPU_STAT(tlbmiss_st_exits), KVM_STAT_VCPU },
{ "addrerr_st", VCPU_STAT(addrerr_st_exits), KVM_STAT_VCPU },
{ "addrerr_ld", VCPU_STAT(addrerr_ld_exits), KVM_STAT_VCPU },
{ "syscall", VCPU_STAT(syscall_exits), KVM_STAT_VCPU },
{ "resvd_inst", VCPU_STAT(resvd_inst_exits), KVM_STAT_VCPU },
{ "break_inst", VCPU_STAT(break_inst_exits), KVM_STAT_VCPU },
{ "trap_inst", VCPU_STAT(trap_inst_exits), KVM_STAT_VCPU },
{ "msa_fpe", VCPU_STAT(msa_fpe_exits), KVM_STAT_VCPU },
{ "fpe", VCPU_STAT(fpe_exits), KVM_STAT_VCPU },
{ "msa_disabled", VCPU_STAT(msa_disabled_exits), KVM_STAT_VCPU },
{ "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU },
VCPU_STAT("wait", wait_exits),
VCPU_STAT("cache", cache_exits),
VCPU_STAT("signal", signal_exits),
VCPU_STAT("interrupt", int_exits),
VCPU_STAT("cop_unusable", cop_unusable_exits),
VCPU_STAT("tlbmod", tlbmod_exits),
VCPU_STAT("tlbmiss_ld", tlbmiss_ld_exits),
VCPU_STAT("tlbmiss_st", tlbmiss_st_exits),
VCPU_STAT("addrerr_st", addrerr_st_exits),
VCPU_STAT("addrerr_ld", addrerr_ld_exits),
VCPU_STAT("syscall", syscall_exits),
VCPU_STAT("resvd_inst", resvd_inst_exits),
VCPU_STAT("break_inst", break_inst_exits),
VCPU_STAT("trap_inst", trap_inst_exits),
VCPU_STAT("msa_fpe", msa_fpe_exits),
VCPU_STAT("fpe", fpe_exits),
VCPU_STAT("msa_disabled", msa_disabled_exits),
VCPU_STAT("flush_dcache", flush_dcache_exits),
#ifdef CONFIG_KVM_MIPS_VZ
{ "vz_gpsi", VCPU_STAT(vz_gpsi_exits), KVM_STAT_VCPU },
{ "vz_gsfc", VCPU_STAT(vz_gsfc_exits), KVM_STAT_VCPU },
{ "vz_hc", VCPU_STAT(vz_hc_exits), KVM_STAT_VCPU },
{ "vz_grr", VCPU_STAT(vz_grr_exits), KVM_STAT_VCPU },
{ "vz_gva", VCPU_STAT(vz_gva_exits), KVM_STAT_VCPU },
{ "vz_ghfc", VCPU_STAT(vz_ghfc_exits), KVM_STAT_VCPU },
{ "vz_gpa", VCPU_STAT(vz_gpa_exits), KVM_STAT_VCPU },
{ "vz_resvd", VCPU_STAT(vz_resvd_exits), KVM_STAT_VCPU },
VCPU_STAT("vz_gpsi", vz_gpsi_exits),
VCPU_STAT("vz_gsfc", vz_gsfc_exits),
VCPU_STAT("vz_hc", vz_hc_exits),
VCPU_STAT("vz_grr", vz_grr_exits),
VCPU_STAT("vz_gva", vz_gva_exits),
VCPU_STAT("vz_ghfc", vz_ghfc_exits),
VCPU_STAT("vz_gpa", vz_gpa_exits),
VCPU_STAT("vz_resvd", vz_resvd_exits),
#endif
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), KVM_STAT_VCPU },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid), KVM_STAT_VCPU },
{ "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU },
VCPU_STAT("halt_successful_poll", halt_successful_poll),
VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
VCPU_STAT("halt_wakeup", halt_wakeup),
VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
{NULL}
};
@ -284,8 +285,7 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
kvm_mips_callbacks->queue_timer_int(vcpu);
vcpu->arch.wait = 0;
if (swq_has_sleeper(&vcpu->wq))
swake_up_one(&vcpu->wq);
rcuwait_wake_up(&vcpu->wait);
return kvm_mips_count_timeout(vcpu);
}
@ -439,8 +439,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
return -ENOIOCTLCMD;
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
int r = -EINTR;
vcpu_load(vcpu);
@ -511,8 +512,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
dvcpu->arch.wait = 0;
if (swq_has_sleeper(&dvcpu->wq))
swake_up_one(&dvcpu->wq);
rcuwait_wake_up(&dvcpu->wait);
return 0;
}

2
arch/powerpc/include/asm/kvm_book3s.h
View File

@ -78,7 +78,7 @@ struct kvmppc_vcore {
struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS];
struct list_head preempt_list;
spinlock_t lock;
struct swait_queue_head wq;
struct rcuwait wait;
spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */
u64 stolen_tb;
u64 preempt_tb;

2
arch/powerpc/include/asm/kvm_host.h
View File

@ -751,7 +751,7 @@ struct kvm_vcpu_arch {
u8 irq_pending; /* Used by XIVE to signal pending guest irqs */
u32 last_inst;
struct swait_queue_head *wqp;
struct rcuwait *waitp;
struct kvmppc_vcore *vcore;
int ret;
int trap;

61
arch/powerpc/kvm/book3s.c
View File

@ -36,41 +36,38 @@
#include "book3s.h"
#include "trace.h"
#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
/* #define EXIT_DEBUG */
struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "exits", VCPU_STAT(sum_exits) },
{ "mmio", VCPU_STAT(mmio_exits) },
{ "sig", VCPU_STAT(signal_exits) },
{ "sysc", VCPU_STAT(syscall_exits) },
{ "inst_emu", VCPU_STAT(emulated_inst_exits) },
{ "dec", VCPU_STAT(dec_exits) },
{ "ext_intr", VCPU_STAT(ext_intr_exits) },
{ "queue_intr", VCPU_STAT(queue_intr) },
{ "halt_poll_success_ns", VCPU_STAT(halt_poll_success_ns) },
{ "halt_poll_fail_ns", VCPU_STAT(halt_poll_fail_ns) },
{ "halt_wait_ns", VCPU_STAT(halt_wait_ns) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), },
{ "halt_successful_wait", VCPU_STAT(halt_successful_wait) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "pf_storage", VCPU_STAT(pf_storage) },
{ "sp_storage", VCPU_STAT(sp_storage) },
{ "pf_instruc", VCPU_STAT(pf_instruc) },
{ "sp_instruc", VCPU_STAT(sp_instruc) },
{ "ld", VCPU_STAT(ld) },
{ "ld_slow", VCPU_STAT(ld_slow) },
{ "st", VCPU_STAT(st) },
{ "st_slow", VCPU_STAT(st_slow) },
{ "pthru_all", VCPU_STAT(pthru_all) },
{ "pthru_host", VCPU_STAT(pthru_host) },
{ "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) },
{ "largepages_2M", VM_STAT(num_2M_pages, .mode = 0444) },
{ "largepages_1G", VM_STAT(num_1G_pages, .mode = 0444) },
VCPU_STAT("exits", sum_exits),
VCPU_STAT("mmio", mmio_exits),
VCPU_STAT("sig", signal_exits),
VCPU_STAT("sysc", syscall_exits),
VCPU_STAT("inst_emu", emulated_inst_exits),
VCPU_STAT("dec", dec_exits),
VCPU_STAT("ext_intr", ext_intr_exits),
VCPU_STAT("queue_intr", queue_intr),
VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
VCPU_STAT("halt_wait_ns", halt_wait_ns),
VCPU_STAT("halt_successful_poll", halt_successful_poll),
VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
VCPU_STAT("halt_successful_wait", halt_successful_wait),
VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
VCPU_STAT("halt_wakeup", halt_wakeup),
VCPU_STAT("pf_storage", pf_storage),
VCPU_STAT("sp_storage", sp_storage),
VCPU_STAT("pf_instruc", pf_instruc),
VCPU_STAT("sp_instruc", sp_instruc),
VCPU_STAT("ld", ld),
VCPU_STAT("ld_slow", ld_slow),
VCPU_STAT("st", st),
VCPU_STAT("st_slow", st_slow),
VCPU_STAT("pthru_all", pthru_all),
VCPU_STAT("pthru_host", pthru_host),
VCPU_STAT("pthru_bad_aff", pthru_bad_aff),
VM_STAT("largepages_2M", num_2M_pages, .mode = 0444),
VM_STAT("largepages_1G", num_1G_pages, .mode = 0444),
{ NULL }
};

23
arch/powerpc/kvm/book3s_hv.c
View File

@ -230,13 +230,11 @@ static bool kvmppc_ipi_thread(int cpu)
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
int cpu;
struct swait_queue_head *wqp;
struct rcuwait *waitp;
wqp = kvm_arch_vcpu_wq(vcpu);
if (swq_has_sleeper(wqp)) {
swake_up_one(wqp);
waitp = kvm_arch_vcpu_get_wait(vcpu);
if (rcuwait_wake_up(waitp))
++vcpu->stat.halt_wakeup;
}
cpu = READ_ONCE(vcpu->arch.thread_cpu);
if (cpu >= 0 && kvmppc_ipi_thread(cpu))
@ -2125,7 +2123,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id)
spin_lock_init(&vcore->lock);
spin_lock_init(&vcore->stoltb_lock);
init_swait_queue_head(&vcore->wq);
rcuwait_init(&vcore->wait);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
vcore->first_vcpuid = id;
@ -3784,7 +3782,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
ktime_t cur, start_poll, start_wait;
int do_sleep = 1;
u64 block_ns;
DECLARE_SWAITQUEUE(wait);
/* Poll for pending exceptions and ceded state */
cur = start_poll = ktime_get();
@ -3812,10 +3809,10 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
}
}
prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
prepare_to_rcuwait(&vc->wait);
set_current_state(TASK_INTERRUPTIBLE);
if (kvmppc_vcore_check_block(vc)) {
finish_swait(&vc->wq, &wait);
finish_rcuwait(&vc->wait);
do_sleep = 0;
/* If we polled, count this as a successful poll */
if (vc->halt_poll_ns)
@ -3829,7 +3826,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
trace_kvmppc_vcore_blocked(vc, 0);
spin_unlock(&vc->lock);
schedule();
finish_swait(&vc->wq, &wait);
finish_rcuwait(&vc->wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
trace_kvmppc_vcore_blocked(vc, 1);
@ -3940,7 +3937,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
kvmppc_start_thread(vcpu, vc);
trace_kvm_guest_enter(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
swake_up_one(&vc->wq);
rcuwait_wake_up(&vc->wait);
}
}
@ -4279,7 +4276,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
}
user_vrsave = mfspr(SPRN_VRSAVE);
vcpu->arch.wqp = &vcpu->arch.vcore->wq;
vcpu->arch.waitp = &vcpu->arch.vcore->wait;
vcpu->arch.pgdir = kvm->mm->pgd;
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;

