linux-stable/include/linux/kvm_host.h
Linus Torvalds bf9095424d S390:
* ultravisor communication device driver
 
 * fix TEID on terminating storage key ops
 
 RISC-V:
 
 * Added Sv57x4 support for G-stage page table
 
 * Added range based local HFENCE functions
 
 * Added remote HFENCE functions based on VCPU requests
 
 * Added ISA extension registers in ONE_REG interface
 
 * Updated KVM RISC-V maintainers entry to cover selftests support
 
 ARM:
 
 * Add support for the ARMv8.6 WFxT extension
 
 * Guard pages for the EL2 stacks
 
 * Trap and emulate AArch32 ID registers to hide unsupported features
 
 * Ability to select and save/restore the set of hypercalls exposed
   to the guest
 
 * Support for PSCI-initiated suspend in collaboration with userspace
 
 * GICv3 register-based LPI invalidation support
 
 * Move host PMU event merging into the vcpu data structure
 
 * GICv3 ITS save/restore fixes
 
 * The usual set of small-scale cleanups and fixes
 
 x86:
 
 * New ioctls to get/set TSC frequency for a whole VM
 
 * Allow userspace to opt out of hypercall patching
 
 * Only do MSR filtering for MSRs accessed by rdmsr/wrmsr
 
 AMD SEV improvements:
 
 * Add KVM_EXIT_SHUTDOWN metadata for SEV-ES
 
 * V_TSC_AUX support
 
 Nested virtualization improvements for AMD:
 
 * Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
   nested vGIF)
 
 * Allow AVIC to co-exist with a nested guest running
 
 * Fixes for LBR virtualizations when a nested guest is running,
   and nested LBR virtualization support
 
 * PAUSE filtering for nested hypervisors
 
 Guest support:
 
 * Decoupling of vcpu_is_preempted from PV spinlocks
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmKN9M4UHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroNLeAf+KizAlQwxEehHHeNyTkZuKyMawrD6
 zsqAENR6i1TxiXe7fDfPFbO2NR0ZulQopHbD9mwnHJ+nNw0J4UT7g3ii1IAVcXPu
 rQNRGMVWiu54jt+lep8/gDg0JvPGKVVKLhxUaU1kdWT9PhIOC6lwpP3vmeWkUfRi
 PFL/TMT0M8Nfryi0zHB0tXeqg41BiXfqO8wMySfBAHUbpv8D53D2eXQL6YlMM0pL
 2quB1HxHnpueE5vj3WEPQ3PCdy1M2MTfCDBJAbZGG78Ljx45FxSGoQcmiBpPnhJr
 C6UGP4ZDWpml5YULUoA70k5ylCbP+vI61U4vUtzEiOjHugpPV5wFKtx5nw==
 =ozWx
 -----END PGP SIGNATURE-----

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

Pull kvm updates from Paolo Bonzini:
 "S390:

   - ultravisor communication device driver

   - fix TEID on terminating storage key ops

  RISC-V:

   - Added Sv57x4 support for G-stage page table

   - Added range based local HFENCE functions

   - Added remote HFENCE functions based on VCPU requests

   - Added ISA extension registers in ONE_REG interface

   - Updated KVM RISC-V maintainers entry to cover selftests support

  ARM:

   - Add support for the ARMv8.6 WFxT extension

   - Guard pages for the EL2 stacks

   - Trap and emulate AArch32 ID registers to hide unsupported features

   - Ability to select and save/restore the set of hypercalls exposed to
     the guest

   - Support for PSCI-initiated suspend in collaboration with userspace

   - GICv3 register-based LPI invalidation support

   - Move host PMU event merging into the vcpu data structure

   - GICv3 ITS save/restore fixes

   - The usual set of small-scale cleanups and fixes

  x86:

   - New ioctls to get/set TSC frequency for a whole VM

   - Allow userspace to opt out of hypercall patching

   - Only do MSR filtering for MSRs accessed by rdmsr/wrmsr

  AMD SEV improvements:

   - Add KVM_EXIT_SHUTDOWN metadata for SEV-ES

   - V_TSC_AUX support

  Nested virtualization improvements for AMD:

   - Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
     nested vGIF)

   - Allow AVIC to co-exist with a nested guest running

   - Fixes for LBR virtualizations when a nested guest is running, and
     nested LBR virtualization support

   - PAUSE filtering for nested hypervisors

  Guest support:

   - Decoupling of vcpu_is_preempted from PV spinlocks"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (199 commits)
  KVM: x86: Fix the intel_pt PMI handling wrongly considered from guest
  KVM: selftests: x86: Sync the new name of the test case to .gitignore
  Documentation: kvm: reorder ARM-specific section about KVM_SYSTEM_EVENT_SUSPEND
  x86, kvm: use correct GFP flags for preemption disabled
  KVM: LAPIC: Drop pending LAPIC timer injection when canceling the timer
  x86/kvm: Alloc dummy async #PF token outside of raw spinlock
  KVM: x86: avoid calling x86 emulator without a decoded instruction
  KVM: SVM: Use kzalloc for sev ioctl interfaces to prevent kernel data leak
  x86/fpu: KVM: Set the base guest FPU uABI size to sizeof(struct kvm_xsave)
  s390/uv_uapi: depend on CONFIG_S390
  KVM: selftests: x86: Fix test failure on arch lbr capable platforms
  KVM: LAPIC: Trace LAPIC timer expiration on every vmentry
  KVM: s390: selftest: Test suppression indication on key prot exception
  KVM: s390: Don't indicate suppression on dirtying, failing memop
  selftests: drivers/s390x: Add uvdevice tests
  drivers/s390/char: Add Ultravisor io device
  MAINTAINERS: Update KVM RISC-V entry to cover selftests support
  RISC-V: KVM: Introduce ISA extension register
  RISC-V: KVM: Cleanup stale TLB entries when host CPU changes
  RISC-V: KVM: Add remote HFENCE functions based on VCPU requests
  ...
2022-05-26 14:20:14 -07:00

