blob: 2d7e61122af81566d857cde0e8540aa852fb5795 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
*
* This module enables machines with Intel VT-x extensions to run virtual
* machines without emulation or binary translation.
*
* MMU support
*
* Copyright (C) 2006 Qumranet, Inc.
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
*/
#include "irq.h"
#include "ioapic.h"
#include "mmu.h"
#include "mmu_internal.h"
#include "tdp_mmu.h"
#include "x86.h"
#include "kvm_cache_regs.h"
#include "kvm_emulate.h"
#include "cpuid.h"
#include "spte.h"
#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/kern_levels.h>
#include <linux/kthread.h>
#include <asm/page.h>
#include <asm/memtype.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/set_memory.h>
#include <asm/vmx.h>
#include <asm/kvm_page_track.h>
#include "trace.h"
#include "paging.h"
extern bool itlb_multihit_kvm_mitigation;
int __read_mostly nx_huge_pages = -1;
#ifdef CONFIG_PREEMPT_RT
/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */
static uint __read_mostly nx_huge_pages_recovery_ratio = 0;
#else
static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
#endif
static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp);
static const struct kernel_param_ops nx_huge_pages_ops = {
.set = set_nx_huge_pages,
.get = param_get_bool,
};
static const struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = {
.set = set_nx_huge_pages_recovery_ratio,
.get = param_get_uint,
};
module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
__MODULE_PARM_TYPE(nx_huge_pages, "bool");
module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops,
&nx_huge_pages_recovery_ratio, 0644);
__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
static bool __read_mostly force_flush_and_sync_on_reuse;
module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644);
/*
* When setting this variable to true it enables Two-Dimensional-Paging
* where the hardware walks 2 page tables:
* 1. the guest-virtual to guest-physical
* 2. while doing 1. it walks guest-physical to host-physical
* If the hardware supports that we don't need to do shadow paging.
*/
bool tdp_enabled = false;
static int max_huge_page_level __read_mostly;
static int tdp_root_level __read_mostly;
static int max_tdp_level __read_mostly;
enum {
AUDIT_PRE_PAGE_FAULT,
AUDIT_POST_PAGE_FAULT,
AUDIT_PRE_PTE_WRITE,
AUDIT_POST_PTE_WRITE,
AUDIT_PRE_SYNC,
AUDIT_POST_SYNC
};
#ifdef MMU_DEBUG
bool dbg = 0;
module_param(dbg, bool, 0644);
#endif
#define PTE_PREFETCH_NUM 8
#define PT32_LEVEL_BITS 10
#define PT32_LEVEL_SHIFT(level) \
(PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS)
#define PT32_LVL_OFFSET_MASK(level) \
(PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
* PT32_LEVEL_BITS))) - 1))
#define PT32_INDEX(address, level)\
(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
#define PT32_BASE_ADDR_MASK PAGE_MASK
#define PT32_DIR_BASE_ADDR_MASK \
(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))
#define PT32_LVL_ADDR_MASK(level) \
(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
* PT32_LEVEL_BITS))) - 1))
#include <trace/events/kvm.h>
/* make pte_list_desc fit well in cache lines */
#define PTE_LIST_EXT 14
/*
* Slight optimization of cacheline layout, by putting `more' and `spte_count'
* at the start; then accessing it will only use one single cacheline for
* either full (entries==PTE_LIST_EXT) case or entries<=6.
*/
struct pte_list_desc {
struct pte_list_desc *more;
/*
* Stores number of entries stored in the pte_list_desc. No need to be
* u64 but just for easier alignment. When PTE_LIST_EXT, means full.
*/
u64 spte_count;
u64 *sptes[PTE_LIST_EXT];
};
struct kvm_shadow_walk_iterator {
u64 addr;
hpa_t shadow_addr;
u64 *sptep;
int level;
unsigned index;
};
#define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker) \
for (shadow_walk_init_using_root(&(_walker), (_vcpu), \
(_root), (_addr)); \
shadow_walk_okay(&(_walker)); \
shadow_walk_next(&(_walker)))
#define for_each_shadow_entry(_vcpu, _addr, _walker) \
for (shadow_walk_init(&(_walker), _vcpu, _addr); \
shadow_walk_okay(&(_walker)); \
shadow_walk_next(&(_walker)))
#define for_each_shadow_entry_lockless(_vcpu, _addr, _walker, spte) \
for (shadow_walk_init(&(_walker), _vcpu, _addr); \
shadow_walk_okay(&(_walker)) && \
({ spte = mmu_spte_get_lockless(_walker.sptep); 1; }); \
__shadow_walk_next(&(_walker), spte))
static struct kmem_cache *pte_list_desc_cache;
struct kmem_cache *mmu_page_header_cache;
static struct percpu_counter kvm_total_used_mmu_pages;
static void mmu_spte_set(u64 *sptep, u64 spte);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
struct kvm_mmu_role_regs {
const unsigned long cr0;
const unsigned long cr4;
const u64 efer;
};
#define CREATE_TRACE_POINTS
#include "mmutrace.h"
/*
* Yes, lot's of underscores. They're a hint that you probably shouldn't be
* reading from the role_regs. Once the mmu_role is constructed, it becomes
* the single source of truth for the MMU's state.
*/
#define BUILD_MMU_ROLE_REGS_ACCESSOR(reg, name, flag) \
static inline bool __maybe_unused ____is_##reg##_##name(struct kvm_mmu_role_regs *regs)\
{ \
return !!(regs->reg & flag); \
}
BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, pg, X86_CR0_PG);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, wp, X86_CR0_WP);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pse, X86_CR4_PSE);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pae, X86_CR4_PAE);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smep, X86_CR4_SMEP);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smap, X86_CR4_SMAP);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pke, X86_CR4_PKE);
BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, la57, X86_CR4_LA57);
BUILD_MMU_ROLE_REGS_ACCESSOR(efer, nx, EFER_NX);
BUILD_MMU_ROLE_REGS_ACCESSOR(efer, lma, EFER_LMA);
/*
* The MMU itself (with a valid role) is the single source of truth for the
* MMU. Do not use the regs used to build the MMU/role, nor the vCPU. The
* regs don't account for dependencies, e.g. clearing CR4 bits if CR0.PG=1,
* and the vCPU may be incorrect/irrelevant.