43
arch/powerpc/kvm/booke.c
View File

@ -35,29 +35,28 @@
unsigned long kvmppc_booke_handlers;
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmio", VCPU_STAT(mmio_exits) },
{ "sig", VCPU_STAT(signal_exits) },
{ "itlb_r", VCPU_STAT(itlb_real_miss_exits) },
{ "itlb_v", VCPU_STAT(itlb_virt_miss_exits) },
{ "dtlb_r", VCPU_STAT(dtlb_real_miss_exits) },
{ "dtlb_v", VCPU_STAT(dtlb_virt_miss_exits) },
{ "sysc", VCPU_STAT(syscall_exits) },
{ "isi", VCPU_STAT(isi_exits) },
{ "dsi", VCPU_STAT(dsi_exits) },
{ "inst_emu", VCPU_STAT(emulated_inst_exits) },
{ "dec", VCPU_STAT(dec_exits) },
{ "ext_intr", VCPU_STAT(ext_intr_exits) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "doorbell", VCPU_STAT(dbell_exits) },
{ "guest doorbell", VCPU_STAT(gdbell_exits) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
VCPU_STAT("mmio", mmio_exits),
VCPU_STAT("sig", signal_exits),
VCPU_STAT("itlb_r", itlb_real_miss_exits),
VCPU_STAT("itlb_v", itlb_virt_miss_exits),
VCPU_STAT("dtlb_r", dtlb_real_miss_exits),
VCPU_STAT("dtlb_v", dtlb_virt_miss_exits),
VCPU_STAT("sysc", syscall_exits),
VCPU_STAT("isi", isi_exits),
VCPU_STAT("dsi", dsi_exits),
VCPU_STAT("inst_emu", emulated_inst_exits),
VCPU_STAT("dec", dec_exits),
VCPU_STAT("ext_intr", ext_intr_exits),
VCPU_STAT("halt_successful_poll", halt_successful_poll),
VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
VCPU_STAT("halt_wakeup", halt_wakeup),
VCPU_STAT("doorbell", dbell_exits),
VCPU_STAT("guest doorbell", gdbell_exits),
VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
VM_STAT("remote_tlb_flush", remote_tlb_flush),
{ NULL }
};

5
arch/powerpc/kvm/powerpc.c
View File

@ -752,7 +752,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
if (err)
goto out_vcpu_uninit;
vcpu->arch.wqp = &vcpu->wq;
vcpu->arch.waitp = &vcpu->wait;
kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id);
return 0;
@ -1765,8 +1765,9 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
return r;
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
int r;
vcpu_load(vcpu);

6
arch/s390/include/asm/kvm_host.h
View File

@ -375,6 +375,8 @@ struct kvm_vcpu_stat {
u64 halt_poll_invalid;
u64 halt_no_poll_steal;
u64 halt_wakeup;
u64 halt_poll_success_ns;
u64 halt_poll_fail_ns;
u64 instruction_lctl;
u64 instruction_lctlg;
u64 instruction_stctl;
@ -971,7 +973,7 @@ struct kvm_arch_async_pf {
unsigned long pfault_token;
};
bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
@ -982,6 +984,8 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
static inline void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) {}
void kvm_arch_crypto_clear_masks(struct kvm *kvm);
void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm,
unsigned long *aqm, unsigned long *adm);

2
arch/s390/kvm/interrupt.c
View File

@ -3082,7 +3082,7 @@ static enum hrtimer_restart gisa_vcpu_kicker(struct hrtimer *timer)
__airqs_kick_single_vcpu(kvm, pending_mask);
hrtimer_forward_now(timer, ns_to_ktime(gi->expires));
return HRTIMER_RESTART;
};
}
return HRTIMER_NORESTART;
}