2259 lines
68 KiB
C++

/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef __KVM_HOST_H
#define __KVM_HOST_H
#include <linux/types.h>
#include <linux/hardirq.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/sched/stat.h>
#include <linux/bug.h>
#include <linux/minmax.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/preempt.h>
#include <linux/msi.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/rcupdate.h>
#include <linux/ratelimit.h>
#include <linux/err.h>
#include <linux/irqflags.h>
#include <linux/context_tracking.h>
#include <linux/irqbypass.h>
#include <linux/rcuwait.h>
#include <linux/refcount.h>
#include <linux/nospec.h>
#include <linux/notifier.h>
#include <linux/ftrace.h>
#include <linux/hashtable.h>
#include <linux/instrumentation.h>
#include <linux/interval_tree.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
#include <asm/signal.h>
#include <linux/kvm.h>
#include <linux/kvm_para.h>
#include <linux/kvm_types.h>
#include <asm/kvm_host.h>
#include <linux/kvm_dirty_ring.h>
#ifndef KVM_MAX_VCPU_IDS
#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS
#endif
/*
* The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
* in kvm, other bits are visible for userspace which are defined in
* include/linux/kvm_h.
*/
#define KVM_MEMSLOT_INVALID (1UL << 16)
/*
* Bit 63 of the memslot generation number is an "update in-progress flag",
* e.g. is temporarily set for the duration of install_new_memslots().
* This flag effectively creates a unique generation number that is used to
* mark cached memslot data, e.g. MMIO accesses, as potentially being stale,
* i.e. may (or may not) have come from the previous memslots generation.
*
* This is necessary because the actual memslots update is not atomic with
* respect to the generation number update. Updating the generation number
* first would allow a vCPU to cache a spte from the old memslots using the
* new generation number, and updating the generation number after switching
* to the new memslots would allow cache hits using the old generation number
* to reference the defunct memslots.
*
* This mechanism is used to prevent getting hits in KVM's caches while a
* memslot update is in-progress, and to prevent cache hits *after* updating
* the actual generation number against accesses that were inserted into the
* cache *before* the memslots were updated.
*/
#define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS BIT_ULL(63)
/* Two fragments for cross MMIO pages. */
#define KVM_MAX_MMIO_FRAGMENTS 2
#ifndef KVM_ADDRESS_SPACE_NUM
#define KVM_ADDRESS_SPACE_NUM 1
#endif
/*
* For the normal pfn, the highest 12 bits should be zero,
* so we can mask bit 62 ~ bit 52 to indicate the error pfn,
* mask bit 63 to indicate the noslot pfn.
*/
#define KVM_PFN_ERR_MASK (0x7ffULL << 52)
#define KVM_PFN_ERR_NOSLOT_MASK (0xfffULL << 52)
#define KVM_PFN_NOSLOT (0x1ULL << 63)
#define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK)
#define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2)
/*
* error pfns indicate that the gfn is in slot but faild to
* translate it to pfn on host.
*/
static inline bool is_error_pfn(kvm_pfn_t pfn)
{
return !!(pfn & KVM_PFN_ERR_MASK);
}
/*
* error_noslot pfns indicate that the gfn can not be
* translated to pfn - it is not in slot or failed to
* translate it to pfn.
*/
static inline bool is_error_noslot_pfn(kvm_pfn_t pfn)
{
return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK);
}
/* noslot pfn indicates that the gfn is not in slot. */
static inline bool is_noslot_pfn(kvm_pfn_t pfn)
{
return pfn == KVM_PFN_NOSLOT;
}
/*
* architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390)
* provide own defines and kvm_is_error_hva
*/
#ifndef KVM_HVA_ERR_BAD
#define KVM_HVA_ERR_BAD (PAGE_OFFSET)
#define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE)
static inline bool kvm_is_error_hva(unsigned long addr)
{
return addr >= PAGE_OFFSET;
}
#endif
#define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT))
static inline bool is_error_page(struct page *page)
{
return IS_ERR(page);
}
#define KVM_REQUEST_MASK GENMASK(7,0)
#define KVM_REQUEST_NO_WAKEUP BIT(8)
#define KVM_REQUEST_WAIT BIT(9)
#define KVM_REQUEST_NO_ACTION BIT(10)
/*
* Architecture-independent vcpu->requests bit members
* Bits 4-7 are reserved for more arch-independent bits.
*/
#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_UNBLOCK 2
#define KVM_REQ_UNHALT 3
#define KVM_REQUEST_ARCH_BASE 8
/*
* KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to
* OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick"
* in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing
* on. A kick only guarantees that the vCPU is on its way out, e.g. a previous
* kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no
* guarantee the vCPU received an IPI and has actually exited guest mode.
*/
#define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \
(unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \
})
#define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0)
bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
unsigned long *vcpu_bitmap);
bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
struct kvm_vcpu *except);
bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req,
unsigned long *vcpu_bitmap);
#define KVM_USERSPACE_IRQ_SOURCE_ID 0
#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1
extern struct mutex kvm_lock;
extern struct list_head vm_list;
struct kvm_io_range {
gpa_t addr;
int len;
struct kvm_io_device *dev;
};
#define NR_IOBUS_DEVS 1000
struct kvm_io_bus {
int dev_count;
int ioeventfd_count;
struct kvm_io_range range[];
};
enum kvm_bus {
KVM_MMIO_BUS,
KVM_PIO_BUS,
KVM_VIRTIO_CCW_NOTIFY_BUS,
KVM_FAST_MMIO_BUS,
KVM_NR_BUSES
};
int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, const void *val);
int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
gpa_t addr, int len, const void *val, long cookie);
int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, void *val);
int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, struct kvm_io_device *dev);
int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
struct kvm_io_device *dev);
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
gpa_t addr);
#ifdef CONFIG_KVM_ASYNC_PF
struct kvm_async_pf {
struct work_struct work;
struct list_head link;
struct list_head queue;
struct kvm_vcpu *vcpu;
struct mm_struct *mm;
gpa_t cr2_or_gpa;
unsigned long addr;
struct kvm_arch_async_pf arch;
bool wakeup_all;
bool notpresent_injected;
};
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
unsigned long hva, struct kvm_arch_async_pf *arch);
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#endif
#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
struct kvm_gfn_range {
struct kvm_memory_slot *slot;
gfn_t start;
gfn_t end;
pte_t pte;
bool may_block;
};
bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
#endif
enum {
OUTSIDE_GUEST_MODE,
IN_GUEST_MODE,
EXITING_GUEST_MODE,
READING_SHADOW_PAGE_TABLES,
};
#define KVM_UNMAPPED_PAGE ((void *) 0x500 + POISON_POINTER_DELTA)
struct kvm_host_map {
/*
* Only valid if the 'pfn' is managed by the host kernel (i.e. There is
* a 'struct page' for it. When using mem= kernel parameter some memory
* can be used as guest memory but they are not managed by host
* kernel).
* If 'pfn' is not managed by the host kernel, this field is
* initialized to KVM_UNMAPPED_PAGE.
*/
struct page *page;
void *hva;
kvm_pfn_t pfn;
kvm_pfn_t gfn;
};
/*
* Used to check if the mapping is valid or not. Never use 'kvm_host_map'
* directly to check for that.
*/
static inline bool kvm_vcpu_mapped(struct kvm_host_map *map)
{
return !!map->hva;
}
static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop)
{
return single_task_running() && !need_resched() && ktime_before(cur, stop);
}
/*
* Sometimes a large or cross-page mmio needs to be broken up into separate
* exits for userspace servicing.
*/
struct kvm_mmio_fragment {
gpa_t gpa;
void *data;
unsigned len;
};
struct kvm_vcpu {
struct kvm *kvm;