*/
#define BUILD_MMU_ROLE_ACCESSOR(base_or_ext, reg, name) \
static inline bool __maybe_unused is_##reg##_##name(struct kvm_mmu *mmu) \
{ \
return !!(mmu->mmu_role. base_or_ext . reg##_##name); \
}
BUILD_MMU_ROLE_ACCESSOR(ext, cr0, pg);
BUILD_MMU_ROLE_ACCESSOR(base, cr0, wp);
BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pse);
BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pae);
BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smep);
BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smap);
BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pke);
BUILD_MMU_ROLE_ACCESSOR(ext, cr4, la57);
BUILD_MMU_ROLE_ACCESSOR(base, efer, nx);
static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu)
{
struct kvm_mmu_role_regs regs = {
.cr0 = kvm_read_cr0_bits(vcpu, KVM_MMU_CR0_ROLE_BITS),
.cr4 = kvm_read_cr4_bits(vcpu, KVM_MMU_CR4_ROLE_BITS),
.efer = vcpu->arch.efer,
};
return regs;
}
static int role_regs_to_root_level(struct kvm_mmu_role_regs *regs)
{
if (!____is_cr0_pg(regs))
return 0;
else if (____is_efer_lma(regs))
return ____is_cr4_la57(regs) ? PT64_ROOT_5LEVEL :
PT64_ROOT_4LEVEL;
else if (____is_cr4_pae(regs))
return PT32E_ROOT_LEVEL;
else
return PT32_ROOT_LEVEL;
}
static inline bool kvm_available_flush_tlb_with_range(void)
{
return kvm_x86_ops.tlb_remote_flush_with_range;
}
static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm,
struct kvm_tlb_range *range)
{
int ret = -ENOTSUPP;
if (range && kvm_x86_ops.tlb_remote_flush_with_range)
ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range);
if (ret)
kvm_flush_remote_tlbs(kvm);
}
void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
u64 start_gfn, u64 pages)
{
struct kvm_tlb_range range;
range.start_gfn = start_gfn;
range.pages = pages;
kvm_flush_remote_tlbs_with_range(kvm, &range);
}
static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
unsigned int access)
{
u64 spte = make_mmio_spte(vcpu, gfn, access);
trace_mark_mmio_spte(sptep, gfn, spte);
mmu_spte_set(sptep, spte);
}
static gfn_t get_mmio_spte_gfn(u64 spte)
{
u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)
& shadow_nonpresent_or_rsvd_mask;
return gpa >> PAGE_SHIFT;
}
static unsigned get_mmio_spte_access(u64 spte)
{
return spte & shadow_mmio_access_mask;
}
static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
{
u64 kvm_gen, spte_gen, gen;
gen = kvm_vcpu_memslots(vcpu)->generation;
if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
return false;
kvm_gen = gen & MMIO_SPTE_GEN_MASK;
spte_gen = get_mmio_spte_generation(spte);
trace_check_mmio_spte(spte, kvm_gen, spte_gen);
return likely(kvm_gen == spte_gen);
}
static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
struct x86_exception *exception)
{
return gpa;
}
static int is_cpuid_PSE36(void)
{
return 1;
}
static gfn_t pse36_gfn_delta(u32 gpte)
{
int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;
return (gpte & PT32_DIR_PSE36_MASK) << shift;
}
#ifdef CONFIG_X86_64
static void __set_spte(u64 *sptep, u64 spte)
{
WRITE_ONCE(*sptep, spte);
}
static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
WRITE_ONCE(*sptep, spte);
}
static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
return xchg(sptep, spte);
}
static u64 __get_spte_lockless(u64 *sptep)
{
return READ_ONCE(*sptep);
}
#else
union split_spte {
struct {
u32 spte_low;
u32 spte_high;
};
u64 spte;
};
static void count_spte_clear(u64 *sptep, u64 spte)
{
struct kvm_mmu_page *sp = sptep_to_sp(sptep);
if (is_shadow_present_pte(spte))
return;
/* Ensure the spte is completely set before we increase the count */
smp_wmb();
sp->clear_spte_count++;
}
static void __set_spte(u64 *sptep, u64 spte)
{
union split_spte *ssptep, sspte;
ssptep = (union split_spte *)sptep;
sspte = (union split_spte)spte;
ssptep->spte_high = sspte.spte_high;
/*
* If we map the spte from nonpresent to present, We should store
* the high bits firstly, then set present bit, so cpu can not
* fetch this spte while we are setting the spte.
*/
smp_wmb();
WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
}
static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
union split_spte *ssptep, sspte;
ssptep = (union split_spte *)sptep;
sspte = (union split_spte)spte;
WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
/*
* If we map the spte from present to nonpresent, we should clear
* present bit firstly to avoid vcpu fetch the old high bits.
*/
smp_wmb();
ssptep->spte_high = sspte.spte_high;
count_spte_clear(sptep, spte);
}
static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
union split_spte *ssptep, sspte, orig;
ssptep = (union split_spte *)sptep;
sspte = (union split_spte)spte;
/* xchg acts as a barrier before the setting of the high bits */
orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
orig.spte_high = ssptep->spte_high;
ssptep->spte_high = sspte.spte_high;
count_spte_clear(sptep, spte);
return orig.spte;
}
/*
* The idea using the light way get the spte on x86_32 guest is from
* gup_get_pte (mm/gup.c).
*
* An spte tlb flush may be pending, because kvm_set_pte_rmapp
* coalesces them and we are running out of the MMU lock. Therefore
* we need to protect against in-progress updates of the spte.
*
* Reading the spte while an update is in progress may get the old value
* for the high part of the spte. The race is fine for a present->non-present
* change (because the high part of the spte is ignored for non-present spte),
* but for a present->present change we must reread the spte.
*
* All such changes are done in two steps (present->non-present and
* non-present->present), hence it is enough to count the number of
* present->non-present updates: if it changed while reading the spte,
* we might have hit the race. This is done using clear_spte_count.
*/
static u64 __get_spte_lockless(u64 *sptep)
{
struct kvm_mmu_page *sp = sptep_to_sp(sptep);
union split_spte spte, *orig = (union split_spte *)sptep;
int count;
retry:
count = sp->clear_spte_count;
smp_rmb();
spte.spte_low = orig->spte_low;
smp_rmb();
spte.spte_high = orig->spte_high;
smp_rmb();
if (unlikely(spte.spte_low != orig->spte_low ||
count != sp->clear_spte_count))
goto retry;
return spte.spte;
}
#endif
static bool spte_has_volatile_bits(u64 spte)
{
if (!is_shadow_present_pte(spte))
return false;
/*
* Always atomically update spte if it can be updated
* out of mmu-lock, it can ensure dirty bit is not lost,
* also, it can help us to get a stable is_writable_pte()
* to ensure tlb flush is not missed.
*/
if (spte_can_locklessly_be_made_writable(spte) ||
is_access_track_spte(spte))
return true;
if (spte_ad_enabled(spte)) {
if ((spte & shadow_accessed_mask) == 0 ||
(is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0))
return true;
}
return false;
}
/* Rules for using mmu_spte_set:
* Set the sptep from nonpresent to present.
* Note: the sptep being assigned *must* be either not present
* or in a state where the hardware will not attempt to update
* the spte.
*/
static void mmu_spte_set(u64 *sptep, u64 new_spte)
{
WARN_ON(is_shadow_present_pte(*sptep));
__set_spte(sptep, new_spte);
}
/*
* Update the SPTE (excluding the PFN), but do not track changes in its
* accessed/dirty status.
*/
static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
{
u64 old_spte = *sptep;
WARN_ON(!is_shadow_present_pte(new_spte));
if (!is_shadow_present_pte(old_spte)) {
mmu_spte_set(sptep, new_spte);
return old_spte;
}
if (!spte_has_volatile_bits(old_spte))
__update_clear_spte_fast(sptep, new_spte);
else
old_spte = __update_clear_spte_slow(sptep, new_spte);
WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
return old_spte;
}
/* Rules for using mmu_spte_update:
* Update the state bits, it means the mapped pfn is not changed.
*
* Whenever we overwrite a writable spte with a read-only one we
* should flush remote TLBs. Otherwise rmap_write_protect
* will find a read-only spte, even though the writable spte
* might be cached on a CPU's TLB, the return value indicates this
* case.
*
* Returns true if the TLB needs to be flushed
*/
static bool mmu_spte_update(u64 *sptep, u64 new_spte)
{
bool flush = false;
u64 old_spte = mmu_spte_update_no_track(sptep, new_spte);
if (!is_shadow_present_pte(old_spte))
return false;
/*
* For the spte updated out of mmu-lock is safe, since
* we always atomically update it, see the comments in
* spte_has_volatile_bits().
*/
if (spte_can_locklessly_be_made_writable(old_spte) &&
!is_writable_pte(new_spte))
flush = true;
/*
* Flush TLB when accessed/dirty states are changed in the page tables,
* to guarantee consistency between TLB and page tables.
*/
if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) {
flush = true;
kvm_set_pfn_accessed(spte_to_pfn(old_spte));
}
if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) {
flush = true;
kvm_set_pfn_dirty(spte_to_pfn(old_spte));
}
return flush;
}
/*
* Rules for using mmu_spte_clear_track_bits:
* It sets the sptep from present to nonpresent, and track the
* state bits, it is used to clear the last level sptep.
* Returns the old PTE.
*/
static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
{
kvm_pfn_t pfn;
u64 old_spte = *sptep;
int level = sptep_to_sp(sptep)->role.level;
if (!spte_has_volatile_bits(old_spte))
__update_clear_spte_fast(sptep, 0ull);
else
old_spte = __update_clear_spte_slow(sptep, 0ull);
if (!is_shadow_present_pte(old_spte))
return old_spte;
kvm_update_page_stats(kvm, level, -1);
pfn = spte_to_pfn(old_spte);
/*
* KVM does not hold the refcount of the page used by
* kvm mmu, before reclaiming the page, we should
* unmap it from mmu first.
*/
WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));
if (is_accessed_spte(old_spte))
kvm_set_pfn_accessed(pfn);
if (is_dirty_spte(old_spte))
kvm_set_pfn_dirty(pfn);
return old_spte;
}
/*
* Rules for using mmu_spte_clear_no_track:
* Directly clear spte without caring the state bits of sptep,
* it is used to set the upper level spte.