210
arch/s390/kvm/kvm-s390.c
View File

@ -57,110 +57,109 @@
#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
(KVM_MAX_VCPUS + LOCAL_IRQS))
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "userspace_handled", VCPU_STAT(exit_userspace) },
{ "exit_null", VCPU_STAT(exit_null) },
{ "exit_validity", VCPU_STAT(exit_validity) },
{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
{ "exit_external_request", VCPU_STAT(exit_external_request) },
{ "exit_io_request", VCPU_STAT(exit_io_request) },
{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
{ "exit_instruction", VCPU_STAT(exit_instruction) },
{ "exit_pei", VCPU_STAT(exit_pei) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
{ "exit_operation_exception", VCPU_STAT(exit_operation_exception) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
{ "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
{ "deliver_ckc", VCPU_STAT(deliver_ckc) },
{ "deliver_cputm", VCPU_STAT(deliver_cputm) },
{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
{ "deliver_virtio", VCPU_STAT(deliver_virtio) },
{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
{ "deliver_program", VCPU_STAT(deliver_program) },
{ "deliver_io", VCPU_STAT(deliver_io) },
{ "deliver_machine_check", VCPU_STAT(deliver_machine_check) },
{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
{ "inject_ckc", VCPU_STAT(inject_ckc) },
{ "inject_cputm", VCPU_STAT(inject_cputm) },
{ "inject_external_call", VCPU_STAT(inject_external_call) },
{ "inject_float_mchk", VM_STAT(inject_float_mchk) },
{ "inject_emergency_signal", VCPU_STAT(inject_emergency_signal) },
{ "inject_io", VM_STAT(inject_io) },
{ "inject_mchk", VCPU_STAT(inject_mchk) },
{ "inject_pfault_done", VM_STAT(inject_pfault_done) },
{ "inject_program", VCPU_STAT(inject_program) },
{ "inject_restart", VCPU_STAT(inject_restart) },
{ "inject_service_signal", VM_STAT(inject_service_signal) },
{ "inject_set_prefix", VCPU_STAT(inject_set_prefix) },
{ "inject_stop_signal", VCPU_STAT(inject_stop_signal) },
{ "inject_pfault_init", VCPU_STAT(inject_pfault_init) },
{ "inject_virtio", VM_STAT(inject_virtio) },
{ "instruction_epsw", VCPU_STAT(instruction_epsw) },
{ "instruction_gs", VCPU_STAT(instruction_gs) },
{ "instruction_io_other", VCPU_STAT(instruction_io_other) },
{ "instruction_lpsw", VCPU_STAT(instruction_lpsw) },
{ "instruction_lpswe", VCPU_STAT(instruction_lpswe) },
{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
{ "instruction_ptff", VCPU_STAT(instruction_ptff) },
{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
{ "instruction_sck", VCPU_STAT(instruction_sck) },
{ "instruction_sckpf", VCPU_STAT(instruction_sckpf) },
{ "instruction_spx", VCPU_STAT(instruction_spx) },
{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
{ "instruction_stap", VCPU_STAT(instruction_stap) },
{ "instruction_iske", VCPU_STAT(instruction_iske) },
{ "instruction_ri", VCPU_STAT(instruction_ri) },
{ "instruction_rrbe", VCPU_STAT(instruction_rrbe) },
{ "instruction_sske", VCPU_STAT(instruction_sske) },
{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
{ "instruction_essa", VCPU_STAT(instruction_essa) },
{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
{ "instruction_tb", VCPU_STAT(instruction_tb) },
{ "instruction_tpi", VCPU_STAT(instruction_tpi) },
{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
{ "instruction_tsch", VCPU_STAT(instruction_tsch) },
{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
{ "instruction_sie", VCPU_STAT(instruction_sie) },
{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
{ "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
{ "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
{ "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
{ "instruction_diag_10", VCPU_STAT(diagnose_10) },
{ "instruction_diag_44", VCPU_STAT(diagnose_44) },
{ "instruction_diag_9c", VCPU_STAT(diagnose_9c) },
{ "diag_9c_ignored", VCPU_STAT(diagnose_9c_ignored) },
{ "instruction_diag_258", VCPU_STAT(diagnose_258) },
{ "instruction_diag_308", VCPU_STAT(diagnose_308) },
{ "instruction_diag_500", VCPU_STAT(diagnose_500) },
{ "instruction_diag_other", VCPU_STAT(diagnose_other) },
VCPU_STAT("userspace_handled", exit_userspace),
VCPU_STAT("exit_null", exit_null),
VCPU_STAT("exit_validity", exit_validity),
VCPU_STAT("exit_stop_request", exit_stop_request),
VCPU_STAT("exit_external_request", exit_external_request),
VCPU_STAT("exit_io_request", exit_io_request),
VCPU_STAT("exit_external_interrupt", exit_external_interrupt),
VCPU_STAT("exit_instruction", exit_instruction),
VCPU_STAT("exit_pei", exit_pei),
VCPU_STAT("exit_program_interruption", exit_program_interruption),
VCPU_STAT("exit_instr_and_program_int", exit_instr_and_program),
VCPU_STAT("exit_operation_exception", exit_operation_exception),
VCPU_STAT("halt_successful_poll", halt_successful_poll),
VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
VCPU_STAT("halt_no_poll_steal", halt_no_poll_steal),
VCPU_STAT("halt_wakeup", halt_wakeup),
VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
VCPU_STAT("instruction_lctlg", instruction_lctlg),
VCPU_STAT("instruction_lctl", instruction_lctl),
VCPU_STAT("instruction_stctl", instruction_stctl),
VCPU_STAT("instruction_stctg", instruction_stctg),
VCPU_STAT("deliver_ckc", deliver_ckc),
VCPU_STAT("deliver_cputm", deliver_cputm),
VCPU_STAT("deliver_emergency_signal", deliver_emergency_signal),
VCPU_STAT("deliver_external_call", deliver_external_call),
VCPU_STAT("deliver_service_signal", deliver_service_signal),
VCPU_STAT("deliver_virtio", deliver_virtio),
VCPU_STAT("deliver_stop_signal", deliver_stop_signal),
VCPU_STAT("deliver_prefix_signal", deliver_prefix_signal),
VCPU_STAT("deliver_restart_signal", deliver_restart_signal),
VCPU_STAT("deliver_program", deliver_program),
VCPU_STAT("deliver_io", deliver_io),
VCPU_STAT("deliver_machine_check", deliver_machine_check),
VCPU_STAT("exit_wait_state", exit_wait_state),
VCPU_STAT("inject_ckc", inject_ckc),
VCPU_STAT("inject_cputm", inject_cputm),
VCPU_STAT("inject_external_call", inject_external_call),
VM_STAT("inject_float_mchk", inject_float_mchk),
VCPU_STAT("inject_emergency_signal", inject_emergency_signal),
VM_STAT("inject_io", inject_io),
VCPU_STAT("inject_mchk", inject_mchk),
VM_STAT("inject_pfault_done", inject_pfault_done),
VCPU_STAT("inject_program", inject_program),
VCPU_STAT("inject_restart", inject_restart),
VM_STAT("inject_service_signal", inject_service_signal),
VCPU_STAT("inject_set_prefix", inject_set_prefix),
VCPU_STAT("inject_stop_signal", inject_stop_signal),
VCPU_STAT("inject_pfault_init", inject_pfault_init),
VM_STAT("inject_virtio", inject_virtio),
VCPU_STAT("instruction_epsw", instruction_epsw),
VCPU_STAT("instruction_gs", instruction_gs),
VCPU_STAT("instruction_io_other", instruction_io_other),
VCPU_STAT("instruction_lpsw", instruction_lpsw),
VCPU_STAT("instruction_lpswe", instruction_lpswe),
VCPU_STAT("instruction_pfmf", instruction_pfmf),
VCPU_STAT("instruction_ptff", instruction_ptff),
VCPU_STAT("instruction_stidp", instruction_stidp),
VCPU_STAT("instruction_sck", instruction_sck),
VCPU_STAT("instruction_sckpf", instruction_sckpf),
VCPU_STAT("instruction_spx", instruction_spx),
VCPU_STAT("instruction_stpx", instruction_stpx),
VCPU_STAT("instruction_stap", instruction_stap),
VCPU_STAT("instruction_iske", instruction_iske),
VCPU_STAT("instruction_ri", instruction_ri),
VCPU_STAT("instruction_rrbe", instruction_rrbe),
VCPU_STAT("instruction_sske", instruction_sske),
VCPU_STAT("instruction_ipte_interlock", instruction_ipte_interlock),
VCPU_STAT("instruction_essa", instruction_essa),
VCPU_STAT("instruction_stsi", instruction_stsi),
VCPU_STAT("instruction_stfl", instruction_stfl),
VCPU_STAT("instruction_tb", instruction_tb),
VCPU_STAT("instruction_tpi", instruction_tpi),
VCPU_STAT("instruction_tprot", instruction_tprot),
VCPU_STAT("instruction_tsch", instruction_tsch),
VCPU_STAT("instruction_sthyi", instruction_sthyi),
VCPU_STAT("instruction_sie", instruction_sie),
VCPU_STAT("instruction_sigp_sense", instruction_sigp_sense),
VCPU_STAT("instruction_sigp_sense_running", instruction_sigp_sense_running),
VCPU_STAT("instruction_sigp_external_call", instruction_sigp_external_call),
VCPU_STAT("instruction_sigp_emergency", instruction_sigp_emergency),
VCPU_STAT("instruction_sigp_cond_emergency", instruction_sigp_cond_emergency),
VCPU_STAT("instruction_sigp_start", instruction_sigp_start),
VCPU_STAT("instruction_sigp_stop", instruction_sigp_stop),
VCPU_STAT("instruction_sigp_stop_store_status", instruction_sigp_stop_store_status),
VCPU_STAT("instruction_sigp_store_status", instruction_sigp_store_status),
VCPU_STAT("instruction_sigp_store_adtl_status", instruction_sigp_store_adtl_status),
VCPU_STAT("instruction_sigp_set_arch", instruction_sigp_arch),
VCPU_STAT("instruction_sigp_set_prefix", instruction_sigp_prefix),
VCPU_STAT("instruction_sigp_restart", instruction_sigp_restart),
VCPU_STAT("instruction_sigp_cpu_reset", instruction_sigp_cpu_reset),
VCPU_STAT("instruction_sigp_init_cpu_reset", instruction_sigp_init_cpu_reset),
VCPU_STAT("instruction_sigp_unknown", instruction_sigp_unknown),
VCPU_STAT("instruction_diag_10", diagnose_10),
VCPU_STAT("instruction_diag_44", diagnose_44),
VCPU_STAT("instruction_diag_9c", diagnose_9c),
VCPU_STAT("diag_9c_ignored", diagnose_9c_ignored),
VCPU_STAT("instruction_diag_258", diagnose_258),
VCPU_STAT("instruction_diag_308", diagnose_308),
VCPU_STAT("instruction_diag_500", diagnose_500),
VCPU_STAT("instruction_diag_other", diagnose_other),
{ NULL }
};
@ -3944,7 +3943,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
/* s390 will always inject the page directly */
}
bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
{
/*
* s390 will always inject the page directly,
@ -4337,8 +4336,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
store_regs_fmt2(vcpu, kvm_run);
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_run *kvm_run = vcpu->run;
int rc;
if (kvm_run->immediate_exit)

3
arch/s390/kvm/vsie.c
View File

@ -1000,8 +1000,6 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
handle_last_fault(vcpu, vsie_page);
if (need_resched())
schedule();
if (test_cpu_flag(CIF_MCCK_PENDING))
s390_handle_mcck();
@ -1185,6 +1183,7 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
kvm_s390_vcpu_has_irq(vcpu, 0) ||
kvm_s390_vcpu_sie_inhibited(vcpu))
break;
cond_resched();
}
if (rc == -EFAULT) {

10
arch/s390/mm/gmap.c
View File

@ -788,19 +788,19 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
unsigned long gaddr, int level)
{
const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
unsigned long *table;
unsigned long *table = gmap->table;
if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
return NULL;
if (gmap_is_shadow(gmap) && gmap->removed)
return NULL;
if (WARN_ON_ONCE(level > (asce_type >> 2) + 1))
return NULL;
if (asce_type != _ASCE_TYPE_REGION1 &&
gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
return NULL;
table = gmap->table;
switch (gmap->asce & _ASCE_TYPE_MASK) {
switch (asce_type) {
case _ASCE_TYPE_REGION1:
table += (gaddr & _REGION1_INDEX) >> _REGION1_SHIFT;
if (level == 4)

8
arch/x86/entry/entry_32.S
View File

@ -1691,14 +1691,6 @@ SYM_CODE_START(general_protection)
jmp common_exception
SYM_CODE_END(general_protection)
#ifdef CONFIG_KVM_GUEST
SYM_CODE_START(async_page_fault)
ASM_CLAC
pushl $do_async_page_fault
jmp common_exception_read_cr2
SYM_CODE_END(async_page_fault)
#endif
SYM_CODE_START(rewind_stack_do_exit)
/* Prevent any naive code from trying to unwind to our caller. */
xorl %ebp, %ebp

4
arch/x86/entry/entry_64.S
View File

@ -1202,10 +1202,6 @@ idtentry xendebug do_debug has_error_code=0
idtentry general_protection do_general_protection has_error_code=1
idtentry page_fault do_page_fault has_error_code=1 read_cr2=1
#ifdef CONFIG_KVM_GUEST
idtentry async_page_fault do_async_page_fault has_error_code=1 read_cr2=1
#endif
#ifdef CONFIG_X86_MCE
idtentry machine_check do_mce has_error_code=0 paranoid=1
#endif

2
arch/x86/include/asm/hyperv-tlfs.h
View File

@ -83,6 +83,8 @@
#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8)
/* Crash MSR available */
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
/* Support for debug MSRs available */
#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11)
/* stimer Direct Mode is available */
#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19)