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier preempt_notifier;
#endif
int cpu;
int vcpu_id; /* id given by userspace at creation */
int vcpu_idx; /* index in kvm->vcpus array */
int ____srcu_idx; /* Don't use this directly. You've been warned. */
#ifdef CONFIG_PROVE_RCU
int srcu_depth;
#endif
int mode;
u64 requests;
unsigned long guest_debug;
struct mutex mutex;
struct kvm_run *run;
#ifndef __KVM_HAVE_ARCH_WQP
struct rcuwait wait;
#endif
struct pid __rcu *pid;
int sigset_active;
sigset_t sigset;
unsigned int halt_poll_ns;
bool valid_wakeup;
#ifdef CONFIG_HAS_IOMEM
int mmio_needed;
int mmio_read_completed;
int mmio_is_write;
int mmio_cur_fragment;
int mmio_nr_fragments;
struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS];
#endif
#ifdef CONFIG_KVM_ASYNC_PF
struct {
u32 queued;
struct list_head queue;
struct list_head done;
spinlock_t lock;
} async_pf;
#endif
#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
/*
* Cpu relax intercept or pause loop exit optimization
* in_spin_loop: set when a vcpu does a pause loop exit
* or cpu relax intercepted.
* dy_eligible: indicates whether vcpu is eligible for directed yield.
*/
struct {
bool in_spin_loop;
bool dy_eligible;
} spin_loop;
#endif
bool preempted;
bool ready;
struct kvm_vcpu_arch arch;
struct kvm_vcpu_stat stat;
char stats_id[KVM_STATS_NAME_SIZE];
struct kvm_dirty_ring dirty_ring;
/*
* The most recently used memslot by this vCPU and the slots generation
* for which it is valid.
* No wraparound protection is needed since generations won't overflow in
* thousands of years, even assuming 1M memslot operations per second.
*/
struct kvm_memory_slot *last_used_slot;
u64 last_used_slot_gen;
};
/*
* Start accounting time towards a guest.
* Must be called before entering guest context.
*/
static __always_inline void guest_timing_enter_irqoff(void)
{
/*
* This is running in ioctl context so its safe to assume that it's the
* stime pending cputime to flush.
*/
instrumentation_begin();
vtime_account_guest_enter();
instrumentation_end();
}
/*
* Enter guest context and enter an RCU extended quiescent state.
*
* Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
* unsafe to use any code which may directly or indirectly use RCU, tracing
* (including IRQ flag tracing), or lockdep. All code in this period must be
* non-instrumentable.
*/
static __always_inline void guest_context_enter_irqoff(void)
{
/*
* KVM does not hold any references to rcu protected data when it
* switches CPU into a guest mode. In fact switching to a guest mode
* is very similar to exiting to userspace from rcu point of view. In
* addition CPU may stay in a guest mode for quite a long time (up to
* one time slice). Lets treat guest mode as quiescent state, just like
* we do with user-mode execution.
*/
if (!context_tracking_guest_enter()) {
instrumentation_begin();
rcu_virt_note_context_switch(smp_processor_id());
instrumentation_end();
}
}
/*
* Deprecated. Architectures should move to guest_timing_enter_irqoff() and
* guest_state_enter_irqoff().
*/
static __always_inline void guest_enter_irqoff(void)
{
guest_timing_enter_irqoff();
guest_context_enter_irqoff();
}
/**
* guest_state_enter_irqoff - Fixup state when entering a guest
*
* Entry to a guest will enable interrupts, but the kernel state is interrupts
* disabled when this is invoked. Also tell RCU about it.
*
* 1) Trace interrupts on state
* 2) Invoke context tracking if enabled to adjust RCU state
* 3) Tell lockdep that interrupts are enabled
*
* Invoked from architecture specific code before entering a guest.
* Must be called with interrupts disabled and the caller must be
* non-instrumentable.
* The caller has to invoke guest_timing_enter_irqoff() before this.
*
* Note: this is analogous to exit_to_user_mode().
*/
static __always_inline void guest_state_enter_irqoff(void)
{
instrumentation_begin();
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
instrumentation_end();
guest_context_enter_irqoff();
lockdep_hardirqs_on(CALLER_ADDR0);
}
/*
* Exit guest context and exit an RCU extended quiescent state.
*
* Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
* unsafe to use any code which may directly or indirectly use RCU, tracing
* (including IRQ flag tracing), or lockdep. All code in this period must be
* non-instrumentable.
*/
static __always_inline void guest_context_exit_irqoff(void)
{
context_tracking_guest_exit();
}
/*
* Stop accounting time towards a guest.
* Must be called after exiting guest context.
*/
static __always_inline void guest_timing_exit_irqoff(void)
{
instrumentation_begin();
/* Flush the guest cputime we spent on the guest */
vtime_account_guest_exit();
instrumentation_end();
}
/*
* Deprecated. Architectures should move to guest_state_exit_irqoff() and
* guest_timing_exit_irqoff().
*/
static __always_inline void guest_exit_irqoff(void)
{
guest_context_exit_irqoff();
guest_timing_exit_irqoff();
}
static inline void guest_exit(void)
{
unsigned long flags;
local_irq_save(flags);
guest_exit_irqoff();
local_irq_restore(flags);
}
/**
* guest_state_exit_irqoff - Establish state when returning from guest mode
*
* Entry from a guest disables interrupts, but guest mode is traced as
* interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
*
* 1) Tell lockdep that interrupts are disabled
* 2) Invoke context tracking if enabled to reactivate RCU
* 3) Trace interrupts off state
*
* Invoked from architecture specific code after exiting a guest.
* Must be invoked with interrupts disabled and the caller must be
* non-instrumentable.
* The caller has to invoke guest_timing_exit_irqoff() after this.
*
* Note: this is analogous to enter_from_user_mode().
*/
static __always_inline void guest_state_exit_irqoff(void)
{
lockdep_hardirqs_off(CALLER_ADDR0);
guest_context_exit_irqoff();
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
}
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
/*
* The memory barrier ensures a previous write to vcpu->requests cannot
* be reordered with the read of vcpu->mode. It pairs with the general
* memory barrier following the write of vcpu->mode in VCPU RUN.
*/
smp_mb__before_atomic();
return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
}
/*
* Some of the bitops functions do not support too long bitmaps.
* This number must be determined not to exceed such limits.
*/
#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
/*
* Since at idle each memslot belongs to two memslot sets it has to contain
* two embedded nodes for each data structure that it forms a part of.
*
* Two memslot sets (one active and one inactive) are necessary so the VM
* continues to run on one memslot set while the other is being modified.
*
* These two memslot sets normally point to the same set of memslots.
* They can, however, be desynchronized when performing a memslot management
* operation by replacing the memslot to be modified by its copy.
* After the operation is complete, both memslot sets once again point to
* the same, common set of memslot data.
*
* The memslots themselves are independent of each other so they can be
* individually added or deleted.
*/
struct kvm_memory_slot {
struct hlist_node id_node[2];
struct interval_tree_node hva_node[2];
struct rb_node gfn_node[2];
gfn_t base_gfn;
unsigned long npages;
unsigned long *dirty_bitmap;
struct kvm_arch_memory_slot arch;
unsigned long userspace_addr;
u32 flags;
short id;
u16 as_id;
};
static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
{
return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
}
static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
{
return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
}
static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot)
{
unsigned long len = kvm_dirty_bitmap_bytes(memslot);
return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap);
}
#ifndef KVM_DIRTY_LOG_MANUAL_CAPS
#define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE
#endif
struct kvm_s390_adapter_int {
u64 ind_addr;
u64 summary_addr;
u64 ind_offset;
u32 summary_offset;
u32 adapter_id;
};
struct kvm_hv_sint {