*/
static void mmu_spte_clear_no_track(u64 *sptep)
{
__update_clear_spte_fast(sptep, 0ull);
}
static u64 mmu_spte_get_lockless(u64 *sptep)
{
return __get_spte_lockless(sptep);
}
/* Restore an acc-track PTE back to a regular PTE */
static u64 restore_acc_track_spte(u64 spte)
{
u64 new_spte = spte;
u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
& SHADOW_ACC_TRACK_SAVED_BITS_MASK;
WARN_ON_ONCE(spte_ad_enabled(spte));
WARN_ON_ONCE(!is_access_track_spte(spte));
new_spte &= ~shadow_acc_track_mask;
new_spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
SHADOW_ACC_TRACK_SAVED_BITS_SHIFT);
new_spte |= saved_bits;
return new_spte;
}
/* Returns the Accessed status of the PTE and resets it at the same time. */
static bool mmu_spte_age(u64 *sptep)
{
u64 spte = mmu_spte_get_lockless(sptep);
if (!is_accessed_spte(spte))
return false;
if (spte_ad_enabled(spte)) {
clear_bit((ffs(shadow_accessed_mask) - 1),
(unsigned long *)sptep);
} else {
/*
* Capture the dirty status of the page, so that it doesn't get
* lost when the SPTE is marked for access tracking.
*/
if (is_writable_pte(spte))
kvm_set_pfn_dirty(spte_to_pfn(spte));
spte = mark_spte_for_access_track(spte);
mmu_spte_update_no_track(sptep, spte);
}
return true;
}
static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
{
if (is_tdp_mmu(vcpu->arch.mmu)) {
kvm_tdp_mmu_walk_lockless_begin();
} else {
/*
* Prevent page table teardown by making any free-er wait during
* kvm_flush_remote_tlbs() IPI to all active vcpus.
*/
local_irq_disable();
/*
* Make sure a following spte read is not reordered ahead of the write
* to vcpu->mode.
*/
smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES);
}
}
static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
{
if (is_tdp_mmu(vcpu->arch.mmu)) {
kvm_tdp_mmu_walk_lockless_end();
} else {
/*
* Make sure the write to vcpu->mode is not reordered in front of
* reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us
* OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
*/
smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
local_irq_enable();
}
}
static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
{
int r;
/* 1 rmap, 1 parent PTE per level, and the prefetched rmaps. */
r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM);
if (r)
return r;
r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
PT64_ROOT_MAX_LEVEL);
if (r)
return r;
if (maybe_indirect) {
r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_gfn_array_cache,
PT64_ROOT_MAX_LEVEL);
if (r)
return r;
}
return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
PT64_ROOT_MAX_LEVEL);
}
static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache);
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache);
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_gfn_array_cache);
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache);
}
static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu)
{
return kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache);
}
static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc)
{
kmem_cache_free(pte_list_desc_cache, pte_list_desc);
}
static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
{
if (!sp->role.direct)
return sp->gfns[index];
return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS));
}
static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
{
if (!sp->role.direct) {
sp->gfns[index] = gfn;
return;
}
if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index)))
pr_err_ratelimited("gfn mismatch under direct page %llx "
"(expected %llx, got %llx)\n",
sp->gfn,
kvm_mmu_page_get_gfn(sp, index), gfn);
}
/*
* Return the pointer to the large page information for a given gfn,
* handling slots that are not large page aligned.
*/
static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
const struct kvm_memory_slot *slot, int level)
{
unsigned long idx;
idx = gfn_to_index(gfn, slot->base_gfn, level);
return &slot->arch.lpage_info[level - 2][idx];
}
static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
gfn_t gfn, int count)
{
struct kvm_lpage_info *linfo;
int i;
for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
linfo->disallow_lpage += count;
WARN_ON(linfo->disallow_lpage < 0);
}
}
void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn)
{
update_gfn_disallow_lpage_count(slot, gfn, 1);
}
void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn)
{
update_gfn_disallow_lpage_count(slot, gfn, -1);
}
static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
gfn_t gfn;
kvm->arch.indirect_shadow_pages++;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
/* the non-leaf shadow pages are keeping readonly. */
if (sp->role.level > PG_LEVEL_4K)
return kvm_slot_page_track_add_page(kvm, slot, gfn,
KVM_PAGE_TRACK_WRITE);
kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
if (sp->lpage_disallowed)
return;
++kvm->stat.nx_lpage_splits;
list_add_tail(&sp->lpage_disallowed_link,
&kvm->arch.lpage_disallowed_mmu_pages);
sp->lpage_disallowed = true;
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
gfn_t gfn;
kvm->arch.indirect_shadow_pages--;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
if (sp->role.level > PG_LEVEL_4K)
return kvm_slot_page_track_remove_page(kvm, slot, gfn,
KVM_PAGE_TRACK_WRITE);
kvm_mmu_gfn_allow_lpage(slot, gfn);
}
void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
--kvm->stat.nx_lpage_splits;
sp->lpage_disallowed = false;
list_del(&sp->lpage_disallowed_link);
}
static struct kvm_memory_slot *
gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
bool no_dirty_log)
{
struct kvm_memory_slot *slot;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
return NULL;
if (no_dirty_log && kvm_slot_dirty_track_enabled(slot))
return NULL;
return slot;
}
/*
* About rmap_head encoding:
*
* If the bit zero of rmap_head->val is clear, then it points to the only spte
* in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct
* pte_list_desc containing more mappings.
*/
/*
* Returns the number of pointers in the rmap chain, not counting the new one.
*/
static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc;
int count = 0;
if (!rmap_head->val) {
rmap_printk("%p %llx 0->1\n", spte, *spte);
rmap_head->val = (unsigned long)spte;
} else if (!(rmap_head->val & 1)) {
rmap_printk("%p %llx 1->many\n", spte, *spte);
desc = mmu_alloc_pte_list_desc(vcpu);
desc->sptes[0] = (u64 *)rmap_head->val;
desc->sptes[1] = spte;
desc->spte_count = 2;
rmap_head->val = (unsigned long)desc | 1;
++count;
} else {
rmap_printk("%p %llx many->many\n", spte, *spte);
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
while (desc->spte_count == PTE_LIST_EXT) {
count += PTE_LIST_EXT;
if (!desc->more) {
desc->more = mmu_alloc_pte_list_desc(vcpu);
desc = desc->more;
desc->spte_count = 0;
break;
}
desc = desc->more;
}
count += desc->spte_count;
desc->sptes[desc->spte_count++] = spte;
}
return count;
}
static void
pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
struct pte_list_desc *desc, int i,
struct pte_list_desc *prev_desc)
{
int j = desc->spte_count - 1;
desc->sptes[i] = desc->sptes[j];
desc->sptes[j] = NULL;
desc->spte_count--;
if (desc->spte_count)
return;
if (!prev_desc && !desc->more)
rmap_head->val = 0;
else
if (prev_desc)
prev_desc->more = desc->more;
else
rmap_head->val = (unsigned long)desc->more | 1;
mmu_free_pte_list_desc(desc);
}
static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc;
struct pte_list_desc *prev_desc;
int i;
if (!rmap_head->val) {
pr_err("%s: %p 0->BUG\n", __func__, spte);
BUG();
} else if (!(rmap_head->val & 1)) {
rmap_printk("%p 1->0\n", spte);
if ((u64 *)rmap_head->val != spte) {
pr_err("%s: %p 1->BUG\n", __func__, spte);
BUG();
}
rmap_head->val = 0;
} else {
rmap_printk("%p many->many\n", spte);
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
prev_desc = NULL;
while (desc) {
for (i = 0; i < desc->spte_count; ++i) {
if (desc->sptes[i] == spte) {
pte_list_desc_remove_entry(rmap_head,
desc, i, prev_desc);
return;
}
}
prev_desc = desc;
desc = desc->more;
}
pr_err("%s: %p many->many\n", __func__, spte);
BUG();
}
}
static void pte_list_remove(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
u64 *sptep)
{
mmu_spte_clear_track_bits(kvm, sptep);
__pte_list_remove(sptep, rmap_head);
}
/* Return true if rmap existed, false otherwise */
static bool pte_list_destroy(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc, *next;
int i;
if (!rmap_head->val)
return false;
if (!(rmap_head->val & 1)) {
mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val);
goto out;
}
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
for (; desc; desc = next) {
for (i = 0; i < desc->spte_count; i++)
mmu_spte_clear_track_bits(kvm, desc->sptes[i]);
next = desc->more;
mmu_free_pte_list_desc(desc);
}
out:
/* rmap_head is meaningless now, remember to reset it */
rmap_head->val = 0;
return true;
}
unsigned int pte_list_count(struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc;
unsigned int count = 0;
if (!rmap_head->val)
return 0;
else if (!(rmap_head->val & 1))
return 1;
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
while (desc) {
count += desc->spte_count;
desc = desc->more;
}
return count;
}
static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level,
const struct kvm_memory_slot *slot)
{
unsigned long idx;
idx = gfn_to_index(gfn, slot->base_gfn, level);
return &slot->arch.rmap[level - PG_LEVEL_4K][idx];
}
static bool rmap_can_add(struct kvm_vcpu *vcpu)
{
struct kvm_mmu_memory_cache *mc;
mc = &vcpu->arch.mmu_pte_list_desc_cache;
return kvm_mmu_memory_cache_nr_free_objects(mc);
}
static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
struct kvm_memory_slot *slot;
struct kvm_mmu_page *sp;
struct kvm_rmap_head *rmap_head;
sp = sptep_to_sp(spte);
kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
return pte_list_add(vcpu, spte, rmap_head);
}
static void rmap_remove(struct kvm *kvm, u64 *spte)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
struct kvm_mmu_page *sp;
gfn_t gfn;
struct kvm_rmap_head *rmap_head;
sp = sptep_to_sp(spte);
gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
/*
* Unlike rmap_add and rmap_recycle, rmap_remove does not run in the
* context of a vCPU so have to determine which memslots to use based
* on context information in sp->role.