134
arch/x86/include/asm/kvm_host.h
View File

@ -83,6 +83,10 @@
#define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24)
#define KVM_REQ_APICV_UPDATE \
KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26)
#define KVM_REQ_HV_TLB_FLUSH \
KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_APF_READY KVM_ARCH_REQ(28)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@ -107,15 +111,8 @@
#define UNMAPPED_GVA (~(gpa_t)0)
/* KVM Hugepage definitions for x86 */
enum {
PT_PAGE_TABLE_LEVEL = 1,
PT_DIRECTORY_LEVEL = 2,
PT_PDPE_LEVEL = 3,
/* set max level to the biggest one */
PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL,
};
#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \
PT_PAGE_TABLE_LEVEL + 1)
#define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G
#define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1)
#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9)
#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
@ -124,7 +121,7 @@ enum {
static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
{
/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
/* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */
return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
}
@ -164,9 +161,13 @@ enum kvm_reg {
NR_VCPU_REGS,
VCPU_EXREG_PDPTR = NR_VCPU_REGS,
VCPU_EXREG_CR0,
VCPU_EXREG_CR3,
VCPU_EXREG_CR4,
VCPU_EXREG_RFLAGS,
VCPU_EXREG_SEGMENTS,
VCPU_EXREG_EXIT_INFO_1,
VCPU_EXREG_EXIT_INFO_2,
};
enum {
@ -182,8 +183,10 @@ enum {
enum exit_fastpath_completion {
EXIT_FASTPATH_NONE,
EXIT_FASTPATH_SKIP_EMUL_INS,
EXIT_FASTPATH_REENTER_GUEST,
EXIT_FASTPATH_EXIT_HANDLED,
};
typedef enum exit_fastpath_completion fastpath_t;
struct x86_emulate_ctxt;
struct x86_exception;
@ -372,12 +375,12 @@ struct rsvd_bits_validate {
};
struct kvm_mmu_root_info {
gpa_t cr3;
gpa_t pgd;
hpa_t hpa;
};
#define KVM_MMU_ROOT_INFO_INVALID \
((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE })
((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE })
#define KVM_MMU_NUM_PREV_ROOTS 3
@ -403,7 +406,7 @@ struct kvm_mmu {
void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
u64 *spte, const void *pte);
hpa_t root_hpa;
gpa_t root_cr3;
gpa_t root_pgd;
union kvm_mmu_role mmu_role;
u8 root_level;
u8 shadow_root_level;
@ -598,6 +601,7 @@ struct kvm_vcpu_arch {
u64 ia32_xss;
u64 microcode_version;
u64 arch_capabilities;
u64 perf_capabilities;
/*
* Paging state of the vcpu
@ -650,7 +654,6 @@ struct kvm_vcpu_arch {
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
struct kvm_pio_request pio;
void *pio_data;
@ -680,6 +683,7 @@ struct kvm_vcpu_arch {
struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
int maxphyaddr;
int tdp_level;
/* emulate context */
@ -703,6 +707,7 @@ struct kvm_vcpu_arch {
struct gfn_to_pfn_cache cache;
} st;
u64 l1_tsc_offset;
u64 tsc_offset;
u64 last_guest_tsc;
u64 last_host_tsc;
@ -762,14 +767,17 @@ struct kvm_vcpu_arch {
struct {
bool halted;
gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
gfn_t gfns[ASYNC_PF_PER_VCPU];
struct gfn_to_hva_cache data;
u64 msr_val;
u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */
u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
u16 vec;
u32 id;
bool send_user_only;
u32 host_apf_reason;
u32 host_apf_flags;
unsigned long nested_apf_token;
bool delivery_as_pf_vmexit;
bool pageready_pending;
} apf;
/* OSVW MSRs (AMD only) */
@ -855,6 +863,18 @@ struct kvm_apic_map {
struct kvm_lapic *phys_map[];
};
/* Hyper-V synthetic debugger (SynDbg)*/
struct kvm_hv_syndbg {
struct {
u64 control;
u64 status;
u64 send_page;
u64 recv_page;
u64 pending_page;
} control;
u64 options;
};
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
@ -878,6 +898,7 @@ struct kvm_hv {
atomic_t num_mismatched_vp_indexes;
struct hv_partition_assist_pg *hv_pa_pg;
struct kvm_hv_syndbg hv_syndbg;
};
enum kvm_irqchip_mode {
@ -1028,6 +1049,8 @@ struct kvm_vcpu_stat {
u64 irq_injections;
u64 nmi_injections;
u64 req_event;
u64 halt_poll_success_ns;
u64 halt_poll_fail_ns;
};
struct x86_instruction_info;
@ -1059,7 +1082,7 @@ struct kvm_x86_ops {
void (*hardware_disable)(void);
void (*hardware_unsetup)(void);
bool (*cpu_has_accelerated_tpr)(void);
bool (*has_emulated_msr)(int index);
bool (*has_emulated_msr)(u32 index);
void (*cpuid_update)(struct kvm_vcpu *vcpu);
unsigned int vm_size;
@ -1085,8 +1108,6 @@ struct kvm_x86_ops {
void (*set_segment)(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg);
void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
@ -1100,7 +1121,8 @@ struct kvm_x86_ops {
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
int (*tlb_remote_flush)(struct kvm *kvm);
int (*tlb_remote_flush_with_range)(struct kvm *kvm,
struct kvm_tlb_range *range);
@ -1113,7 +1135,13 @@ struct kvm_x86_ops {
*/
void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
void (*run)(struct kvm_vcpu *vcpu);
/*
* Flush any TLB entries created by the guest. Like tlb_flush_gva(),
* does not need to flush GPA->HPA mappings.
*/
void (*tlb_flush_guest)(struct kvm_vcpu *vcpu);
enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
@ -1126,8 +1154,8 @@ struct kvm_x86_ops {
void (*set_nmi)(struct kvm_vcpu *vcpu);
void (*queue_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
int (*nmi_allowed)(struct kvm_vcpu *vcpu);
int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
@ -1141,7 +1169,7 @@ struct kvm_x86_ops {
bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
@ -1153,7 +1181,6 @@ struct kvm_x86_ops {
bool (*has_wbinvd_exit)(void);
u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
/* Returns actual tsc_offset set in active VMCS */
u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
@ -1163,10 +1190,8 @@ struct kvm_x86_ops {
struct x86_instruction_info *info,
enum x86_intercept_stage stage,
struct x86_exception *exception);
void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion *exit_fastpath);
void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
int (*check_nested_events)(struct kvm_vcpu *vcpu);
void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@ -1199,6 +1224,7 @@ struct kvm_x86_ops {
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
const struct kvm_x86_nested_ops *nested_ops;
/*
* Architecture specific hooks for vCPU blocking due to
@ -1226,18 +1252,10 @@ struct kvm_x86_ops {
void (*setup_mce)(struct kvm_vcpu *vcpu);
int (*get_nested_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
unsigned user_data_size);
int (*set_nested_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
struct kvm_nested_state *kvm_state);
bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
@ -1245,14 +1263,28 @@ struct kvm_x86_ops {
int (*get_msr_feature)(struct kvm_msr_entry *entry);
int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
void (*migrate_timers)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_nested_ops {
int (*check_events)(struct kvm_vcpu *vcpu);
bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
int (*get_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
unsigned user_data_size);
int (*set_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
struct kvm_nested_state *kvm_state);
bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
int (*enable_evmcs)(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_init_ops {
@ -1451,6 +1483,8 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault);
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t gfn, void *data, int offset, int len,
u32 access);
@ -1478,6 +1512,8 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
void kvm_update_dr7(struct kvm_vcpu *vcpu);
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
@ -1508,8 +1544,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gva_t gva, hpa_t root_hpa);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush);
void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush,
bool skip_mmu_sync);
void kvm_configure_mmu(bool enable_tdp, int tdp_page_level);
@ -1573,8 +1612,6 @@ enum {
};
#define HF_GIF_MASK (1 << 0)
#define HF_HIF_MASK (1 << 1)
#define HF_VINTR_MASK (1 << 2)
#define HF_NMI_MASK (1 << 3)
#define HF_IRET_MASK (1 << 4)
#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
@ -1640,7 +1677,8 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu);
bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);

27
arch/x86/include/asm/kvm_para.h
View File

@ -88,11 +88,21 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
bool kvm_para_available(void);
unsigned int kvm_arch_para_features(void);
unsigned int kvm_arch_para_hints(void);
void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
void kvm_async_pf_task_wait_schedule(u32 token);
void kvm_async_pf_task_wake(u32 token);
u32 kvm_read_and_reset_pf_reason(void);
extern void kvm_disable_steal_time(void);
void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
u32 kvm_read_and_reset_apf_flags(void);
void kvm_disable_steal_time(void);
bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token);
DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
{
if (static_branch_unlikely(&kvm_async_pf_enabled))
return __kvm_handle_async_pf(regs, token);
else
return false;
}
#ifdef CONFIG_PARAVIRT_SPINLOCKS
void __init kvm_spinlock_init(void);
@ -103,7 +113,7 @@ static inline void kvm_spinlock_init(void)
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
#else /* CONFIG_KVM_GUEST */
#define kvm_async_pf_task_wait(T, I) do {} while(0)
#define kvm_async_pf_task_wait_schedule(T) do {} while(0)
#define kvm_async_pf_task_wake(T) do {} while(0)
static inline bool kvm_para_available(void)
@ -121,7 +131,7 @@ static inline unsigned int kvm_arch_para_hints(void)
return 0;
}
static inline u32 kvm_read_and_reset_pf_reason(void)
static inline u32 kvm_read_and_reset_apf_flags(void)
{
return 0;
}
@ -130,6 +140,11 @@ static inline void kvm_disable_steal_time(void)
{
return;
}
static inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
{
return false;
}
#endif
#endif /* _ASM_X86_KVM_PARA_H */

9
arch/x86/include/asm/svm.h
View File

@ -96,7 +96,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
u8 reserved_6[8]; /* Offset 0xe8 */
u64 avic_logical_id; /* Offset 0xf0 */
u64 avic_physical_id; /* Offset 0xf8 */
u8 reserved_7[768];
};
@ -203,8 +202,16 @@ struct __attribute__ ((__packed__)) vmcb_save_area {
u64 last_excp_to;
};
static inline void __unused_size_checks(void)
{
BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298);
BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256);
}
struct __attribute__ ((__packed__)) vmcb {
struct vmcb_control_area control;
u8 reserved_control[1024 - sizeof(struct vmcb_control_area)];
struct vmcb_save_area save;
};