u32 vcpu;
u32 sint;
};
struct kvm_xen_evtchn {
u32 port;
u32 vcpu_id;
int vcpu_idx;
u32 priority;
};
struct kvm_kernel_irq_routing_entry {
u32 gsi;
u32 type;
int (*set)(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status);
union {
struct {
unsigned irqchip;
unsigned pin;
} irqchip;
struct {
u32 address_lo;
u32 address_hi;
u32 data;
u32 flags;
u32 devid;
} msi;
struct kvm_s390_adapter_int adapter;
struct kvm_hv_sint hv_sint;
struct kvm_xen_evtchn xen_evtchn;
};
struct hlist_node link;
};
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
struct kvm_irq_routing_table {
int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
u32 nr_rt_entries;
/*
* Array indexed by gsi. Each entry contains list of irq chips
* the gsi is connected to.
*/
struct hlist_head map[];
};
#endif
#ifndef KVM_PRIVATE_MEM_SLOTS
#define KVM_PRIVATE_MEM_SLOTS 0
#endif
#define KVM_MEM_SLOTS_NUM SHRT_MAX
#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
{
return 0;
}
#endif
struct kvm_memslots {
u64 generation;
atomic_long_t last_used_slot;
struct rb_root_cached hva_tree;
struct rb_root gfn_tree;
/*
* The mapping table from slot id to memslot.
*
* 7-bit bucket count matches the size of the old id to index array for
* 512 slots, while giving good performance with this slot count.
* Higher bucket counts bring only small performance improvements but
* always result in higher memory usage (even for lower memslot counts).
*/
DECLARE_HASHTABLE(id_hash, 7);
int node_idx;
};
struct kvm {
#ifdef KVM_HAVE_MMU_RWLOCK
rwlock_t mmu_lock;
#else
spinlock_t mmu_lock;
#endif /* KVM_HAVE_MMU_RWLOCK */
struct mutex slots_lock;
/*
* Protects the arch-specific fields of struct kvm_memory_slots in
* use by the VM. To be used under the slots_lock (above) or in a
* kvm->srcu critical section where acquiring the slots_lock would
* lead to deadlock with the synchronize_srcu in
* install_new_memslots.
*/
struct mutex slots_arch_lock;
struct mm_struct *mm; /* userspace tied to this vm */
unsigned long nr_memslot_pages;
/* The two memslot sets - active and inactive (per address space) */
struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
/* The current active memslot set for each address space */
struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
struct xarray vcpu_array;
/* Used to wait for completion of MMU notifiers. */
spinlock_t mn_invalidate_lock;
unsigned long mn_active_invalidate_count;
struct rcuwait mn_memslots_update_rcuwait;
/* For management / invalidation of gfn_to_pfn_caches */
spinlock_t gpc_lock;
struct list_head gpc_list;
/*
* created_vcpus is protected by kvm->lock, and is incremented
* at the beginning of KVM_CREATE_VCPU. online_vcpus is only
* incremented after storing the kvm_vcpu pointer in vcpus,
* and is accessed atomically.
*/
atomic_t online_vcpus;
int max_vcpus;
int created_vcpus;
int last_boosted_vcpu;
struct list_head vm_list;
struct mutex lock;
struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
#ifdef CONFIG_HAVE_KVM_EVENTFD
struct {
spinlock_t lock;
struct list_head items;
struct list_head resampler_list;
struct mutex resampler_lock;
} irqfds;
struct list_head ioeventfds;
#endif
struct kvm_vm_stat stat;
struct kvm_arch arch;
refcount_t users_count;
#ifdef CONFIG_KVM_MMIO
struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
spinlock_t ring_lock;
struct list_head coalesced_zones;
#endif
struct mutex irq_lock;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
/*
* Update side is protected by irq_lock.
*/
struct kvm_irq_routing_table __rcu *irq_routing;
#endif
#ifdef CONFIG_HAVE_KVM_IRQFD
struct hlist_head irq_ack_notifier_list;
#endif
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
struct mmu_notifier mmu_notifier;
unsigned long mmu_notifier_seq;
long mmu_notifier_count;
unsigned long mmu_notifier_range_start;
unsigned long mmu_notifier_range_end;
#endif
struct list_head devices;
u64 manual_dirty_log_protect;
struct dentry *debugfs_dentry;
struct kvm_stat_data **debugfs_stat_data;
struct srcu_struct srcu;
struct srcu_struct irq_srcu;
pid_t userspace_pid;
unsigned int max_halt_poll_ns;
u32 dirty_ring_size;
bool vm_bugged;
bool vm_dead;
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
struct notifier_block pm_notifier;
#endif
char stats_id[KVM_STATS_NAME_SIZE];
};
#define kvm_err(fmt, ...) \
pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_info(fmt, ...) \
pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_debug(fmt, ...) \
pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_debug_ratelimited(fmt, ...) \
pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \
## __VA_ARGS__)
#define kvm_pr_unimpl(fmt, ...) \
pr_err_ratelimited("kvm [%i]: " fmt, \
task_tgid_nr(current), ## __VA_ARGS__)
/* The guest did something we don't support. */
#define vcpu_unimpl(vcpu, fmt, ...) \
kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt, \
(vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__)
#define vcpu_debug(vcpu, fmt, ...) \
kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
#define vcpu_debug_ratelimited(vcpu, fmt, ...) \
kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id, \
## __VA_ARGS__)
#define vcpu_err(vcpu, fmt, ...) \
kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
static inline void kvm_vm_dead(struct kvm *kvm)
{
kvm->vm_dead = true;
kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD);
}
static inline void kvm_vm_bugged(struct kvm *kvm)
{
kvm->vm_bugged = true;
kvm_vm_dead(kvm);
}
#define KVM_BUG(cond, kvm, fmt...) \
({ \
int __ret = (cond); \
\
if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \
kvm_vm_bugged(kvm); \
unlikely(__ret); \
})
#define KVM_BUG_ON(cond, kvm) \
({ \
int __ret = (cond); \
\
if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \
kvm_vm_bugged(kvm); \
unlikely(__ret); \
})
static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_PROVE_RCU
WARN_ONCE(vcpu->srcu_depth++,
"KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1);
#endif
vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
}
static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu)
{
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx);
#ifdef CONFIG_PROVE_RCU
WARN_ONCE(--vcpu->srcu_depth,
"KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth);
#endif
}
static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm)
{
return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET);
}
static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
{
return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
}
static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
int num_vcpus = atomic_read(&kvm->online_vcpus);
i = array_index_nospec(i, num_vcpus);
/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */
smp_rmb();
return xa_load(&kvm->vcpu_array, i);
}
#define kvm_for_each_vcpu(idx, vcpup, kvm) \
xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \
(atomic_read(&kvm->online_vcpus) - 1))
static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
{
struct kvm_vcpu *vcpu = NULL;
unsigned long i;
if (id < 0)
return NULL;
if (id < KVM_MAX_VCPUS)
vcpu = kvm_get_vcpu(kvm, id);
if (vcpu && vcpu->vcpu_id == id)
return vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
if (vcpu->vcpu_id == id)
return vcpu;
return NULL;
}
static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
{
return vcpu->vcpu_idx;
}
void kvm_destroy_vcpus(struct kvm *kvm);
void vcpu_load(struct kvm_vcpu *vcpu);
void vcpu_put(struct kvm_vcpu *vcpu);
#ifdef __KVM_HAVE_IOAPIC
void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm);
void kvm_arch_post_irq_routing_update(struct kvm *kvm);
#else
static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
{
}
static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
{
}
#endif
#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd_init(void);
void kvm_irqfd_exit(void);
#else
static inline int kvm_irqfd_init(void)
{
return 0;
}
static inline void kvm_irqfd_exit(void)
{
}
#endif
int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
struct module *module);
void kvm_exit(void);
void kvm_get_kvm(struct kvm *kvm);