*/
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
__pte_list_remove(spte, rmap_head);
}
/*
* Used by the following functions to iterate through the sptes linked by a
* rmap. All fields are private and not assumed to be used outside.
*/
struct rmap_iterator {
/* private fields */
struct pte_list_desc *desc; /* holds the sptep if not NULL */
int pos; /* index of the sptep */
};
/*
* Iteration must be started by this function. This should also be used after
* removing/dropping sptes from the rmap link because in such cases the
* information in the iterator may not be valid.
*
* Returns sptep if found, NULL otherwise.
*/
static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
struct rmap_iterator *iter)
{
u64 *sptep;
if (!rmap_head->val)
return NULL;
if (!(rmap_head->val & 1)) {
iter->desc = NULL;
sptep = (u64 *)rmap_head->val;
goto out;
}
iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
iter->pos = 0;
sptep = iter->desc->sptes[iter->pos];
out:
BUG_ON(!is_shadow_present_pte(*sptep));
return sptep;
}
/*
* Must be used with a valid iterator: e.g. after rmap_get_first().
*
* Returns sptep if found, NULL otherwise.
*/
static u64 *rmap_get_next(struct rmap_iterator *iter)
{
u64 *sptep;
if (iter->desc) {
if (iter->pos < PTE_LIST_EXT - 1) {
++iter->pos;
sptep = iter->desc->sptes[iter->pos];
if (sptep)
goto out;
}
iter->desc = iter->desc->more;
if (iter->desc) {
iter->pos = 0;
/* desc->sptes[0] cannot be NULL */
sptep = iter->desc->sptes[iter->pos];
goto out;
}
}
return NULL;
out:
BUG_ON(!is_shadow_present_pte(*sptep));
return sptep;
}
#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_) \
for (_spte_ = rmap_get_first(_rmap_head_, _iter_); \
_spte_; _spte_ = rmap_get_next(_iter_))
static void drop_spte(struct kvm *kvm, u64 *sptep)
{
u64 old_spte = mmu_spte_clear_track_bits(kvm, sptep);
if (is_shadow_present_pte(old_spte))
rmap_remove(kvm, sptep);
}
static bool __drop_large_spte(struct kvm *kvm, u64 *sptep)
{
if (is_large_pte(*sptep)) {
WARN_ON(sptep_to_sp(sptep)->role.level == PG_LEVEL_4K);
drop_spte(kvm, sptep);
return true;
}
return false;
}
static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
{
if (__drop_large_spte(vcpu->kvm, sptep)) {
struct kvm_mmu_page *sp = sptep_to_sp(sptep);
kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
KVM_PAGES_PER_HPAGE(sp->role.level));
}
}
/*
* Write-protect on the specified @sptep, @pt_protect indicates whether
* spte write-protection is caused by protecting shadow page table.
*
* Note: write protection is difference between dirty logging and spte
* protection:
* - for dirty logging, the spte can be set to writable at anytime if
* its dirty bitmap is properly set.
* - for spte protection, the spte can be writable only after unsync-ing
* shadow page.
*
* Return true if tlb need be flushed.
*/
static bool spte_write_protect(u64 *sptep, bool pt_protect)
{
u64 spte = *sptep;
if (!is_writable_pte(spte) &&
!(pt_protect && spte_can_locklessly_be_made_writable(spte)))
return false;
rmap_printk("spte %p %llx\n", sptep, *sptep);
if (pt_protect)
spte &= ~shadow_mmu_writable_mask;
spte = spte & ~PT_WRITABLE_MASK;
return mmu_spte_update(sptep, spte);
}
static bool __rmap_write_protect(struct kvm *kvm,
struct kvm_rmap_head *rmap_head,
bool pt_protect)
{
u64 *sptep;
struct rmap_iterator iter;
bool flush = false;
for_each_rmap_spte(rmap_head, &iter, sptep)
flush |= spte_write_protect(sptep, pt_protect);
return flush;
}
static bool spte_clear_dirty(u64 *sptep)
{
u64 spte = *sptep;
rmap_printk("spte %p %llx\n", sptep, *sptep);
MMU_WARN_ON(!spte_ad_enabled(spte));
spte &= ~shadow_dirty_mask;
return mmu_spte_update(sptep, spte);
}
static bool spte_wrprot_for_clear_dirty(u64 *sptep)
{
bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
(unsigned long *)sptep);
if (was_writable && !spte_ad_enabled(*sptep))
kvm_set_pfn_dirty(spte_to_pfn(*sptep));
return was_writable;
}
/*
* Gets the GFN ready for another round of dirty logging by clearing the
* - D bit on ad-enabled SPTEs, and
* - W bit on ad-disabled SPTEs.
* Returns true iff any D or W bits were cleared.
*/
static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
const struct kvm_memory_slot *slot)
{
u64 *sptep;
struct rmap_iterator iter;
bool flush = false;
for_each_rmap_spte(rmap_head, &iter, sptep)
if (spte_ad_need_write_protect(*sptep))
flush |= spte_wrprot_for_clear_dirty(sptep);
else
flush |= spte_clear_dirty(sptep);
return flush;
}
/**
* kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
* @kvm: kvm instance
* @slot: slot to protect
* @gfn_offset: start of the BITS_PER_LONG pages we care about
* @mask: indicates which pages we should protect
*
* Used when we do not need to care about huge page mappings.
*/
static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset, unsigned long mask)
{
struct kvm_rmap_head *rmap_head;
if (is_tdp_mmu_enabled(kvm))
kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
slot->base_gfn + gfn_offset, mask, true);
if (!kvm_memslots_have_rmaps(kvm))
return;
while (mask) {
rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
PG_LEVEL_4K, slot);
__rmap_write_protect(kvm, rmap_head, false);
/* clear the first set bit */
mask &= mask - 1;
}
}
/**
* kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write
* protect the page if the D-bit isn't supported.
* @kvm: kvm instance
* @slot: slot to clear D-bit
* @gfn_offset: start of the BITS_PER_LONG pages we care about
* @mask: indicates which pages we should clear D-bit
*
* Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap.
*/
static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset, unsigned long mask)
{
struct kvm_rmap_head *rmap_head;
if (is_tdp_mmu_enabled(kvm))
kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
slot->base_gfn + gfn_offset, mask, false);
if (!kvm_memslots_have_rmaps(kvm))
return;
while (mask) {
rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
PG_LEVEL_4K, slot);
__rmap_clear_dirty(kvm, rmap_head, slot);
/* clear the first set bit */
mask &= mask - 1;
}
}
/**
* kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
* PT level pages.
*
* It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
* enable dirty logging for them.
*
* We need to care about huge page mappings: e.g. during dirty logging we may
* have such mappings.
*/
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset, unsigned long mask)
{
/*
* Huge pages are NOT write protected when we start dirty logging in
* initially-all-set mode; must write protect them here so that they
* are split to 4K on the first write.
*
* The gfn_offset is guaranteed to be aligned to 64, but the base_gfn
* of memslot has no such restriction, so the range can cross two large
* pages.
*/
if (kvm_dirty_log_manual_protect_and_init_set(kvm)) {
gfn_t start = slot->base_gfn + gfn_offset + __ffs(mask);
gfn_t end = slot->base_gfn + gfn_offset + __fls(mask);
kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M);
/* Cross two large pages? */
if (ALIGN(start << PAGE_SHIFT, PMD_SIZE) !=
ALIGN(end << PAGE_SHIFT, PMD_SIZE))
kvm_mmu_slot_gfn_write_protect(kvm, slot, end,
PG_LEVEL_2M);
}
/* Now handle 4K PTEs. */
if (kvm_x86_ops.cpu_dirty_log_size)
kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask);
else
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
int kvm_cpu_dirty_log_size(void)
{
return kvm_x86_ops.cpu_dirty_log_size;
}
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn,
int min_level)
{
struct kvm_rmap_head *rmap_head;
int i;
bool write_protected = false;
if (kvm_memslots_have_rmaps(kvm)) {
for (i = min_level; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
rmap_head = gfn_to_rmap(gfn, i, slot);
write_protected |= __rmap_write_protect(kvm, rmap_head, true);
}
}
if (is_tdp_mmu_enabled(kvm))
write_protected |=
kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level);
return write_protected;
}
static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
{
struct kvm_memory_slot *slot;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K);
}
static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
const struct kvm_memory_slot *slot)
{
return pte_list_destroy(kvm, rmap_head);
}
static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn, int level,
pte_t unused)
{
return kvm_zap_rmapp(kvm, rmap_head, slot);
}
static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn, int level,
pte_t pte)
{
u64 *sptep;
struct rmap_iterator iter;
int need_flush = 0;
u64 new_spte;
kvm_pfn_t new_pfn;
WARN_ON(pte_huge(pte));
new_pfn = pte_pfn(pte);
restart:
for_each_rmap_spte(rmap_head, &iter, sptep) {
rmap_printk("spte %p %llx gfn %llx (%d)\n",
sptep, *sptep, gfn, level);
need_flush = 1;
if (pte_write(pte)) {
pte_list_remove(kvm, rmap_head, sptep);
goto restart;
} else {
new_spte = kvm_mmu_changed_pte_notifier_make_spte(
*sptep, new_pfn);
mmu_spte_clear_track_bits(kvm, sptep);
mmu_spte_set(sptep, new_spte);
}
}
if (need_flush && kvm_available_flush_tlb_with_range()) {
kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
return 0;
}
return need_flush;
}
struct slot_rmap_walk_iterator {
/* input fields. */
const struct kvm_memory_slot *slot;
gfn_t start_gfn;
gfn_t end_gfn;
int start_level;
int end_level;
/* output fields. */
gfn_t gfn;
struct kvm_rmap_head *rmap;
int level;
/* private field. */
struct kvm_rmap_head *end_rmap;
};
static void
rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
{
iterator->level = level;
iterator->gfn = iterator->start_gfn;
iterator->rmap = gfn_to_rmap(iterator->gfn, level, iterator->slot);
iterator->end_rmap = gfn_to_rmap(iterator->end_gfn, level, iterator->slot);
}
static void
slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
const struct kvm_memory_slot *slot, int start_level,
int end_level, gfn_t start_gfn, gfn_t end_gfn)
{
iterator->slot = slot;
iterator->start_level = start_level;
iterator->end_level = end_level;
iterator->start_gfn = start_gfn;
iterator->end_gfn = end_gfn;
rmap_walk_init_level(iterator, iterator->start_level);
}
static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
{
return !!iterator->rmap;
}
static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
{
if (++iterator->rmap <= iterator->end_rmap) {
iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
return;
}
if (++iterator->level > iterator->end_level) {
iterator->rmap = NULL;
return;
}
rmap_walk_init_level(iterator, iterator->level);
}
#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \
_start_gfn, _end_gfn, _iter_) \
for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \
_end_level_, _start_gfn, _end_gfn); \
slot_rmap_walk_okay(_iter_); \
slot_rmap_walk_next(_iter_))
typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn,
int level, pte_t pte);
static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
struct kvm_gfn_range *range,
rmap_handler_t handler)
{
struct slot_rmap_walk_iterator iterator;
bool ret = false;
for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
range->start, range->end - 1, &iterator)
ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn,
iterator.level, range->pte);
return ret;
}
bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool flush = false;
if (kvm_memslots_have_rmaps(kvm))
flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp);
if (is_tdp_mmu_enabled(kvm))
flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
return flush;
}
bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool flush = false;
if (kvm_memslots_have_rmaps(kvm))
flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmapp);
if (is_tdp_mmu_enabled(kvm))
flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range);
return flush;
}
static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn, int level,
pte_t unused)
{
u64 *sptep;
struct rmap_iterator iter;
int young = 0;
for_each_rmap_spte(rmap_head, &iter, sptep)
young |= mmu_spte_age(sptep);
return young;
}
static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn,
int level, pte_t unused)
{
u64 *sptep;
struct rmap_iterator iter;
for_each_rmap_spte(rmap_head, &iter, sptep)
if (is_accessed_spte(*sptep))
return 1;
return 0;
}
#define RMAP_RECYCLE_THRESHOLD 1000
static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
struct kvm_memory_slot *slot;
struct kvm_rmap_head *rmap_head;
struct kvm_mmu_page *sp;
sp = sptep_to_sp(spte);
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, __pte(0));
kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
KVM_PAGES_PER_HPAGE(sp->role.level));
}
bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool young = false;
if (kvm_memslots_have_rmaps(kvm))
young = kvm_handle_gfn_range(kvm, range, kvm_age_rmapp);
if (is_tdp_mmu_enabled(kvm))
young |= kvm_tdp_mmu_age_gfn_range(kvm, range);
return young;
}
bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool young = false;
if (kvm_memslots_have_rmaps(kvm))
young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmapp);
if (is_tdp_mmu_enabled(kvm))
young |= kvm_tdp_mmu_test_age_gfn(kvm, range);
return young;
}
#ifdef MMU_DEBUG
static int is_empty_shadow_page(u64 *spt)
{
u64 *pos;
u64 *end;
for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
if (is_shadow_present_pte(*pos)) {
printk(KERN_ERR "%s: %p %llx\n", __func__,
pos, *pos);
return 0;
}
return 1;
}
#endif
/*
* This value is the sum of all of the kvm instances's
* kvm->arch.n_used_mmu_pages values. We need a global,
* aggregate version in order to make the slab shrinker
* faster
*/
static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
}
static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
{
MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
hlist_del(&sp->hash_link);
list_del(&sp->link);
free_page((unsigned long)sp->spt);
if (!sp->role.direct)
free_page((unsigned long)sp->gfns);
kmem_cache_free(mmu_page_header_cache, sp);
}
static unsigned kvm_page_table_hashfn(gfn_t gfn)
{
return hash_64(gfn, KVM_MMU_HASH_SHIFT);
}
static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *parent_pte)
{
if (!parent_pte)
return;
pte_list_add(vcpu, parent_pte, &sp->parent_ptes);
}
static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
u64 *parent_pte)
{
__pte_list_remove(parent_pte, &sp->parent_ptes);
}
static void drop_parent_pte(struct kvm_mmu_page *sp,
u64 *parent_pte)
{
mmu_page_remove_parent_pte(sp, parent_pte);
mmu_spte_clear_no_track(parent_pte);
}
static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct)
{
struct kvm_mmu_page *sp;
sp = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache);
sp->spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_shadow_page_cache);
if (!direct)
sp->gfns = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_gfn_array_cache);
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
/*
* active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
* depends on valid pages being added to the head of the list. See
* comments in kvm_zap_obsolete_pages().