10
arch/x86/include/asm/vmx.h
View File

@ -527,10 +527,12 @@ struct vmx_msr_entry {
/*
* Exit Qualifications for entry failure during or after loading guest state
*/
#define ENTRY_FAIL_DEFAULT 0
#define ENTRY_FAIL_PDPTE 2
#define ENTRY_FAIL_NMI 3
#define ENTRY_FAIL_VMCS_LINK_PTR 4
enum vm_entry_failure_code {
ENTRY_FAIL_DEFAULT = 0,
ENTRY_FAIL_PDPTE = 2,
ENTRY_FAIL_NMI = 3,
ENTRY_FAIL_VMCS_LINK_PTR = 4,
};
/*
* Exit Qualifications for EPT Violations

2
arch/x86/include/asm/x86_init.h
View File

@ -50,14 +50,12 @@ struct x86_init_resources {
* @pre_vector_init: init code to run before interrupt vectors
* are set up.
* @intr_init: interrupt init code
* @trap_init: platform specific trap setup
* @intr_mode_select: interrupt delivery mode selection
* @intr_mode_init: interrupt delivery mode setup
*/
struct x86_init_irqs {
void (*pre_vector_init)(void);
void (*intr_init)(void);
void (*trap_init)(void);
void (*intr_mode_select)(void);
void (*intr_mode_init)(void);
};

20
arch/x86/include/uapi/asm/kvm.h
View File

@ -385,32 +385,48 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
#define KVM_STATE_NESTED_FORMAT_SVM 1
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
#define KVM_STATE_NESTED_MTF_PENDING 0x00000008
#define KVM_STATE_NESTED_GIF_SET 0x00000100
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
#define KVM_STATE_NESTED_SVM_VMCB_SIZE 0x1000
#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
struct kvm_vmx_nested_state_data {
__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
};
struct kvm_vmx_nested_state_hdr {
__u32 flags;
__u64 vmxon_pa;
__u64 vmcs12_pa;
__u64 preemption_timer_deadline;
struct {
__u16 flags;
} smm;
};
struct kvm_svm_nested_state_data {
/* Save area only used if KVM_STATE_NESTED_RUN_PENDING. */
__u8 vmcb12[KVM_STATE_NESTED_SVM_VMCB_SIZE];
};
struct kvm_svm_nested_state_hdr {
__u64 vmcb_pa;
};
/* for KVM_CAP_NESTED_STATE */
struct kvm_nested_state {
__u16 flags;
@ -419,6 +435,7 @@ struct kvm_nested_state {
union {
struct kvm_vmx_nested_state_hdr vmx;
struct kvm_svm_nested_state_hdr svm;
/* Pad the header to 128 bytes. */
__u8 pad[120];
@ -431,6 +448,7 @@ struct kvm_nested_state {
*/
union {
struct kvm_vmx_nested_state_data vmx[0];
struct kvm_svm_nested_state_data svm[0];
} data;
};

17
arch/x86/include/uapi/asm/kvm_para.h
View File

@ -31,6 +31,7 @@
#define KVM_FEATURE_PV_SEND_IPI 11
#define KVM_FEATURE_POLL_CONTROL 12
#define KVM_FEATURE_PV_SCHED_YIELD 13
#define KVM_FEATURE_ASYNC_PF_INT 14
#define KVM_HINTS_REALTIME 0
@ -50,6 +51,8 @@
#define MSR_KVM_STEAL_TIME 0x4b564d03
#define MSR_KVM_PV_EOI_EN 0x4b564d04
#define MSR_KVM_POLL_CONTROL 0x4b564d05
#define MSR_KVM_ASYNC_PF_INT 0x4b564d06
#define MSR_KVM_ASYNC_PF_ACK 0x4b564d07
struct kvm_steal_time {
__u64 steal;
@ -81,6 +84,11 @@ struct kvm_clock_pairing {
#define KVM_ASYNC_PF_ENABLED (1 << 0)
#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
#define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT (1 << 2)
#define KVM_ASYNC_PF_DELIVERY_AS_INT (1 << 3)
/* MSR_KVM_ASYNC_PF_INT */
#define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0)
/* Operations for KVM_HC_MMU_OP */
#define KVM_MMU_OP_WRITE_PTE 1
@ -112,8 +120,13 @@ struct kvm_mmu_op_release_pt {
#define KVM_PV_REASON_PAGE_READY 2
struct kvm_vcpu_pv_apf_data {
__u32 reason;
__u8 pad[60];
/* Used for 'page not present' events delivered via #PF */
__u32 flags;
/* Used for 'page ready' events delivered via interrupt notification */
__u32 token;
__u8 pad[56];
__u32 enabled;
};

3
arch/x86/include/uapi/asm/vmx.h
View File

@ -150,6 +150,9 @@
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4

174
arch/x86/kernel/kvm.c
View File

@ -35,6 +35,8 @@
#include <asm/tlb.h>
#include <asm/cpuidle_haltpoll.h>
DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
static int kvmapf = 1;
static int __init parse_no_kvmapf(char *arg)
@ -73,7 +75,6 @@ struct kvm_task_sleep_node {
struct swait_queue_head wq;
u32 token;
int cpu;
bool halted;
};
static struct kvm_task_sleep_head {
@ -96,77 +97,64 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
return NULL;
}
/*
* @interrupt_kernel: Is this called from a routine which interrupts the kernel
* (other than user space)?
*/
void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
{
u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
struct kvm_task_sleep_node n, *e;
DECLARE_SWAITQUEUE(wait);
rcu_irq_enter();
struct kvm_task_sleep_node *e;
raw_spin_lock(&b->lock);
e = _find_apf_task(b, token);
if (e) {
/* dummy entry exist -> wake up was delivered ahead of PF */
hlist_del(&e->link);
kfree(e);
raw_spin_unlock(&b->lock);
rcu_irq_exit();
return;
kfree(e);
return false;
}
n.token = token;
n.cpu = smp_processor_id();
n.halted = is_idle_task(current) ||
(IS_ENABLED(CONFIG_PREEMPT_COUNT)
? preempt_count() > 1 || rcu_preempt_depth()
: interrupt_kernel);
init_swait_queue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
n->token = token;
n->cpu = smp_processor_id();
init_swait_queue_head(&n->wq);
hlist_add_head(&n->link, &b->list);
raw_spin_unlock(&b->lock);
return true;
}
/*
* kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled
* @token: Token to identify the sleep node entry
*
* Invoked from the async pagefault handling code or from the VM exit page
* fault handler. In both cases RCU is watching.
*/
void kvm_async_pf_task_wait_schedule(u32 token)
{
struct kvm_task_sleep_node n;
DECLARE_SWAITQUEUE(wait);
lockdep_assert_irqs_disabled();
if (!kvm_async_pf_queue_task(token, &n))
return;
for (;;) {
if (!n.halted)
prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
if (hlist_unhashed(&n.link))
break;
rcu_irq_exit();
if (!n.halted) {
local_irq_enable();
schedule();
local_irq_disable();
} else {
/*
* We cannot reschedule. So halt.
*/
native_safe_halt();
local_irq_disable();
}
rcu_irq_enter();
local_irq_enable();
schedule();
local_irq_disable();
}
if (!n.halted)
finish_swait(&n.wq, &wait);
rcu_irq_exit();
return;
finish_swait(&n.wq, &wait);
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule);
static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
hlist_del_init(&n->link);
if (n->halted)
smp_send_reschedule(n->cpu);
else if (swq_has_sleeper(&n->wq))
if (swq_has_sleeper(&n->wq))
swake_up_one(&n->wq);
}
@ -175,12 +163,13 @@ static void apf_task_wake_all(void)
int i;
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
struct hlist_node *p, *next;
struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
struct kvm_task_sleep_node *n;
struct hlist_node *p, *next;
raw_spin_lock(&b->lock);
hlist_for_each_safe(p, next, &b->list) {
struct kvm_task_sleep_node *n =
hlist_entry(p, typeof(*n), link);
n = hlist_entry(p, typeof(*n), link);
if (n->cpu == smp_processor_id())
apf_task_wake_one(n);
}
@ -221,46 +210,61 @@ again:
n->cpu = smp_processor_id();
init_swait_queue_head(&n->wq);
hlist_add_head(&n->link, &b->list);
} else
} else {
apf_task_wake_one(n);
}
raw_spin_unlock(&b->lock);
return;
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
u32 kvm_read_and_reset_pf_reason(void)
u32 kvm_read_and_reset_apf_flags(void)
{
u32 reason = 0;
u32 flags = 0;
if (__this_cpu_read(apf_reason.enabled)) {
reason = __this_cpu_read(apf_reason.reason);
__this_cpu_write(apf_reason.reason, 0);
flags = __this_cpu_read(apf_reason.flags);
__this_cpu_write(apf_reason.flags, 0);
}
return reason;
return flags;
}
EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason);
EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
NOKPROBE_SYMBOL(kvm_read_and_reset_apf_flags);
dotraplinkage void
do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address)
bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
{
switch (kvm_read_and_reset_pf_reason()) {
default:
do_page_fault(regs, error_code, address);
break;
u32 reason = kvm_read_and_reset_apf_flags();
switch (reason) {
case KVM_PV_REASON_PAGE_NOT_PRESENT:
/* page is swapped out by the host. */
kvm_async_pf_task_wait((u32)address, !user_mode(regs));
break;
case KVM_PV_REASON_PAGE_READY:
rcu_irq_enter();
kvm_async_pf_task_wake((u32)address);
rcu_irq_exit();
break;
default:
return false;
}
/*
* If the host managed to inject an async #PF into an interrupt
* disabled region, then die hard as this is not going to end well
* and the host side is seriously broken.
*/
if (unlikely(!(regs->flags & X86_EFLAGS_IF)))
panic("Host injected async #PF in interrupt disabled region\n");
if (reason == KVM_PV_REASON_PAGE_NOT_PRESENT) {
if (unlikely(!(user_mode(regs))))
panic("Host injected async #PF in kernel mode\n");
/* Page is swapped out by the host. */
kvm_async_pf_task_wait_schedule(token);
} else {
rcu_irq_enter();
kvm_async_pf_task_wake(token);
rcu_irq_exit();
}
return true;
}
NOKPROBE_SYMBOL(do_async_page_fault);
NOKPROBE_SYMBOL(__kvm_handle_async_pf);
static void __init paravirt_ops_setup(void)
{
@ -306,11 +310,11 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
static void kvm_guest_cpu_init(void)
{
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
u64 pa;
#ifdef CONFIG_PREEMPTION
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled));
pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
pa |= KVM_ASYNC_PF_ENABLED;
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
@ -318,12 +322,12 @@ static void kvm_guest_cpu_init(void)
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
__this_cpu_write(apf_reason.enabled, 1);
printk(KERN_INFO"KVM setup async PF for cpu %d\n",
smp_processor_id());
pr_info("KVM setup async PF for cpu %d\n", smp_processor_id());
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) {
unsigned long pa;
/* Size alignment is implied but just to make it explicit. */
BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
__this_cpu_write(kvm_apic_eoi, 0);
@ -344,8 +348,7 @@ static void kvm_pv_disable_apf(void)
wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
__this_cpu_write(apf_reason.enabled, 0);
printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
smp_processor_id());
pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id());
}
static void kvm_pv_guest_cpu_reboot(void *unused)
@ -592,12 +595,6 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
}
#endif
static void __init kvm_apf_trap_init(void)
{
update_intr_gate(X86_TRAP_PF, async_page_fault);
}
static void kvm_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
@ -632,8 +629,6 @@ static void __init kvm_guest_init(void)
register_reboot_notifier(&kvm_pv_reboot_nb);
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
raw_spin_lock_init(&async_pf_sleepers[i].lock);
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
x86_init.irqs.trap_init = kvm_apf_trap_init;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
@ -649,6 +644,9 @@ static void __init kvm_guest_init(void)
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf)
static_branch_enable(&kvm_async_pf_enabled);
#ifdef CONFIG_SMP
smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;