bool kvm_get_kvm_safe(struct kvm *kvm);
void kvm_put_kvm(struct kvm *kvm);
bool file_is_kvm(struct file *file);
void kvm_put_kvm_no_destroy(struct kvm *kvm);
static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
{
as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
}
static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
{
return __kvm_memslots(kvm, 0);
}
static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu)
{
int as_id = kvm_arch_vcpu_memslots_id(vcpu);
return __kvm_memslots(vcpu->kvm, as_id);
}
static inline bool kvm_memslots_empty(struct kvm_memslots *slots)
{
return RB_EMPTY_ROOT(&slots->gfn_tree);
}
#define kvm_for_each_memslot(memslot, bkt, slots) \
hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \
if (WARN_ON_ONCE(!memslot->npages)) { \
} else
static inline
struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id)
{
struct kvm_memory_slot *slot;
int idx = slots->node_idx;
hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) {
if (slot->id == id)
return slot;
}
return NULL;
}
/* Iterator used for walking memslots that overlap a gfn range. */
struct kvm_memslot_iter {
struct kvm_memslots *slots;
struct rb_node *node;
struct kvm_memory_slot *slot;
};
static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter)
{
iter->node = rb_next(iter->node);
if (!iter->node)
return;
iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]);
}
static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter,
struct kvm_memslots *slots,
gfn_t start)
{
int idx = slots->node_idx;
struct rb_node *tmp;
struct kvm_memory_slot *slot;
iter->slots = slots;
/*
* Find the so called "upper bound" of a key - the first node that has
* its key strictly greater than the searched one (the start gfn in our case).
*/
iter->node = NULL;
for (tmp = slots->gfn_tree.rb_node; tmp; ) {
slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]);
if (start < slot->base_gfn) {
iter->node = tmp;
tmp = tmp->rb_left;
} else {
tmp = tmp->rb_right;
}
}
/*
* Find the slot with the lowest gfn that can possibly intersect with
* the range, so we'll ideally have slot start <= range start
*/
if (iter->node) {
/*
* A NULL previous node means that the very first slot
* already has a higher start gfn.
* In this case slot start > range start.
*/
tmp = rb_prev(iter->node);
if (tmp)
iter->node = tmp;
} else {
/* a NULL node below means no slots */
iter->node = rb_last(&slots->gfn_tree);
}
if (iter->node) {
iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]);
/*
* It is possible in the slot start < range start case that the
* found slot ends before or at range start (slot end <= range start)
* and so it does not overlap the requested range.
*
* In such non-overlapping case the next slot (if it exists) will
* already have slot start > range start, otherwise the logic above
* would have found it instead of the current slot.
*/
if (iter->slot->base_gfn + iter->slot->npages <= start)
kvm_memslot_iter_next(iter);
}
}
static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end)
{
if (!iter->node)
return false;
/*
* If this slot starts beyond or at the end of the range so does
* every next one
*/
return iter->slot->base_gfn < end;
}
/* Iterate over each memslot at least partially intersecting [start, end) range */
#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \
for (kvm_memslot_iter_start(iter, slots, start); \
kvm_memslot_iter_is_valid(iter, end); \
kvm_memslot_iter_next(iter))
/*
* KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
* - create a new memory slot
* - delete an existing memory slot
* - modify an existing memory slot
* -- move it in the guest physical memory space
* -- just change its flags
*
* Since flags can be changed by some of these operations, the following
* differentiation is the best we can do for __kvm_set_memory_region():
*/
enum kvm_mr_change {
KVM_MR_CREATE,
KVM_MR_DELETE,
KVM_MR_MOVE,
KVM_MR_FLAGS_ONLY,
};
int kvm_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem);
int __kvm_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem);
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
enum kvm_mr_change change);
void kvm_arch_commit_memory_region(struct kvm *kvm,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change);
/* flush all memory translations */
void kvm_arch_flush_shadow_all(struct kvm *kvm);
/* flush memory translations pointing to 'slot' */
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot);
int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
struct page **pages, int nr_pages);
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
bool *writable);
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
void kvm_set_page_accessed(struct page *page);
kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable);
kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
bool atomic, bool *async, bool write_fault,
bool *writable, hva_t *hva);
void kvm_release_pfn_clean(kvm_pfn_t pfn);
void kvm_release_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_accessed(kvm_pfn_t pfn);
void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len);
int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len);
int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
int offset, int len);
int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
unsigned long len);
int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len);
int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len);
int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
gpa_t gpa, unsigned long len);
#define __kvm_get_guest(kvm, gfn, offset, v) \
({ \
unsigned long __addr = gfn_to_hva(kvm, gfn); \
typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \
int __ret = -EFAULT; \
\
if (!kvm_is_error_hva(__addr)) \
__ret = get_user(v, __uaddr); \
__ret; \
})
#define kvm_get_guest(kvm, gpa, v) \
({ \
gpa_t __gpa = gpa; \
struct kvm *__kvm = kvm; \
\
__kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \
offset_in_page(__gpa), v); \
})
#define __kvm_put_guest(kvm, gfn, offset, v) \
({ \
unsigned long __addr = gfn_to_hva(kvm, gfn); \
typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \
int __ret = -EFAULT; \
\
if (!kvm_is_error_hva(__addr)) \
__ret = put_user(v, __uaddr); \
if (!__ret) \
mark_page_dirty(kvm, gfn); \
__ret; \
})
#define kvm_put_guest(kvm, gpa, v) \
({ \
gpa_t __gpa = gpa; \
struct kvm *__kvm = kvm; \
\
__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \
offset_in_page(__gpa), v); \
})
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
int len);
int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data,
unsigned long len);
int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data,
unsigned long len);
int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data,
int offset, int len);
int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
unsigned long len);
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
/**
* kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a
* given guest physical address.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
* @vcpu: vCPU to be used for marking pages dirty and to be woken on
* invalidation.
* @usage: indicates if the resulting host physical PFN is used while
* the @vcpu is IN_GUEST_MODE (in which case invalidation of
* the cache from MMU notifiers---but not for KVM memslot
* changes!---will also force @vcpu to exit the guest and
* refresh the cache); and/or if the PFN used directly
* by KVM (and thus needs a kernel virtual mapping).
* @gpa: guest physical address to map.
* @len: sanity check; the range being access must fit a single page.
*
* @return: 0 for success.
* -EINVAL for a mapping which would cross a page boundary.
* -EFAULT for an untranslatable guest physical address.
*
* This primes a gfn_to_pfn_cache and links it into the @kvm's list for
* invalidations to be processed. Callers are required to use
* kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before
* accessing the target page.
*/
int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
gpa_t gpa, unsigned long len);
/**
* kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
* @gpa: current guest physical address to map.
* @len: sanity check; the range being access must fit a single page.
*
* @return: %true if the cache is still valid and the address matches.
* %false if the cache is not valid.
*
* Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock
* while calling this function, and then continue to hold the lock until the
* access is complete.
*
* Callers in IN_GUEST_MODE may do so without locking, although they should
* still hold a read lock on kvm->scru for the memslot checks.
*/
bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
gpa_t gpa, unsigned long len);
/**
* kvm_gfn_to_pfn_cache_refresh - update a previously initialized cache.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
* @gpa: updated guest physical address to map.
* @len: sanity check; the range being access must fit a single page.
*
* @return: 0 for success.
* -EINVAL for a mapping which would cross a page boundary.
* -EFAULT for an untranslatable guest physical address.
*
* This will attempt to refresh a gfn_to_pfn_cache. Note that a successful
* returm from this function does not mean the page can be immediately
* accessed because it may have raced with an invalidation. Callers must
* still lock and check the cache status, as this function does not return
* with the lock still held to permit access.
*/
int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
gpa_t gpa, unsigned long len);
/**
* kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
*
* This unmaps the referenced page. The cache is left in the invalid state
* but at least the mapping from GPA to userspace HVA will remain cached
* and can be reused on a subsequent refresh.
*/
void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
/**
* kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
*
* This removes a cache from the @kvm's list to be processed on MMU notifier
* invocation.
*/
void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
void kvm_sigset_activate(struct kvm_vcpu *vcpu);
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
void kvm_vcpu_halt(struct kvm_vcpu *vcpu);
bool kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
int kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible);
void kvm_flush_remote_tlbs(struct kvm *kvm);
#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc);
void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
#endif
void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
unsigned long end);
void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
unsigned long end);
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset,
unsigned long mask);
void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot);
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log);
int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
int *is_dirty, struct kvm_memory_slot **memslot);
#endif
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
bool line_status);
int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap);
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
struct kvm_translation *tr);
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
struct kvm_guest_debug *dbg);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu);
int kvm_arch_init(void *opaque);
void kvm_arch_exit(void);
void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id);
int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state);
#endif
#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry);
#endif
int kvm_arch_hardware_enable(void);
void kvm_arch_hardware_disable(void);
int kvm_arch_hardware_setup(void *opaque);
void kvm_arch_hardware_unsetup(void);
int kvm_arch_check_processor_compat(void *opaque);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
int kvm_arch_post_init_vm(struct kvm *kvm);
void kvm_arch_pre_destroy_vm(struct kvm *kvm);
int kvm_arch_create_vm_debugfs(struct kvm *kvm);
#ifndef __KVM_HAVE_ARCH_VM_ALLOC
/*
* All architectures that want to use vzalloc currently also
* need their own kvm_arch_alloc_vm implementation.
*/
static inline struct kvm *kvm_arch_alloc_vm(void)
{
return kzalloc(sizeof(struct kvm), GFP_KERNEL);
}
#endif
static inline void __kvm_arch_free_vm(struct kvm *kvm)
{
kvfree(kvm);
}
#ifndef __KVM_HAVE_ARCH_VM_FREE
static inline void kvm_arch_free_vm(struct kvm *kvm)
{
__kvm_arch_free_vm(kvm);
}
#endif
#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
{
return -ENOTSUPP;
}
#endif
#ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
bool kvm_arch_has_noncoherent_dma(struct kvm *kvm);
#else
static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
{
}
static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
{
}
static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
{
return false;
}
#endif
#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE
void kvm_arch_start_assignment(struct kvm *kvm);
void kvm_arch_end_assignment(struct kvm *kvm);
bool kvm_arch_has_assigned_device(struct kvm *kvm);
#else
static inline void kvm_arch_start_assignment(struct kvm *kvm)
{
}
static inline void kvm_arch_end_assignment(struct kvm *kvm)
{
}
static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
{
return false;
}
#endif
static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu)
{
#ifdef __KVM_HAVE_ARCH_WQP
return vcpu->arch.waitp;
#else
return &vcpu->wait;
#endif
}
/*
* Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns
* true if the vCPU was blocking and was awakened, false otherwise.
*/
static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
{
return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu));
}
static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu)
{
return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu));
}
#ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED
/*
* returns true if the virtual interrupt controller is initialized and
* ready to accept virtual IRQ. On some architectures the virtual interrupt
* controller is dynamically instantiated and this is not always true.
*/
bool kvm_arch_intc_initialized(struct kvm *kvm);
#else
static inline bool kvm_arch_intc_initialized(struct kvm *kvm)
{
return true;
}
#endif
#ifdef CONFIG_GUEST_PERF_EVENTS
unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu);
void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void));
void kvm_unregister_perf_callbacks(void);
#else
static inline void kvm_register_perf_callbacks(void *ign) {}
static inline void kvm_unregister_perf_callbacks(void) {}
#endif /* CONFIG_GUEST_PERF_EVENTS */
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
void kvm_arch_destroy_vm(struct kvm *kvm);
void kvm_arch_sync_events(struct kvm *kvm);
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
bool kvm_is_zone_device_pfn(kvm_pfn_t pfn);
struct kvm_irq_ack_notifier {
struct hlist_node link;
unsigned gsi;
void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
};
int kvm_irq_map_gsi(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *entries, int gsi);
int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
bool line_status);
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
int irq_source_id, int level, bool line_status);
int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id,
int level, bool line_status);
bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin);
void kvm_notify_acked_gsi(struct kvm *kvm, int gsi);
void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
void kvm_register_irq_ack_notifier(struct kvm *kvm,
struct kvm_irq_ack_notifier *kian);
void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
struct kvm_irq_ack_notifier *kian);
int kvm_request_irq_source_id(struct kvm *kvm);
void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
/*
* Returns a pointer to the memslot if it contains gfn.
* Otherwise returns NULL.
*/
static inline struct kvm_memory_slot *
try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
{
if (!slot)
return NULL;
if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages)
return slot;
else
return NULL;
}
/*
