*/
#include "mmu.h"
+#include "x86.h"
#include "kvm_cache_regs.h"
#include <linux/kvm_host.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
+#include <linux/srcu.h>
#include <asm/page.h>
#include <asm/cmpxchg.h>
#define PFERR_RSVD_MASK (1U << 3)
#define PFERR_FETCH_MASK (1U << 4)
-#define PT_PDPE_LEVEL 3
-#define PT_DIRECTORY_LEVEL 2
-#define PT_PAGE_TABLE_LEVEL 1
-
#define RMAP_EXT 4
#define ACC_EXEC_MASK 1
#define ACC_USER_MASK PT_USER_MASK
#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+#include <trace/events/kvm.h>
+
+#undef TRACE_INCLUDE_FILE
#define CREATE_TRACE_POINTS
#include "mmutrace.h"
+#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
struct kvm_rmap_desc {
static int is_write_protection(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr0 & X86_CR0_WP;
+ return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
}
static int is_cpuid_PSE36(void)
static int is_nx(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.shadow_efer & EFER_NX;
+ return vcpu->arch.efer & EFER_NX;
}
static int is_shadow_present_pte(u64 pte)
return pte & PT_PAGE_SIZE_MASK;
}
-static int is_writeble_pte(unsigned long pte)
+static int is_writable_pte(unsigned long pte)
{
return pte & PT_WRITABLE_MASK;
}
static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
{
- unsigned long page_size = PAGE_SIZE;
- struct vm_area_struct *vma;
- unsigned long addr;
+ unsigned long page_size;
int i, ret = 0;
- addr = gfn_to_hva(kvm, gfn);
- if (kvm_is_error_hva(addr))
- return page_size;
-
- down_read(¤t->mm->mmap_sem);
- vma = find_vma(current->mm, addr);
- if (!vma)
- goto out;
-
- page_size = vma_kernel_pagesize(vma);
-
-out:
- up_read(¤t->mm->mmap_sem);
+ page_size = kvm_host_page_size(kvm, gfn);
for (i = PT_PAGE_TABLE_LEVEL;
i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) {
static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
struct kvm_memory_slot *slot;
- int host_level;
- int level = PT_PAGE_TABLE_LEVEL;
+ int host_level, level, max_level;
slot = gfn_to_memslot(vcpu->kvm, large_gfn);
if (slot && slot->dirty_bitmap)
if (host_level == PT_PAGE_TABLE_LEVEL)
return host_level;
- for (level = PT_DIRECTORY_LEVEL; level <= host_level; ++level) {
+ max_level = kvm_x86_ops->get_lpage_level() < host_level ?
+ kvm_x86_ops->get_lpage_level() : host_level;
+ for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
break;
- }
return level - 1;
}
pfn = spte_to_pfn(*spte);
if (*spte & shadow_accessed_mask)
kvm_set_pfn_accessed(pfn);
- if (is_writeble_pte(*spte))
- kvm_release_pfn_dirty(pfn);
- else
- kvm_release_pfn_clean(pfn);
+ if (is_writable_pte(*spte))
+ kvm_set_pfn_dirty(pfn);
rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level);
if (!*rmapp) {
printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
prev_desc = desc;
desc = desc->more;
}
+ pr_err("rmap_remove: %p %llx many->many\n", spte, *spte);
BUG();
}
}
BUG_ON(!spte);
BUG_ON(!(*spte & PT_PRESENT_MASK));
rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
- if (is_writeble_pte(*spte)) {
+ if (is_writable_pte(*spte)) {
__set_spte(spte, *spte & ~PT_WRITABLE_MASK);
write_protected = 1;
}
BUG_ON(!(*spte & PT_PRESENT_MASK));
BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK));
pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
- if (is_writeble_pte(*spte)) {
+ if (is_writable_pte(*spte)) {
rmap_remove(kvm, spte);
--kvm->stat.lpages;
__set_spte(spte, shadow_trap_nonpresent_pte);
return write_protected;
}
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
{
u64 *spte;
int need_tlb_flush = 0;
return need_tlb_flush;
}
+static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
+{
+ int need_flush = 0;
+ u64 *spte, new_spte;
+ pte_t *ptep = (pte_t *)data;
+ pfn_t new_pfn;
+
+ WARN_ON(pte_huge(*ptep));
+ new_pfn = pte_pfn(*ptep);
+ spte = rmap_next(kvm, rmapp, NULL);
+ while (spte) {
+ BUG_ON(!is_shadow_present_pte(*spte));
+ rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
+ need_flush = 1;
+ if (pte_write(*ptep)) {
+ rmap_remove(kvm, spte);
+ __set_spte(spte, shadow_trap_nonpresent_pte);
+ spte = rmap_next(kvm, rmapp, NULL);
+ } else {
+ new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
+ new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+ new_spte &= ~PT_WRITABLE_MASK;
+ new_spte &= ~SPTE_HOST_WRITEABLE;
+ if (is_writable_pte(*spte))
+ kvm_set_pfn_dirty(spte_to_pfn(*spte));
+ __set_spte(spte, new_spte);
+ spte = rmap_next(kvm, rmapp, spte);
+ }
+ }
+ if (need_flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ return 0;
+}
+
static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
- int (*handler)(struct kvm *kvm, unsigned long *rmapp))
+ unsigned long data,
+ int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data))
{
int i, j;
+ int ret;
int retval = 0;
+ struct kvm_memslots *slots;
- /*
- * If mmap_sem isn't taken, we can look the memslots with only
- * the mmu_lock by skipping over the slots with userspace_addr == 0.