*/
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
kvm_mod_used_mmu_pages(vcpu->kvm, +1);
return sp;
}
static void mark_unsync(u64 *spte);
static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
{
u64 *sptep;
struct rmap_iterator iter;
for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) {
mark_unsync(sptep);
}
}
static void mark_unsync(u64 *spte)
{
struct kvm_mmu_page *sp;
unsigned int index;
sp = sptep_to_sp(spte);
index = spte - sp->spt;
if (__test_and_set_bit(index, sp->unsync_child_bitmap))
return;
if (sp->unsync_children++)
return;
kvm_mmu_mark_parents_unsync(sp);
}
static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp)
{
return 0;
}
#define KVM_PAGE_ARRAY_NR 16
struct kvm_mmu_pages {
struct mmu_page_and_offset {
struct kvm_mmu_page *sp;
unsigned int idx;
} page[KVM_PAGE_ARRAY_NR];
unsigned int nr;
};
static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
int idx)
{
int i;
if (sp->unsync)
for (i=0; i < pvec->nr; i++)
if (pvec->page[i].sp == sp)
return 0;
pvec->page[pvec->nr].sp = sp;
pvec->page[pvec->nr].idx = idx;
pvec->nr++;
return (pvec->nr == KVM_PAGE_ARRAY_NR);
}
static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
{
--sp->unsync_children;
WARN_ON((int)sp->unsync_children < 0);
__clear_bit(idx, sp->unsync_child_bitmap);
}
static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
struct kvm_mmu_pages *pvec)
{
int i, ret, nr_unsync_leaf = 0;
for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
struct kvm_mmu_page *child;
u64 ent = sp->spt[i];
if (!is_shadow_present_pte(ent) || is_large_pte(ent)) {
clear_unsync_child_bit(sp, i);
continue;
}
child = to_shadow_page(ent & PT64_BASE_ADDR_MASK);
if (child->unsync_children) {
if (mmu_pages_add(pvec, child, i))
return -ENOSPC;
ret = __mmu_unsync_walk(child, pvec);
if (!ret) {
clear_unsync_child_bit(sp, i);
continue;
} else if (ret > 0) {
nr_unsync_leaf += ret;
} else
return ret;
} else if (child->unsync) {
nr_unsync_leaf++;
if (mmu_pages_add(pvec, child, i))
return -ENOSPC;
} else
clear_unsync_child_bit(sp, i);
}
return nr_unsync_leaf;
}
#define INVALID_INDEX (-1)
static int mmu_unsync_walk(struct kvm_mmu_page *sp,
struct kvm_mmu_pages *pvec)
{
pvec->nr = 0;
if (!sp->unsync_children)
return 0;
mmu_pages_add(pvec, sp, INVALID_INDEX);
return __mmu_unsync_walk(sp, pvec);
}
static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
WARN_ON(!sp->unsync);
trace_kvm_mmu_sync_page(sp);
sp->unsync = 0;
--kvm->stat.mmu_unsync;
}
static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
struct list_head *invalid_list);
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
struct list_head *invalid_list);
#define for_each_valid_sp(_kvm, _sp, _list) \
hlist_for_each_entry(_sp, _list, hash_link) \
if (is_obsolete_sp((_kvm), (_sp))) { \
} else
#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \
for_each_valid_sp(_kvm, _sp, \
&(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \
if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
if (vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
return false;
}
return true;
}
static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
struct list_head *invalid_list,
bool remote_flush)
{
if (!remote_flush && list_empty(invalid_list))
return false;
if (!list_empty(invalid_list))
kvm_mmu_commit_zap_page(kvm, invalid_list);
else
kvm_flush_remote_tlbs(kvm);
return true;
}
static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
struct list_head *invalid_list,
bool remote_flush, bool local_flush)
{
if (kvm_mmu_remote_flush_or_zap(vcpu->kvm, invalid_list, remote_flush))
return;
if (local_flush)
kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}
#ifdef CONFIG_KVM_MMU_AUDIT
#include "mmu_audit.c"
#else
static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
static void mmu_audit_disable(void) { }
#endif
static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
{
return sp->role.invalid ||
unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
}
struct mmu_page_path {
struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL];
unsigned int idx[PT64_ROOT_MAX_LEVEL];
};
#define for_each_sp(pvec, sp, parents, i) \
for (i = mmu_pages_first(&pvec, &parents); \
i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
i = mmu_pages_next(&pvec, &parents, i))
static int mmu_pages_next(struct kvm_mmu_pages *pvec,
struct mmu_page_path *parents,
int i)
{
int n;
for (n = i+1; n < pvec->nr; n++) {
struct kvm_mmu_page *sp = pvec->page[n].sp;
unsigned idx = pvec->page[n].idx;
int level = sp->role.level;
parents->idx[level-1] = idx;
if (level == PG_LEVEL_4K)
break;
parents->parent[level-2] = sp;
}
return n;
}
static int mmu_pages_first(struct kvm_mmu_pages *pvec,
struct mmu_page_path *parents)
{
struct kvm_mmu_page *sp;
int level;
if (pvec->nr == 0)
return 0;
WARN_ON(pvec->page[0].idx != INVALID_INDEX);
sp = pvec->page[0].sp;
level = sp->role.level;
WARN_ON(level == PG_LEVEL_4K);
parents->parent[level-2] = sp;
/* Also set up a sentinel. Further entries in pvec are all
* children of sp, so this element is never overwritten.
*/
parents->parent[level-1] = NULL;
return mmu_pages_next(pvec, parents, 0);
}
static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
struct kvm_mmu_page *sp;
unsigned int level = 0;
do {
unsigned int idx = parents->idx[level];
sp = parents->parent[level];
if (!sp)
return;
WARN_ON(idx == INVALID_INDEX);
clear_unsync_child_bit(sp, idx);
level++;
} while (!sp->unsync_children);
}
static void mmu_sync_children(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *parent)
{
int i;
struct kvm_mmu_page *sp;
struct mmu_page_path parents;
struct kvm_mmu_pages pages;
LIST_HEAD(invalid_list);
bool flush = false;
while (mmu_unsync_walk(parent, &pages)) {
bool protected = false;
for_each_sp(pages, sp, parents, i)
protected |= rmap_write_protect(vcpu, sp->gfn);
if (protected) {
kvm_flush_remote_tlbs(vcpu->kvm);
flush = false;
}
for_each_sp(pages, sp, parents, i) {
kvm_unlink_unsync_page(vcpu->kvm, sp);
flush |= kvm_sync_page(vcpu, sp, &invalid_list);
mmu_pages_clear_parents(&parents);
}
if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
flush = false;
}
}
kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
}
static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
{
atomic_set(&sp->write_flooding_count, 0);
}
static void clear_sp_write_flooding_count(u64 *spte)
{
__clear_sp_write_flooding_count(sptep_to_sp(spte));
}
static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
gfn_t gfn,
gva_t gaddr,
unsigned level,
int direct,
unsigned int access)
{
bool direct_mmu = vcpu->arch.mmu->direct_map;
union kvm_mmu_page_role role;
struct hlist_head *sp_list;
unsigned quadrant;
struct kvm_mmu_page *sp;
int collisions = 0;
LIST_HEAD(invalid_list);
role = vcpu->arch.mmu->mmu_role.base;
role.level = level;
role.direct = direct;
if (role.direct)
role.gpte_is_8_bytes = true;
role.access = access;
if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
}
sp_list = &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)];
for_each_valid_sp(vcpu->kvm, sp, sp_list) {
if (sp->gfn != gfn) {
collisions++;
continue;
}
if (sp->role.word != role.word) {
/*
* If the guest is creating an upper-level page, zap
* unsync pages for the same gfn. While it's possible
* the guest is using recursive page tables, in all
* likelihood the guest has stopped using the unsync
* page and is installing a completely unrelated page.
* Unsync pages must not be left as is, because the new
* upper-level page will be write-protected.
*/
if (level > PG_LEVEL_4K && sp->unsync)
kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
&invalid_list);
continue;
}
if (direct_mmu)
goto trace_get_page;
if (sp->unsync) {
/*
* The page is good, but is stale. kvm_sync_page does
* get the latest guest state, but (unlike mmu_unsync_children)
* it doesn't write-protect the page or mark it synchronized!
* This way the validity of the mapping is ensured, but the
* overhead of write protection is not incurred until the
* guest invalidates the TLB mapping. This allows multiple
* SPs for a single gfn to be unsync.
*
* If the sync fails, the page is zapped. If so, break
* in order to rebuild it.
*/
if (!kvm_sync_page(vcpu, sp, &invalid_list))
break;
WARN_ON(!list_empty(&invalid_list));
kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}
if (sp->unsync_children)
kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
__clear_sp_write_flooding_count(sp);
trace_get_page:
trace_kvm_mmu_get_page(sp, false);
goto out;
}
++vcpu->kvm->stat.mmu_cache_miss;
sp = kvm_mmu_alloc_page(vcpu, direct);
sp->gfn = gfn;
sp->role = role;
hlist_add_head(&sp->hash_link, sp_list);
if (!direct) {
account_shadowed(vcpu->kvm, sp);
if (level == PG_LEVEL_4K && rmap_write_protect(vcpu, gfn))
kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, 1);
}
trace_kvm_mmu_get_page(sp, true);
out:
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
if (collisions > vcpu->kvm->stat.max_mmu_page_hash_collisions)
vcpu->kvm->stat.max_mmu_page_hash_collisions = collisions;
return sp;
}
static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterator,
struct kvm_vcpu *vcpu, hpa_t root,
u64 addr)
{
iterator->addr = addr;
iterator->shadow_addr = root;
iterator->level = vcpu->arch.mmu->shadow_root_level;
if (iterator->level == PT64_ROOT_4LEVEL &&
vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
!vcpu->arch.mmu->direct_map)
--iterator->level;
if (iterator->level == PT32E_ROOT_LEVEL) {
/*
* prev_root is currently only used for 64-bit hosts. So only
* the active root_hpa is valid here.
*/
BUG_ON(root != vcpu->arch.mmu->root_hpa);
iterator->shadow_addr
= vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
--iterator->level;
if (!iterator->shadow_addr)
iterator->level = 0;
}
}
static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
struct kvm_vcpu *vcpu, u64 addr)
{
shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root_hpa,
addr);
}
static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
{
if (iterator->level < PG_LEVEL_4K)
return false;
iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
return true;
}
static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator,
u64 spte)
{
if (is_last_spte(spte, iterator->level)) {
iterator->level = 0;
return;
}
iterator->shadow_addr = spte & PT64_BASE_ADDR_MASK;
--iterator->level;
}
static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
{
__shadow_walk_next(iterator, *iterator->sptep);
}
static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
struct kvm_mmu_page *sp)
{
u64 spte;
BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp));
mmu_spte_set(sptep, spte);
mmu_page_add_parent_pte(vcpu, sp, sptep);
if (sp->unsync_children || sp->unsync)
mark_unsync(sptep);
}
static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned direct_access)
{
if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) {
struct kvm_mmu_page *child;
/*
* For the direct sp, if the guest pte's dirty bit
* changed form clean to dirty, it will corrupt the
* sp's access: allow writable in the read-only sp,
* so we should update the spte at this point to get
* a new sp with the correct access.
*/
child = to_shadow_page(*sptep & PT64_BASE_ADDR_MASK);
if (child->role.access == direct_access)
return;
drop_parent_pte(child, sptep);
kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
}
}
/* Returns the number of zapped non-leaf child shadow pages. */
static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
u64 *spte, struct list_head *invalid_list)
{
u64 pte;
struct kvm_mmu_page *child;
pte = *spte;
if (is_shadow_present_pte(pte)) {
if (is_last_spte(pte, sp->role.level)) {
drop_spte(kvm, spte);
} else {
child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
drop_parent_pte(child, spte);
/*
* Recursively zap nested TDP SPs, parentless SPs are
* unlikely to be used again in the near future. This
* avoids retaining a large number of stale nested SPs.
*/
if (tdp_enabled && invalid_list &&
child->role.guest_mode && !child->parent_ptes.val)
return kvm_mmu_prepare_zap_page(kvm, child,
invalid_list);
}
} else if (is_mmio_spte(pte)) {
mmu_spte_clear_no_track(spte);
}
return 0;
}
static int kvm_mmu_page_unlink_children(struct kvm *kvm,
struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
int zapped = 0;
unsigned i;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
zapped += mmu_page_zap_pte(kvm, sp, sp->spt + i, invalid_list);
return zapped;
}
static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
u64 *sptep;
struct rmap_iterator iter;
while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
drop_parent_pte(sp, sptep);
}
static int mmu_zap_unsync_children(struct kvm *kvm,
struct kvm_mmu_page *parent,
struct list_head *invalid_list)
{
int i, zapped = 0;
struct mmu_page_path parents;
struct kvm_mmu_pages pages;
if (parent->role.level == PG_LEVEL_4K)
return 0;
while (mmu_unsync_walk(parent, &pages)) {
struct kvm_mmu_page *sp;
for_each_sp(pages, sp, parents, i) {
kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
mmu_pages_clear_parents(&parents);
zapped++;
}
}
return zapped;
}
static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
struct kvm_mmu_page *sp,
struct list_head *invalid_list,
int *nr_zapped)
{
bool list_unstable;
trace_kvm_mmu_prepare_zap_page(sp);
++kvm->stat.mmu_shadow_zapped;
*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
*nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list);
kvm_mmu_unlink_parents(kvm, sp);
/* Zapping children means active_mmu_pages has become unstable. */
list_unstable = *nr_zapped;
if (!sp->role.invalid && !sp->role.direct)
unaccount_shadowed(kvm, sp);
if (sp->unsync)
kvm_unlink_unsync_page(kvm, sp);
if (!sp->root_count) {
/* Count self */
(*nr_zapped)++;
/*
* Already invalid pages (previously active roots) are not on
* the active page list. See list_del() in the "else" case of
* !sp->root_count.
*/
if (sp->role.invalid)
list_add(&sp->link, invalid_list);
else
list_move(&sp->link, invalid_list);
kvm_mod_used_mmu_pages(kvm, -1);
} else {
/*
* Remove the active root from the active page list, the root
* will be explicitly freed when the root_count hits zero.
*/
list_del(&sp->link);
/*
* Obsolete pages cannot be used on any vCPUs, see the comment
* in kvm_mmu_zap_all_fast(). Note, is_obsolete_sp() also
* treats invalid shadow pages as being obsolete.
*/
if (!is_obsolete_sp(kvm, sp))
kvm_reload_remote_mmus(kvm);
}
if (sp->lpage_disallowed)
unaccount_huge_nx_page(kvm, sp);
sp->role.invalid = 1;
return list_unstable;
}
static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
int nr_zapped;
__kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped);
return nr_zapped;
}
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
struct list_head *invalid_list)
{
struct kvm_mmu_page *sp, *nsp;
if (list_empty(invalid_list))
return;
/*
* We need to make sure everyone sees our modifications to
* the page tables and see changes to vcpu->mode here. The barrier
* in the kvm_flush_remote_tlbs() achieves this. This pairs
* with vcpu_enter_guest and walk_shadow_page_lockless_begin/end.
*
* In addition, kvm_flush_remote_tlbs waits for all vcpus to exit
* guest mode and/or lockless shadow page table walks.
*/
kvm_flush_remote_tlbs(kvm);
list_for_each_entry_safe(sp, nsp, invalid_list, link) {
WARN_ON(!sp->role.invalid || sp->root_count);
kvm_mmu_free_page(sp);
}
}
static unsigned long kvm_mmu_zap_oldest_mmu_pages(struct kvm *kvm,
unsigned long nr_to_zap)
{
unsigned long total_zapped = 0;
struct kvm_mmu_page *sp, *tmp;
LIST_HEAD(invalid_list);
bool unstable;
int nr_zapped;
if (list_empty(&kvm->arch.active_mmu_pages))
return 0;
restart:
list_for_each_entry_safe_reverse(sp, tmp, &kvm->arch.active_mmu_pages, link) {
/*
* Don't zap active root pages, the page itself can't be freed
* and zapping it will just force vCPUs to realloc and reload.
*/
if (sp->root_count)
continue;
unstable = __kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list,
&nr_zapped);
total_zapped += nr_zapped;
if (total_zapped >= nr_to_zap)
break;
if (unstable)
goto restart;
}
kvm_mmu_commit_zap_page(kvm, &invalid_list);
kvm->stat.mmu_recycled += total_zapped;
return total_zapped;
}
static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
{
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
return kvm->arch.n_max_mmu_pages -
kvm->arch.n_used_mmu_pages;
return 0;
}
static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
{
unsigned long avail = kvm_mmu_available_pages(vcpu->kvm);
if (likely(avail >= KVM_MIN_FREE_MMU_PAGES))
return 0;
kvm_mmu_zap_oldest_mmu_pages(vcpu->kvm, KVM_REFILL_PAGES - avail);
/*
* Note, this check is intentionally soft, it only guarantees that one
* page is available, while the caller may end up allocating as many as
* four pages, e.g. for PAE roots or for 5-level paging. Temporarily
* exceeding the (arbitrary by default) limit will not harm the host,
* being too aggressive may unnecessarily kill the guest, and getting an
* exact count is far more trouble than it's worth, especially in the
* page fault paths.
*/
if (!kvm_mmu_available_pages(vcpu->kvm))
return -ENOSPC;
return 0;
}
/*
* Changing the number of mmu pages allocated to the vm
* Note: if goal_nr_mmu_pages is too small, you will get dead lock
*/
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
write_lock(&kvm->mmu_lock);
if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages -
goal_nr_mmu_pages);
goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
}
kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
write_unlock(&kvm->mmu_lock);
}
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
{
struct kvm_mmu_page *sp;
LIST_HEAD(invalid_list);
int r;
pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
r = 0;
write_lock(&kvm->mmu_lock);
for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
sp->role.word);
r = 1;
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
}
kvm_mmu_commit_zap_page(kvm, &invalid_list);
write_unlock(&kvm->mmu_lock);
return r;
}
static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
{
gpa_t gpa;
int r;
if (vcpu->arch.mmu->direct_map)
return 0;
gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
return r;
}
static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
trace_kvm_mmu_unsync_page(sp);
++vcpu->kvm->stat.mmu_unsync;
sp->unsync = 1;
kvm_mmu_mark_parents_unsync(sp);
}
/*
* Attempt to unsync any shadow pages that can be reached by the specified gfn,
* KVM is creating a writable mapping for said gfn. Returns 0 if all pages
* were marked unsync (or if there is no shadow page), -EPERM if the SPTE must
* be write-protected.
*/
int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
{
struct kvm_mmu_page *sp;
bool locked = false;
/*
* Force write-protection if the page is being tracked. Note, the page
* track machinery is used to write-protect upper-level shadow pages,
* i.e. this guards the role.level == 4K assertion below!
*/
if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
return -EPERM;
/*
* The page is not write-tracked, mark existing shadow pages unsync
* unless KVM is synchronizing an unsync SP (can_unsync = false). In
* that case, KVM must complete emulation of the guest TLB flush before
* allowing shadow pages to become unsync (writable by the guest).
*/
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (!can_unsync)
return -EPERM;
if (sp->unsync)
continue;
/*
* TDP MMU page faults require an additional spinlock as they
* run with mmu_lock held for read, not write, and the unsync
* logic is not thread safe. Take the spinklock regardless of
* the MMU type to avoid extra conditionals/parameters, there's
* no meaningful penalty if mmu_lock is held for write.
*/
if (!locked) {
locked = true;
spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
/*
* Recheck after taking the spinlock, a different vCPU
* may have since marked the page unsync. A false
* positive on the unprotected check above is not
* possible as clearing sp->unsync _must_ hold mmu_lock
* for write, i.e. unsync cannot transition from 0->1
* while this CPU holds mmu_lock for read (or write).
*/
if (READ_ONCE(sp->unsync))
continue;
}
WARN_ON(sp->role.level != PG_LEVEL_4K);
kvm_unsync_page(vcpu, sp);
}
if (locked)
spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
/*
* We need to ensure that the marking of unsync pages is visible
* before the SPTE is updated to allow writes because
* kvm_mmu_sync_roots() checks the unsync flags without holding
* the MMU lock and so can race with this. If the SPTE was updated
* before the page had been marked as unsync-ed, something like the
* following could happen:
*
* CPU 1 CPU 2
* ---------------------------------------------------------------------
* 1.2 Host updates SPTE
* to be writable
* 2.1 Guest writes a GPTE for GVA X.
* (GPTE being in the guest page table shadowed
* by the SP from CPU 1.)
* This reads SPTE during the page table walk.
* Since SPTE.W is read as 1, there is no
* fault.
*
* 2.2 Guest issues TLB flush.
* That causes a VM Exit.
*
* 2.3 Walking of unsync pages sees sp->unsync is
* false and skips the page.
*
* 2.4 Guest accesses GVA X.
* Since the mapping in the SP was not updated,
* so the old mapping for GVA X incorrectly
* gets used.
* 1.1 Host marks SP
* as unsync
* (sp->unsync = true)
*
* The write barrier below ensures that 1.1 happens before 1.2 and thus
* the situation in 2.4 does not arise. The implicit barrier in 2.2
* pairs with this write barrier.
*/
smp_wmb();
return 0;
}
static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned int pte_access, int level,
gfn_t gfn, kvm_pfn_t pfn, bool speculative,
bool can_unsync, bool host_writable)
{
u64 spte;
struct kvm_mmu_page *sp;
int ret;
sp = sptep_to_sp(sptep);
ret = make_spte(vcpu, pte_access, level, gfn, pfn, *sptep, speculative,
can_unsync, host_writable, sp_ad_disabled(sp), &spte);
if (spte & PT_WRITABLE_MASK)
kvm_vcpu_mark_page_dirty(vcpu, gfn);
if (*sptep == spte)
ret |= SET_SPTE_SPURIOUS;
else if (mmu_spte_update(sptep, spte))
ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
return ret;
}
static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned int pte_access, bool write_fault, int level,
gfn_t gfn, kvm_pfn_t pfn, bool speculative,
bool host_writable)
{
int was_rmapped = 0;
int rmap_count;
int set_spte_ret;
int ret = RET_PF_FIXED;
bool flush = false;
pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
*sptep, write_fault, gfn);
if (unlikely(is_noslot_pfn(pfn))) {
mark_mmio_spte(vcpu, sptep, gfn, pte_access);
return RET_PF_EMULATE;
}
if (is_shadow_present_pte(*sptep)) {
/*
* If we overwrite a PTE page pointer with a 2MB PMD, unlink
* the parent of the now unreachable PTE.
*/
if (level > PG_LEVEL_4K && !is_large_pte(*sptep)) {
struct kvm_mmu_page *child;
u64 pte = *sptep;
child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
drop_parent_pte(child, sptep);
flush = true;
} else if (pfn != spte_to_pfn(*sptep)) {
pgprintk("hfn old %llx new %llx\n",
spte_to_pfn(*sptep), pfn);
drop_spte(vcpu->kvm, sptep);
flush = true;
} else
was_rmapped = 1;
}
set_spte_ret = set_spte(vcpu, sptep, pte_access, level, gfn, pfn,
speculative, true, host_writable);
if (set_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) {
if (write_fault)
ret = RET_PF_EMULATE;
kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}
if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH || flush)
kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
KVM_PAGES_PER_HPAGE(level));
/*
* The fault is fully spurious if and only if the new SPTE and old SPTE
* are identical, and emulation is not required.
*/
if ((set_spte_ret & SET_SPTE_SPURIOUS) && ret == RET_PF_FIXED) {
WARN_ON_ONCE(!was_rmapped);
return RET_PF_SPURIOUS;
}
pgprintk("%s: setting spte %llx\n", __func__, *sptep);
trace_kvm_mmu_set_spte(level, gfn, sptep);
if (!was_rmapped) {
kvm_update_page_stats(vcpu->kvm, level, 1);
rmap_count = rmap_add(vcpu, sptep, gfn);
if (rmap_count > RMAP_RECYCLE_THRESHOLD)
rmap_recycle(vcpu, sptep, gfn);
}
return ret;
}
static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
bool no_dirty_log)
{
struct kvm_memory_slot *slot;
slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
if (!slot)
return KVM_PFN_ERR_FAULT;
return gfn_to_pfn_memslot_atomic(slot, gfn);
}
static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp,
u64 *start, u64 *end)
{
struct page *pages[PTE_PREFETCH_NUM];
struct kvm_memory_slot *slot;
unsigned int access = sp->role.access;
int i, ret;
gfn_t gfn;
gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
if (!slot)
return -1;
ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
if (ret <= 0)
return -1;
for (i = 0; i < ret; i++, gfn++, start++) {
mmu_set_spte(vcpu, start, access, false, sp->role.level, gfn,
page_to_pfn(pages[i]), true, true);
put_page(pages[i]);
}
return 0;
}
static void __direct_pte_prefetch(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *sptep)
{
u64 *spte, *start = NULL;
int i;
WARN_ON(!sp->role.direct);
i = (sptep - sp->spt) & ~(PTE_PREFETCH_NUM - 1);
spte = sp->spt + i;
for (i = 0; i < PTE_PREFETCH_NUM; i