* Returns a pointer to the memslot that contains gfn. Otherwise returns NULL.
*
* With "approx" set returns the memslot also when the address falls
* in a hole. In that case one of the memslots bordering the hole is
* returned.
*/
static inline struct kvm_memory_slot *
search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx)
{
struct kvm_memory_slot *slot;
struct rb_node *node;
int idx = slots->node_idx;
slot = NULL;
for (node = slots->gfn_tree.rb_node; node; ) {
slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]);
if (gfn >= slot->base_gfn) {
if (gfn < slot->base_gfn + slot->npages)
return slot;
node = node->rb_right;
} else
node = node->rb_left;
}
return approx ? slot : NULL;
}
static inline struct kvm_memory_slot *
____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx)
{
struct kvm_memory_slot *slot;
slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot);
slot = try_get_memslot(slot, gfn);
if (slot)
return slot;
slot = search_memslots(slots, gfn, approx);
if (slot) {
atomic_long_set(&slots->last_used_slot, (unsigned long)slot);
return slot;
}
return NULL;
}
/*
* __gfn_to_memslot() and its descendants are here to allow arch code to inline
* the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline
* because that would bloat other code too much.
*/
static inline struct kvm_memory_slot *
__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
{
return ____gfn_to_memslot(slots, gfn, false);
}
static inline unsigned long
__gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
{
/*
* The index was checked originally in search_memslots. To avoid
* that a malicious guest builds a Spectre gadget out of e.g. page
* table walks, do not let the processor speculate loads outside
* the guest's registered memslots.
*/
unsigned long offset = gfn - slot->base_gfn;
offset = array_index_nospec(offset, slot->npages);
return slot->userspace_addr + offset * PAGE_SIZE;
}
static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_memslot(kvm, gfn)->id;
}
static inline gfn_t
hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
{
gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;
return slot->base_gfn + gfn_offset;
}
static inline gpa_t gfn_to_gpa(gfn_t gfn)
{
return (gpa_t)gfn << PAGE_SHIFT;
}
static inline gfn_t gpa_to_gfn(gpa_t gpa)
{
return (gfn_t)(gpa >> PAGE_SHIFT);
}
static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn)
{
return (hpa_t)pfn << PAGE_SHIFT;
}
static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu,
gpa_t gpa)
{
return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa));
}
static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
{
unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
return kvm_is_error_hva(hva);
}
enum kvm_stat_kind {
KVM_STAT_VM,
KVM_STAT_VCPU,
};
struct kvm_stat_data {
struct kvm *kvm;
const struct _kvm_stats_desc *desc;
enum kvm_stat_kind kind;
};
struct _kvm_stats_desc {
struct kvm_stats_desc desc;
char name[KVM_STATS_NAME_SIZE];
};
#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \
.flags = type | unit | base | \
BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \
BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \
BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \
.exponent = exp, \
.size = sz, \
.bucket_size = bsz
#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vm_stat, generic.stat) \
}, \
.name = #stat, \
}
#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
}, \
.name = #stat, \
}
#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vm_stat, stat) \
}, \
.name = #stat, \
}
#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vcpu_stat, stat) \
}, \
.name = #stat, \
}
/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
#define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \
SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz)
#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \
unit, base, exponent, 1, 0)
#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \
unit, base, exponent, 1, 0)
#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \
unit, base, exponent, 1, 0)
#define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \
unit, base, exponent, sz, bsz)
#define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \
unit, base, exponent, sz, 0)
/* Cumulative counter, read/write */
#define STATS_DESC_COUNTER(SCOPE, name) \
STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \
KVM_STATS_BASE_POW10, 0)
/* Instantaneous counter, read only */
#define STATS_DESC_ICOUNTER(SCOPE, name) \
STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \
KVM_STATS_BASE_POW10, 0)
/* Peak counter, read/write */
#define STATS_DESC_PCOUNTER(SCOPE, name) \
STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \
KVM_STATS_BASE_POW10, 0)
/* Cumulative time in nanosecond */
#define STATS_DESC_TIME_NSEC(SCOPE, name) \
STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \
KVM_STATS_BASE_POW10, -9)
/* Linear histogram for time in nanosecond */
#define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \
STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \
KVM_STATS_BASE_POW10, -9, sz, bsz)
/* Logarithmic histogram for time in nanosecond */
#define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \
STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \
KVM_STATS_BASE_POW10, -9, sz)
#define KVM_GENERIC_VM_STATS() \
STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \
STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests)
#define KVM_GENERIC_VCPU_STATS() \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \
STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \
STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \
STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \
STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \
HALT_POLL_HIST_COUNT), \
STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \
HALT_POLL_HIST_COUNT), \
STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \
HALT_POLL_HIST_COUNT), \
STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking)
extern struct dentry *kvm_debugfs_dir;
ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
const struct _kvm_stats_desc *desc,
void *stats, size_t size_stats,
char __user *user_buffer, size_t size, loff_t *offset);
/**
* kvm_stats_linear_hist_update() - Update bucket value for linear histogram
* statistics data.
*
* @data: start address of the stats data
* @size: the number of bucket of the stats data
* @value: the new value used to update the linear histogram's bucket
* @bucket_size: the size (width) of a bucket
*/
static inline void kvm_stats_linear_hist_update(u64 *data, size_t size,
u64 value, size_t bucket_size)
{
size_t index = div64_u64(value, bucket_size);
index = min(index, size - 1);
++data[index];
}
/**
* kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram
* statistics data.
*
* @data: start address of the stats data
* @size: the number of bucket of the stats data
* @value: the new value used to update the logarithmic histogram's bucket
*/
static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value)
{
size_t index = fls64(value);
index = min(index, size - 1);
++data[index];
}
#define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \
kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize)
#define KVM_STATS_LOG_HIST_UPDATE(array, value) \
kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value)
extern const struct kvm_stats_header kvm_vm_stats_header;
extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
extern const struct kvm_stats_header kvm_vcpu_stats_header;
extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
{
if (unlikely(kvm->mmu_notifier_count))
return 1;
/*
* Ensure the read of mmu_notifier_count happens before the read
* of mmu_notifier_seq. This interacts with the smp_wmb() in
* mmu_notifier_invalidate_range_end to make sure that the caller
* either sees the old (non-zero) value of mmu_notifier_count or
* the new (incremented) value of mmu_notifier_seq.
* PowerPC Book3s HV KVM calls this under a per-page lock
* rather than under kvm->mmu_lock, for scalability, so
* can't rely on kvm->mmu_lock to keep things ordered.
*/
smp_rmb();
if (kvm->mmu_notifier_seq != mmu_seq)
return 1;
return 0;
}
static inline int mmu_notifier_retry_hva(struct kvm *kvm,
unsigned long mmu_seq,
unsigned long hva)
{
lockdep_assert_held(&kvm->mmu_lock);
/*
* If mmu_notifier_count is non-zero, then the range maintained by
* kvm_mmu_notifier_invalidate_range_start contains all addresses that
* might be being invalidated. Note that it may include some false
* positives, due to shortcuts when handing concurrent invalidations.
*/
if (unlikely(kvm->mmu_notifier_count) &&
hva >= kvm->mmu_notifier_range_start &&
hva < kvm->mmu_notifier_range_end)
return 1;
if (kvm->mmu_notifier_seq != mmu_seq)
return 1;
return 0;
}
#endif
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */
bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
const struct kvm_irq_routing_entry *entries,
unsigned nr,
unsigned flags);
int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue);
void kvm_free_irq_routing(struct kvm *kvm);
#else
static inline void kvm_free_irq_routing(struct kvm *kvm) {}
#endif
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
#ifdef CONFIG_HAVE_KVM_EVENTFD
void kvm_eventfd_init(struct kvm *kvm);
int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
void kvm_irq_routing_update(struct kvm *);
#else
static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
return -EINVAL;
}
static inline void kvm_irqfd_release(struct kvm *kvm) {}
#endif
#else
static inline void kvm_eventfd_init(struct kvm *kvm) {}
static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
return -EINVAL;
}
static inline void kvm_irqfd_release(struct kvm *kvm) {}
#ifdef CONFIG_HAVE_KVM_IRQCHIP
static inline void kvm_irq_routing_update(struct kvm *kvm)
{
}
#endif
static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
{
return -ENOSYS;
}
#endif /* CONFIG_HAVE_KVM_EVENTFD */
void kvm_arch_irq_routing_update(struct kvm *kvm);
static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
/*
* Ensure the rest of the request is published to kvm_check_request's
* caller. Paired with the smp_mb__after_atomic in kvm_check_request.
*/
smp_wmb();
set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}
static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
/*
* Request that don't require vCPU action should never be logged in
* vcpu->requests. The vCPU won't clear the request, so it will stay
* logged indefinitely and prevent the vCPU from entering the guest.
*/
BUILD_BUG_ON(!__builtin_constant_p(req) ||
(req & KVM_REQUEST_NO_ACTION));
__kvm_make_request(req, vcpu);
}
static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
{
return READ_ONCE(vcpu->requests);
}
static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
{
return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}
static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
{
clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}
static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
{
if (kvm_test_request(req, vcpu)) {
kvm_clear_request(req, vcpu);
/*
* Ensure the rest of the request is visible to kvm_check_request's
* caller. Paired with the smp_wmb in kvm_make_request.
*/
smp_mb__after_atomic();
return true;
} else {
return false;
}
}
extern bool kvm_rebooting;
extern unsigned int halt_poll_ns;
extern unsigned int halt_poll_ns_grow;
extern unsigned int halt_poll_ns_grow_start;
extern unsigned int halt_poll_ns_shrink;
struct kvm_device {
const struct kvm_device_ops *ops;
struct kvm *kvm;
void *private;
struct list_head vm_node;
};
/* create, destroy, and name are mandatory */
struct kvm_device_ops {
const char *name;
/*
* create is called holding kvm->lock and any operations not suitable
* to do while holding the lock should be deferred to init (see
* below).
*/
int (*create)(struct kvm_device *dev, u32 type);
/*
* init is called after create if create is successful and is called
* outside of holding kvm->lock.
*/
void (*init)(struct kvm_device *dev);
/*
* Destroy is responsible for freeing dev.
*
* Destroy may be called before or after destructors are called
* on emulated I/O regions, depending on whether a reference is
* held by a vcpu or other kvm component that gets destroyed
* after the emulated I/O.
*/
void (*destroy)(struct kvm_device *dev);
/*
* Release is an alternative method to free the device. It is
* called when the device file descriptor is closed. Once
* release is called, the destroy method will not be called
* anymore as the device is removed from the device list of
* the VM. kvm->lock is held.
*/
void (*release)(struct kvm_device *dev);
int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
long (*ioctl)(struct kvm_device *dev, unsigned int ioctl,
unsigned long arg);
int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma);
};
void kvm_device_get(struct kvm_device *dev);
void kvm_device_put(struct kvm_device *dev);
struct kvm_device *kvm_device_from_filp(struct file *filp);
int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type);
void kvm_unregister_device_ops(u32 type);
extern struct kvm_device_ops kvm_mpic_ops;
extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
{
vcpu->spin_loop.in_spin_loop = val;
}
static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
vcpu->spin_loop.dy_eligible = val;
}
#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
{
}
static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
}
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot)
{
return (memslot && memslot->id < KVM_USER_MEM_SLOTS &&
!(memslot->flags & KVM_MEMSLOT_INVALID));
}
struct kvm_vcpu *kvm_get_running_vcpu(void);
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
bool kvm_arch_has_irq_bypass(void);
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
struct irq_bypass_producer *);
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *,
struct irq_bypass_producer *);
void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *);
void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *,
struct kvm_kernel_irq_routing_entry *);
#endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
#ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS
/* If we wakeup during the poll time, was it a sucessful poll? */
static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
{
return vcpu->valid_wakeup;
}
#else
static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
{
return true;
}
#endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */
#ifdef CONFIG_HAVE_KVM_NO_POLL
/* Callback that tells if we must not poll */
bool kvm_arch_no_poll(struct kvm_vcpu *vcpu);
#else
static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
{
return false;
}
#endif /* CONFIG_HAVE_KVM_NO_POLL */
#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL
long kvm_arch_vcpu_async_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
#else
static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
unsigned int ioctl,
unsigned long arg)
{
return -ENOIOCTLCMD;
}
#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
unsigned long start, unsigned long end);
void kvm_arch_guest_memory_reclaimed(struct kvm *kvm);
#ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
#else
static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
{
return 0;
}
#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */
typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data);
int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
uintptr_t data, const char *name,
struct task_struct **thread_ptr);
#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
{
vcpu->run->exit_reason = KVM_EXIT_INTR;
vcpu->stat.signal_exits++;
}
#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
/*
* This defines how many reserved entries we want to keep before we
* kick the vcpu to the userspace to avoid dirty ring full. This
* value can be tuned to higher if e.g. PML is enabled on the host.
*/
#define KVM_DIRTY_RING_RSVD_ENTRIES 64
/* Max number of entries allowed for each kvm dirty ring */
#define KVM_DIRTY_RING_MAX_ENTRIES 65536
#endif