- */
- for (i = 0; i < kvm->nmemslots; i++) {
- struct kvm_memory_slot *memslot = &kvm->memslots[i];
+ slots = rcu_dereference(kvm->memslots);
+
+ for (i = 0; i < slots->nmemslots; i++) {
+ struct kvm_memory_slot *memslot = &slots->memslots[i];
unsigned long start = memslot->userspace_addr;
unsigned long end;
- /* mmu_lock protects userspace_addr */
- if (!start)
- continue;
-
end = start + (memslot->npages << PAGE_SHIFT);
if (hva >= start && hva < end) {
gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
- retval |= handler(kvm, &memslot->rmap[gfn_offset]);
+ ret = handler(kvm, &memslot->rmap[gfn_offset], data);
for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
int idx = gfn_offset;
idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j);
- retval |= handler(kvm,
- &memslot->lpage_info[j][idx].rmap_pde);
+ ret |= handler(kvm,
+ &memslot->lpage_info[j][idx].rmap_pde,
+ data);
}
+ trace_kvm_age_page(hva, memslot, ret);
+ retval |= ret;
}
}
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
- return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+ return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
}
-static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+ kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long data)
{
u64 *spte;
int young = 0;
- /* always return old for EPT */
+ /*
+ * Emulate the accessed bit for EPT, by checking if this page has
+ * an EPT mapping, and clearing it if it does. On the next access,
+ * a new EPT mapping will be established.
+ * This has some overhead, but not as much as the cost of swapping
+ * out actively used pages or breaking up actively used hugepages.
+ */
if (!shadow_accessed_mask)
- return 0;
+ return kvm_unmap_rmapp(kvm, rmapp, data);
spte = rmap_next(kvm, rmapp, NULL);
while (spte) {
gfn = unalias_gfn(vcpu->kvm, gfn);
rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
- kvm_unmap_rmapp(vcpu->kvm, rmapp);
+ kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
kvm_flush_remote_tlbs(vcpu->kvm);
}
int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
- return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+ return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
}
#ifdef MMU_DEBUG
static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
{
- int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn));
+ int slot = memslot_id(kvm, gfn);
struct kvm_mmu_page *sp = page_header(__pa(pte));
__set_bit(slot, sp->slot_bitmap);
unsigned pte_access, int user_fault,
int write_fault, int dirty, int level,
gfn_t gfn, pfn_t pfn, bool speculative,
- bool can_unsync)
+ bool can_unsync, bool reset_host_protection)
{
u64 spte;
int ret = 0;
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
kvm_is_mmio_pfn(pfn));
+ if (reset_host_protection)
+ spte |= SPTE_HOST_WRITEABLE;
+
spte |= (u64)pfn << PAGE_SHIFT;
if ((pte_access & ACC_WRITE_MASK)
* is responsibility of mmu_get_page / kvm_sync_page.
* Same reasoning can be applied to dirty page accounting.