2
arch/x86/kernel/traps.c
View File

@ -903,7 +903,5 @@ void __init trap_init(void)
idt_setup_ist_traps();
x86_init.irqs.trap_init();
idt_setup_debugidt_traps();
}

1
arch/x86/kernel/x86_init.c
View File

@ -79,7 +79,6 @@ struct x86_init_ops x86_init __initdata = {
.irqs = {
.pre_vector_init = init_ISA_irqs,
.intr_init = native_init_IRQ,
.trap_init = x86_init_noop,
.intr_mode_select = apic_intr_mode_select,
.intr_mode_init = apic_intr_mode_init
},

15
arch/x86/kvm/cpuid.c
View File

@ -86,12 +86,10 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
if (!best) {
vcpu->arch.guest_supported_xcr0 = 0;
vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
} else {
vcpu->arch.guest_supported_xcr0 =
(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
vcpu->arch.guest_xstate_size = best->ebx =
xstate_required_size(vcpu->arch.xcr0, false);
best->ebx = xstate_required_size(vcpu->arch.xcr0, false);
}
best = kvm_find_cpuid_entry(vcpu, 0xD, 1);
@ -124,8 +122,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
MSR_IA32_MISC_ENABLE_MWAIT);
}
/* Update physical-address width */
/* Note, maxphyaddr must be updated before tdp_level. */
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
vcpu->arch.tdp_level = kvm_x86_ops.get_tdp_level(vcpu);
kvm_mmu_reset_context(vcpu);
kvm_pmu_refresh(vcpu);
@ -297,7 +296,7 @@ void kvm_set_cpu_caps(void)
F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
0 /* DS-CPL, VMX, SMX, EST */ |
0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ |
F(FMA) | F(CX16) | 0 /* xTPR Update */ | F(PDCM) |
F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) |
F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
@ -712,7 +711,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
(1 << KVM_FEATURE_ASYNC_PF_VMEXIT) |
(1 << KVM_FEATURE_PV_SEND_IPI) |
(1 << KVM_FEATURE_POLL_CONTROL) |
(1 << KVM_FEATURE_PV_SCHED_YIELD);
(1 << KVM_FEATURE_PV_SCHED_YIELD) |
(1 << KVM_FEATURE_ASYNC_PF_INT);
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
@ -728,6 +728,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
cpuid_entry_override(entry, CPUID_8000_0001_EDX);
cpuid_entry_override(entry, CPUID_8000_0001_ECX);
break;
case 0x80000006:
/* L2 cache and TLB: pass through host info. */
break;
case 0x80000007: /* Advanced power management */
/* invariant TSC is CPUID.80000007H:EDX[8] */
entry->edx &= (1 << 8);

5
arch/x86/kvm/cpuid.h
View File

@ -303,4 +303,9 @@ static __always_inline void kvm_cpu_cap_check_and_set(unsigned int x86_feature)
kvm_cpu_cap_set(x86_feature);
}
static inline bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
{
return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
}
#endif

2
arch/x86/kvm/emulate.c
View File

@ -5798,6 +5798,8 @@ writeback:
}
ctxt->eip = ctxt->_eip;
if (ctxt->mode != X86EMUL_MODE_PROT64)
ctxt->eip = (u32)ctxt->_eip;
done:
if (rc == X86EMUL_PROPAGATE_FAULT) {

195
arch/x86/kvm/hyperv.c
View File

@ -21,6 +21,7 @@
#include "x86.h"
#include "lapic.h"
#include "ioapic.h"
#include "cpuid.h"
#include "hyperv.h"
#include <linux/cpu.h>
@ -266,6 +267,123 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
return ret;
}
static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *entry;
entry = kvm_find_cpuid_entry(vcpu,
HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES,
0);
if (!entry)
return false;
return entry->eax & HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING;
}
static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_hv *hv = &kvm->arch.hyperv;
if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL)
hv->hv_syndbg.control.status =
vcpu->run->hyperv.u.syndbg.status;
return 1;
}
static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr)
{
struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG;
hv_vcpu->exit.u.syndbg.msr = msr;
hv_vcpu->exit.u.syndbg.control = syndbg->control.control;
hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page;
hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page;
hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page;
vcpu->arch.complete_userspace_io =
kvm_hv_syndbg_complete_userspace;
kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
}
static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
{
struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
if (!kvm_hv_is_syndbg_enabled(vcpu) && !host)
return 1;
trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id,
vcpu_to_hv_vcpu(vcpu)->vp_index, msr, data);
switch (msr) {
case HV_X64_MSR_SYNDBG_CONTROL:
syndbg->control.control = data;
if (!host)
syndbg_exit(vcpu, msr);
break;
case HV_X64_MSR_SYNDBG_STATUS:
syndbg->control.status = data;
break;
case HV_X64_MSR_SYNDBG_SEND_BUFFER:
syndbg->control.send_page = data;
break;
case HV_X64_MSR_SYNDBG_RECV_BUFFER:
syndbg->control.recv_page = data;
break;
case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
syndbg->control.pending_page = data;
if (!host)
syndbg_exit(vcpu, msr);
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
syndbg->options = data;
break;
default:
break;
}
return 0;
}
static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
{
struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
if (!kvm_hv_is_syndbg_enabled(vcpu) && !host)
return 1;
switch (msr) {
case HV_X64_MSR_SYNDBG_CONTROL:
*pdata = syndbg->control.control;
break;
case HV_X64_MSR_SYNDBG_STATUS:
*pdata = syndbg->control.status;
break;
case HV_X64_MSR_SYNDBG_SEND_BUFFER:
*pdata = syndbg->control.send_page;
break;
case HV_X64_MSR_SYNDBG_RECV_BUFFER:
*pdata = syndbg->control.recv_page;
break;
case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
*pdata = syndbg->control.pending_page;
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
*pdata = syndbg->options;
break;
default:
break;
}
trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id,
vcpu_to_hv_vcpu(vcpu)->vp_index, msr,
*pdata);
return 0;
}
static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata,
bool host)
{
@ -800,6 +918,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
case HV_X64_MSR_TSC_EMULATION_CONTROL:
case HV_X64_MSR_TSC_EMULATION_STATUS:
case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
r = true;
break;
}
@ -1061,6 +1181,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
if (!host)
return 1;
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
return syndbg_set_msr(vcpu, msr, data, host);
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n",
msr, data);
@ -1190,7 +1313,8 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
return 0;
}
static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
bool host)
{
u64 data = 0;
struct kvm *kvm = vcpu->kvm;
@ -1227,6 +1351,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case HV_X64_MSR_TSC_EMULATION_STATUS:
data = hv->hv_tsc_emulation_status;
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
return syndbg_get_msr(vcpu, msr, pdata, host);
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
@ -1316,7 +1443,7 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
int r;
mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock);
r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host);
mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock);
return r;
} else
@ -1425,8 +1552,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
* vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
* analyze it here, flush TLB regardless of the specified address space.
*/
kvm_make_vcpus_request_mask(kvm,
KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH,
NULL, vcpu_mask, &hv_vcpu->tlb_flush);
ret_success:
@ -1530,7 +1656,7 @@ ret_success:
bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
return READ_ONCE(kvm->arch.hyperv.hv_guest_os_id) != 0;
}
static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
@ -1709,6 +1835,34 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
}
ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false);
break;
case HVCALL_POST_DEBUG_DATA:
case HVCALL_RETRIEVE_DEBUG_DATA:
if (unlikely(fast)) {
ret = HV_STATUS_INVALID_PARAMETER;
break;
}
fallthrough;
case HVCALL_RESET_DEBUG_SESSION: {
struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
if (!kvm_hv_is_syndbg_enabled(vcpu)) {
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
break;
}
if (!(syndbg->options & HV_X64_SYNDBG_OPTION_USE_HCALLS)) {
ret = HV_STATUS_OPERATION_DENIED;
break;
}
vcpu->run->exit_reason = KVM_EXIT_HYPERV;
vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
vcpu->run->hyperv.u.hcall.input = param;
vcpu->run->hyperv.u.hcall.params[0] = ingpa;
vcpu->run->hyperv.u.hcall.params[1] = outgpa;
vcpu->arch.complete_userspace_io =
kvm_hv_hypercall_complete_userspace;
return 0;
}
default:
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
break;
@ -1796,12 +1950,15 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
{ .function = HYPERV_CPUID_FEATURES },
{ .function = HYPERV_CPUID_ENLIGHTMENT_INFO },
{ .function = HYPERV_CPUID_IMPLEMENT_LIMITS },
{ .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS },
{ .function = HYPERV_CPUID_SYNDBG_INTERFACE },
{ .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES },
{ .function = HYPERV_CPUID_NESTED_FEATURES },
};
int i, nent = ARRAY_SIZE(cpuid_entries);
if (kvm_x86_ops.nested_get_evmcs_version)
evmcs_ver = kvm_x86_ops.nested_get_evmcs_version(vcpu);
if (kvm_x86_ops.nested_ops->get_evmcs_version)
evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu);
/* Skip NESTED_FEATURES if eVMCS is not supported */
if (!evmcs_ver)
@ -1821,7 +1978,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS:
memcpy(signature, "Linux KVM Hv", 12);
ent->eax = HYPERV_CPUID_NESTED_FEATURES;
ent->eax = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES;
ent->ebx = signature[0];
ent->ecx = signature[1];
ent->edx = signature[2];
@ -1860,6 +2017,10 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE;
ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
ent->ebx |= HV_DEBUGGING;
ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE;
ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE;
/*
* Direct Synthetic timers only make sense with in-kernel
* LAPIC
@ -1903,6 +2064,24 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
break;
case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS:
memcpy(signature, "Linux KVM Hv", 12);
ent->eax = 0;
ent->ebx = signature[0];
ent->ecx = signature[1];
ent->edx = signature[2];
break;
case HYPERV_CPUID_SYNDBG_INTERFACE:
memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12);
ent->eax = signature[0];
break;
case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES:
ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING;
break;
default:
break;
}

32
arch/x86/kvm/hyperv.h
View File

@ -23,6 +23,33 @@
#include <linux/kvm_host.h>
/*
* The #defines related to the synthetic debugger are required by KDNet, but
* they are not documented in the Hyper-V TLFS because the synthetic debugger
* functionality has been deprecated and is subject to removal in future
* versions of Windows.
*/
#define HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 0x40000080
#define HYPERV_CPUID_SYNDBG_INTERFACE 0x40000081
#define HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 0x40000082
/*
* Hyper-V synthetic debugger platform capabilities
* These are HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX bits.
*/
#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1)
/* Hyper-V Synthetic debug options MSR */
#define HV_X64_MSR_SYNDBG_CONTROL 0x400000F1
#define HV_X64_MSR_SYNDBG_STATUS 0x400000F2
#define HV_X64_MSR_SYNDBG_SEND_BUFFER 0x400000F3
#define HV_X64_MSR_SYNDBG_RECV_BUFFER 0x400000F4
#define HV_X64_MSR_SYNDBG_PENDING_BUFFER 0x400000F5
#define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF
/* Hyper-V HV_X64_MSR_SYNDBG_OPTIONS bits */
#define HV_X64_SYNDBG_OPTION_USE_HCALLS BIT(2)
static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu)
{
return &vcpu->arch.hyperv;
@ -46,6 +73,11 @@ static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic)
return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic));
}
static inline struct kvm_hv_syndbg *vcpu_to_hv_syndbg(struct kvm_vcpu *vcpu)
{
return &vcpu->kvm->arch.hyperv.hv_syndbg;
}
int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host);

8
arch/x86/kvm/ioapic.h
View File

@ -3,8 +3,8 @@
#define __KVM_IO_APIC_H
#include <linux/kvm_host.h>
#include <kvm/iodev.h>
#include "irq.h"
struct kvm;
struct kvm_vcpu;
@ -108,11 +108,7 @@ do { \
static inline int ioapic_in_kernel(struct kvm *kvm)
{
int mode = kvm->arch.irqchip_mode;
/* Matches smp_wmb() when setting irqchip_mode */
smp_rmb();
return mode == KVM_IRQCHIP_KERNEL;
return irqchip_kernel(kvm);
}
void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);

3
arch/x86/kvm/irq.c
View File

@ -83,6 +83,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
}
EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
/*
* check if there is pending interrupt without
@ -159,6 +160,8 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
{
__kvm_migrate_apic_timer(vcpu);
__kvm_migrate_pit_timer(vcpu);
if (kvm_x86_ops.migrate_timers)
kvm_x86_ops.migrate_timers(vcpu);
}
bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)

15
arch/x86/kvm/irq.h
View File

@ -16,7 +16,6 @@
#include <linux/spinlock.h>
#include <kvm/iodev.h>
#include "ioapic.h"
#include "lapic.h"
#define PIC_NUM_PINS 16
@ -66,15 +65,6 @@ void kvm_pic_destroy(struct kvm *kvm);
int kvm_pic_read_irq(struct kvm *kvm);
void kvm_pic_update_irq(struct kvm_pic *s);
static inline int pic_in_kernel(struct kvm *kvm)
{
int mode = kvm->arch.irqchip_mode;
/* Matches smp_wmb() when setting irqchip_mode */
smp_rmb();
return mode == KVM_IRQCHIP_KERNEL;
}
static inline int irqchip_split(struct kvm *kvm)
{
int mode = kvm->arch.irqchip_mode;
@ -93,6 +83,11 @@ static inline int irqchip_kernel(struct kvm *kvm)
return mode == KVM_IRQCHIP_KERNEL;
}
static inline int pic_in_kernel(struct kvm *kvm)
{
return irqchip_kernel(kvm);
}
static inline int irqchip_in_kernel(struct kvm *kvm)
{
int mode = kvm->arch.irqchip_mode;

10
arch/x86/kvm/kvm_cache_regs.h
View File

@ -116,8 +116,9 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask)
{
ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS;
if (tmask & vcpu->arch.cr0_guest_owned_bits)
kvm_x86_ops.decache_cr0_guest_bits(vcpu);
if ((tmask & vcpu->arch.cr0_guest_owned_bits) &&
!kvm_register_is_available(vcpu, VCPU_EXREG_CR0))
kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR0);
return vcpu->arch.cr0 & mask;
}
@ -129,8 +130,9 @@ static inline ulong kvm_read_cr0(struct kvm_vcpu *vcpu)
static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
{
ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS;
if (tmask & vcpu->arch.cr4_guest_owned_bits)
kvm_x86_ops.decache_cr4_guest_bits(vcpu);
if ((tmask & vcpu->arch.cr4_guest_owned_bits) &&
!kvm_register_is_available(vcpu, VCPU_EXREG_CR4))
kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR4);
return vcpu->arch.cr4 & mask;
}

95
arch/x86/kvm/lapic.c
View File

@ -36,6 +36,7 @@
#include <linux/jump_label.h>
#include "kvm_cache_regs.h"
#include "irq.h"
#include "ioapic.h"
#include "trace.h"
#include "x86.h"
#include "cpuid.h"
@ -110,11 +111,18 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
return apic->vcpu->vcpu_id;
}
bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu)
static bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu)
{
return pi_inject_timer && kvm_vcpu_apicv_active(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_can_post_timer_interrupt);
bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu)
{
return kvm_x86_ops.set_hv_timer
&& !(kvm_mwait_in_guest(vcpu->kvm) ||
kvm_can_post_timer_interrupt(vcpu));
}
EXPORT_SYMBOL_GPL(kvm_can_use_hv_timer);
static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu)
{
@ -1593,7 +1601,7 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
}
}
static void apic_timer_expired(struct kvm_lapic *apic)
static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
{
struct kvm_vcpu *vcpu = apic->vcpu;
struct kvm_timer *ktimer = &apic->lapic_timer;
@ -1604,6 +1612,12 @@ static void apic_timer_expired(struct kvm_lapic *apic)
if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
ktimer->expired_tscdeadline = ktimer->tscdeadline;
if (!from_timer_fn && vcpu->arch.apicv_active) {
WARN_ON(kvm_get_running_vcpu() != vcpu);
kvm_apic_inject_pending_timer_irqs(apic);
return;
}
if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
if (apic->lapic_timer.timer_advance_ns)
__kvm_wait_lapic_expire(vcpu);
@ -1643,18 +1657,23 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD);
} else
apic_timer_expired(apic);
apic_timer_expired(apic, false);
local_irq_restore(flags);
}
static inline u64 tmict_to_ns(struct kvm_lapic *apic, u32 tmict)
{
return (u64)tmict * APIC_BUS_CYCLE_NS * (u64)apic->divide_count;
}
static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor)
{
ktime_t now, remaining;
u64 ns_remaining_old, ns_remaining_new;
apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
* APIC_BUS_CYCLE_NS * apic->divide_count;
apic->lapic_timer.period =
tmict_to_ns(apic, kvm_lapic_get_reg(apic, APIC_TMICT));
limit_periodic_timer_frequency(apic);
now = ktime_get();
@ -1672,14 +1691,15 @@ static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_diviso
apic->lapic_timer.target_expiration = ktime_add_ns(now, ns_remaining_new);
}
static bool set_target_expiration(struct kvm_lapic *apic)
static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg)
{
ktime_t now;
u64 tscl = rdtsc();
s64 deadline;
now = ktime_get();
apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
* APIC_BUS_CYCLE_NS * apic->divide_count;
apic->lapic_timer.period =
tmict_to_ns(apic, kvm_lapic_get_reg(apic, APIC_TMICT));
if (!apic->lapic_timer.period) {
apic->lapic_timer.tscdeadline = 0;
@ -1687,10 +1707,32 @@ static bool set_target_expiration(struct kvm_lapic *apic)
}
limit_periodic_timer_frequency(apic);
deadline = apic->lapic_timer.period;
if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
if (unlikely(count_reg != APIC_TMICT)) {
deadline = tmict_to_ns(apic,
kvm_lapic_get_reg(apic, count_reg));
if (unlikely(deadline <= 0))
deadline = apic->lapic_timer.period;
else if (unlikely(deadline > apic->lapic_timer.period)) {
pr_info_ratelimited(
"kvm: vcpu %i: requested lapic timer restore with "
"starting count register %#x=%u (%lld ns) > initial count (%lld ns). "
"Using initial count to start timer.\n",
apic->vcpu->vcpu_id,
count_reg,
kvm_lapic_get_reg(apic, count_reg),
deadline, apic->lapic_timer.period);
kvm_lapic_set_reg(apic, count_reg, 0);
deadline = apic->lapic_timer.period;
}
}
}
apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
apic->lapic_timer.target_expiration = ktime_add_ns(now, apic->lapic_timer.period);
nsec_to_cycles(apic->vcpu, deadline);
apic->lapic_timer.target_expiration = ktime_add_ns(now, deadline);
return true;
}
@ -1723,7 +1765,7 @@ static void start_sw_period(struct kvm_lapic *apic)
if (ktime_after(ktime_get(),
apic->lapic_timer.target_expiration)) {
apic_timer_expired(apic);
apic_timer_expired(apic, false);
if (apic_lvtt_oneshot(apic))
return;
@ -1760,7 +1802,7 @@ static bool start_hv_timer(struct kvm_lapic *apic)
bool expired;
WARN_ON(preemptible());
if (!kvm_x86_ops.set_hv_timer)
if (!kvm_can_use_hv_timer(vcpu))
return false;
if (!ktimer->tscdeadline)
@ -1785,7 +1827,7 @@ static bool start_hv_timer(struct kvm_lapic *apic)
if (atomic_read(&ktimer->pending)) {
cancel_hv_timer(apic);
} else if (expired) {
apic_timer_expired(apic);
apic_timer_expired(apic, false);
cancel_hv_timer(apic);
}
}
@ -1833,9 +1875,9 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
/* If the preempt notifier has already run, it also called apic_timer_expired */
if (!apic->lapic_timer.hv_timer_in_use)
goto out;
WARN_ON(swait_active(&vcpu->wq));
WARN_ON(rcuwait_active(&vcpu->wait));
cancel_hv_timer(apic);
apic_timer_expired(apic);
apic_timer_expired(apic, false);
if (apic_lvtt_period(apic) && apic->lapic_timer.period) {
advance_periodic_target_expiration(apic);
@ -1872,17 +1914,22 @@ void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu)
restart_apic_timer(apic);
}
static void start_apic_timer(struct kvm_lapic *apic)
static void __start_apic_timer(struct kvm_lapic *apic, u32 count_reg)
{
atomic_set(&apic->lapic_timer.pending, 0);
if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
&& !set_target_expiration(apic))
&& !set_target_expiration(apic, count_reg))
return;
restart_apic_timer(apic);
}
static void start_apic_timer(struct kvm_lapic *apic)
{
__start_apic_timer(apic, APIC_TMICT);
}
static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
{
bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val);
@ -2336,7 +2383,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
apic_timer_expired(apic);
apic_timer_expired(apic, true);
if (lapic_is_periodic(apic)) {
advance_periodic_target_expiration(apic);
@ -2493,6 +2540,14 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
{
memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s));
/*
* Get calculated timer current count for remaining timer period (if
* any) and store it in the returned register set.
*/
__kvm_lapic_set_reg(s->regs, APIC_TMCCT,
__apic_read(vcpu->arch.apic, APIC_TMCCT));
return kvm_apic_state_fixup(vcpu, s, false);
}
@ -2520,7 +2575,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
apic_update_lvtt(apic);
apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
update_divide_count(apic);
start_apic_timer(apic);
__start_apic_timer(apic, APIC_TMCCT);
kvm_apic_update_apicv(vcpu);
apic->highest_isr_cache = -1;
if (vcpu->arch.apicv_active) {

9
arch/x86/kvm/lapic.h
View File

@ -161,9 +161,14 @@ static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off)
return *((u32 *) (apic->regs + reg_off));
}
static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val)
{
*((u32 *) (regs + reg_off)) = val;
}
static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
*((u32 *) (apic->regs + reg_off)) = val;
__kvm_lapic_set_reg(apic->regs, reg_off, val);
}
extern struct static_key kvm_no_apic_vcpu;
@ -245,7 +250,7 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu);
void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu);
bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu);
bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu);
static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
{

4
arch/x86/kvm/mmu.h
View File

@ -51,13 +51,13 @@ static inline u64 rsvd_bits(int s, int e)
return ((1ULL << (e - s + 1)) - 1) << s;
}
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask);
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty, gpa_t new_eptp);
bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);

517
arch/x86/kvm/mmu/mmu.c
View File

File diff suppressed because it is too large Load Diff

4
arch/x86/kvm/mmu/page_track.c
View File

@ -61,7 +61,7 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
{
int index, val;
index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
val = slot->arch.gfn_track[mode][index];
@ -151,7 +151,7 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
if (!slot)
return false;
index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
}

20
arch/x86/kvm/mmu/paging_tmpl.h
View File

@ -75,7 +75,7 @@
#define PT_GUEST_ACCESSED_MASK (1 << PT_GUEST_ACCESSED_SHIFT)
#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl)
#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PT_PAGE_TABLE_LEVEL)
#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PG_LEVEL_4K)
/*
* The guest_walker structure emulates the behavior of the hardware page
@ -198,7 +198,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
!(gpte & PT_GUEST_ACCESSED_MASK))
goto no_present;
if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PG_LEVEL_4K))
goto no_present;
return false;
@ -436,7 +436,7 @@ retry_walk:
gfn = gpte_to_gfn_lvl(pte, walker->level);
gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;
if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
gfn += pse36_gfn_delta(pte);
real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
@ -552,7 +552,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
* we call mmu_set_spte() with host_writable = true because
* pte_prefetch_gfn_to_pfn always gets a writable pfn.
*/
mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn,
mmu_set_spte(vcpu, spte, pte_access, 0, PG_LEVEL_4K, gfn, pfn,
true, true);
kvm_release_pfn_clean(pfn);
@ -575,7 +575,7 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,
u64 mask;
int r, index;
if (level == PT_PAGE_TABLE_LEVEL) {
if (level == PG_LEVEL_4K) {
mask = PTE_PREFETCH_NUM * sizeof(pt_element_t) - 1;
base_gpa = pte_gpa & ~mask;
index = (pte_gpa - base_gpa) / sizeof(pt_element_t);
@ -600,7 +600,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
sp = page_header(__pa(sptep));
if (sp->role.level > PT_PAGE_TABLE_LEVEL)
if (sp->role.level > PG_LEVEL_4K)
return;
if (sp->role.direct)
@ -812,7 +812,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
if (!r) {
pgprintk("%s: guest page fault\n", __func__);
if (!prefault)
inject_page_fault(vcpu, &walker.fault);
kvm_inject_emulated_page_fault(vcpu, &walker.fault);
return RET_PF_RETRY;
}
@ -828,7 +828,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
&walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
if (lpage_disallowed || is_self_change_mapping)
max_level = PT_PAGE_TABLE_LEVEL;
max_level = PG_LEVEL_4K;
else
max_level = walker.level;
@ -884,7 +884,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
{
int offset = 0;
WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
WARN_ON(sp->role.level != PG_LEVEL_4K);
if (PTTYPE == 32)
offset = sp->role.quadrant << PT64_LEVEL_BITS;
@ -1070,7 +1070,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
set_spte_ret |= set_spte(vcpu, &sp->spt[i],
pte_access, PT_PAGE_TABLE_LEVEL,
pte_access, PG_LEVEL_4K,
gfn, spte_to_pfn(sp->spt[i]),
true, false, host_writable);
}

6
arch/x86/kvm/mmu_audit.c
View File

@ -100,7 +100,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
sp = page_header(__pa(sptep));
if (sp->unsync) {
if (level != PT_PAGE_TABLE_LEVEL) {
if (level != PG_LEVEL_4K) {
audit_printk(vcpu->kvm, "unsync sp: %p "
"level = %d\n", sp, level);
return;
@ -176,7 +176,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp)
{
int i;
if (sp->role.level != PT_PAGE_TABLE_LEVEL)
if (sp->role.level != PG_LEVEL_4K)
return;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
@ -200,7 +200,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, sp->gfn);
rmap_head = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot);
rmap_head = __gfn_to_rmap(sp->gfn, PG_LEVEL_4K, slot);
for_each_rmap_spte(rmap_head, &iter, sptep) {
if (is_writable_pte(*sptep))

4
arch/x86/kvm/pmu.c
View File

@ -397,9 +397,9 @@ static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
__set_bit(pmc->idx, pmu->pmc_in_use);
}
int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr, data);
return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr_info);
}
int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)

4
arch/x86/kvm/pmu.h
View File

@ -32,7 +32,7 @@ struct kvm_pmu_ops {
struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
void (*refresh)(struct kvm_vcpu *vcpu);
void (*init)(struct kvm_vcpu *vcpu);
@ -147,7 +147,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
void kvm_pmu_reset(struct kvm_vcpu *vcpu);

Some files were not shown because too many files have changed in this diff Show More