*/
- if (!can_unsync && is_writeble_pte(*sptep))
+ if (!can_unsync && is_writable_pte(*sptep))
goto set_pte;
if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
__func__, gfn);
ret = 1;
pte_access &= ~ACC_WRITE_MASK;
- if (is_writeble_pte(spte))
+ if (is_writable_pte(spte))
spte &= ~PT_WRITABLE_MASK;
}
}
unsigned pt_access, unsigned pte_access,
int user_fault, int write_fault, int dirty,
int *ptwrite, int level, gfn_t gfn,
- pfn_t pfn, bool speculative)
+ pfn_t pfn, bool speculative,
+ bool reset_host_protection)
{
int was_rmapped = 0;
- int was_writeble = is_writeble_pte(*sptep);
+ int was_writable = is_writable_pte(*sptep);
int rmap_count;
pgprintk("%s: spte %llx access %x write_fault %d"
}
if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
- dirty, level, gfn, pfn, speculative, true)) {
+ dirty, level, gfn, pfn, speculative, true,
+ reset_host_protection)) {
if (write_fault)
*ptwrite = 1;
kvm_x86_ops->tlb_flush(vcpu);
page_header_update_slot(vcpu->kvm, sptep, gfn);
if (!was_rmapped) {
rmap_count = rmap_add(vcpu, sptep, gfn);
- if (!is_rmap_spte(*sptep))
- kvm_release_pfn_clean(pfn);
+ kvm_release_pfn_clean(pfn);
if (rmap_count > RMAP_RECYCLE_THRESHOLD)
rmap_recycle(vcpu, sptep, gfn);
} else {
- if (was_writeble)
+ if (was_writable)
kvm_release_pfn_dirty(pfn);
else
kvm_release_pfn_clean(pfn);
if (iterator.level == level) {
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
0, write, 1, &pt_write,
- level, gfn, pfn, false);
+ level, gfn, pfn, false, true);
++vcpu->stat.pf_fixed;
break;
}
gpa_t gpa;
int r;
+ if (tdp_enabled)
+ return 0;
+
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
spin_lock(&vcpu->kvm->mmu_lock);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
{
- while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES) {
+ while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES &&
+ !list_empty(&vcpu->kvm->arch.active_mmu_pages)) {
struct kvm_mmu_page *sp;
sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev,
if (r)
goto out;
- er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0);
+ er = emulate_instruction(vcpu, cr2, error_code, 0);
switch (er) {
case EMULATE_DONE:
case EMULATE_FAIL:
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
return 0;
default:
BUG();
ASSERT(vcpu);
- spin_lock(&vcpu->kvm->mmu_lock);
- if (vcpu->kvm->arch.n_requested_mmu_pages)
- vcpu->kvm->arch.n_free_mmu_pages =
- vcpu->kvm->arch.n_requested_mmu_pages;
- else
- vcpu->kvm->arch.n_free_mmu_pages =
- vcpu->kvm->arch.n_alloc_mmu_pages;
- spin_unlock(&vcpu->kvm->mmu_lock);
/*
* When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
* Therefore we need to allocate shadow page tables in the first
*/
page = alloc_page(GFP_KERNEL | __GFP_DMA32);
if (!page)
- goto error_1;
+ return -ENOMEM;
+
vcpu->arch.mmu.pae_root = page_address(page);
for (i = 0; i < 4; ++i)
vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
return 0;
-
-error_1:
- free_mmu_pages(vcpu);
- return -ENOMEM;
}
int kvm_mmu_create(struct kvm_vcpu *vcpu)
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
- int npages;
+ int npages, idx;
- if (!down_read_trylock(&kvm->slots_lock))
- continue;
+ idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
npages = kvm->arch.n_alloc_mmu_pages -
kvm->arch.n_free_mmu_pages;
nr_to_scan--;
spin_unlock(&kvm->mmu_lock);
- up_read(&kvm->slots_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
}
if (kvm_freed)
list_move_tail(&kvm_freed->vm_list, &vm_list);
int i;
unsigned int nr_mmu_pages;
unsigned int nr_pages = 0;
+ struct kvm_memslots *slots;
- for (i = 0; i < kvm->nmemslots; i++)
- nr_pages += kvm->memslots[i].npages;
+ slots = rcu_dereference(kvm->memslots);
+ for (i = 0; i < slots->nmemslots; i++)
+ nr_pages += slots->memslots[i].npages;
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
nr_mmu_pages = max(nr_mmu_pages,
static int count_rmaps(struct kvm_vcpu *vcpu)
{
int nmaps = 0;
- int i, j, k;
+ int i, j, k, idx;
+ idx = srcu_read_lock(&kvm->srcu);
+ slots = rcu_dereference(kvm->memslots);
for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
- struct kvm_memory_slot *m = &vcpu->kvm->memslots[i];
+ struct kvm_memory_slot *m = &slots->memslots[i];
struct kvm_rmap_desc *d;
for (j = 0; j < m->npages; ++j) {
}
}
}
+ srcu_read_unlock(&kvm->srcu, idx);
return nmaps;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff