#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/kern_levels.h>
+#include <linux/kthread.h>
#include <asm/page.h>
+#include <asm/pat.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>
#include <asm/kvm_page_track.h>
#include "trace.h"
+extern bool itlb_multihit_kvm_mitigation;
+
+static int __read_mostly nx_huge_pages = -1;
+static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
+
+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 struct kernel_param_ops nx_huge_pages_ops = {
+ .set = set_nx_huge_pages,
+ .get = param_get_bool,
+};
+
+static 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");
+
/*
* When setting this variable to true it enables Two-Dimensional-Paging
* where the hardware walks 2 page tables:
#include <trace/events/kvm.h>
-#define CREATE_TRACE_POINTS
-#include "mmutrace.h"
-
#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
PT64_EPT_EXECUTABLE_MASK;
static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT;
+/*
+ * This mask must be set on all non-zero Non-Present or Reserved SPTEs in order
+ * to guard against L1TF attacks.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
+
+/*
+ * The number of high-order 1 bits to use in the mask above.
+ */
+static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
+
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts. This mask covers the lower bits of the GFN.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+
static void mmu_spte_set(u64 *sptep, u64 spte);
static void mmu_free_roots(struct kvm_vcpu *vcpu);
+static bool is_executable_pte(u64 spte);
+
+#define CREATE_TRACE_POINTS
+#include "mmutrace.h"
+
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
{
return !(spte & shadow_acc_track_value);
}
+static bool is_nx_huge_page_enabled(void)
+{
+ return READ_ONCE(nx_huge_pages);
+}
+
static inline u64 spte_shadow_accessed_mask(u64 spte)
{
MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
{
unsigned int gen = kvm_current_mmio_generation(vcpu);
u64 mask = generation_mmio_spte_mask(gen);
+ u64 gpa = gfn << PAGE_SHIFT;
access &= ACC_WRITE_MASK | ACC_USER_MASK;
- mask |= shadow_mmio_value | access | gfn << PAGE_SHIFT;
+ mask |= shadow_mmio_value | access;
+ mask |= gpa | shadow_nonpresent_or_rsvd_mask;
+ mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
+ << shadow_nonpresent_or_rsvd_mask_len;
trace_mark_mmio_spte(sptep, gfn, access, gen);
mmu_spte_set(sptep, mask);
static gfn_t get_mmio_spte_gfn(u64 spte)
{
- u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
- return (spte & ~mask) >> PAGE_SHIFT;
+ 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)
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
-void kvm_mmu_clear_all_pte_masks(void)
+static void kvm_mmu_reset_all_pte_masks(void)
{
+ u8 low_phys_bits;
+
shadow_user_mask = 0;
shadow_accessed_mask = 0;
shadow_dirty_mask = 0;
shadow_mmio_mask = 0;
shadow_present_mask = 0;
shadow_acc_track_mask = 0;
+
+ /*
+ * If the CPU has 46 or less physical address bits, then set an
+ * appropriate mask to guard against L1TF attacks. Otherwise, it is
+ * assumed that the CPU is not vulnerable to L1TF.
+ */
+ low_phys_bits = boot_cpu_data.x86_phys_bits;
+ if (boot_cpu_data.x86_phys_bits <
+ 52 - shadow_nonpresent_or_rsvd_mask_len) {
+ shadow_nonpresent_or_rsvd_mask =
+ rsvd_bits(boot_cpu_data.x86_phys_bits -
+ shadow_nonpresent_or_rsvd_mask_len,
+ boot_cpu_data.x86_phys_bits - 1);
+ low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+ }
+ shadow_nonpresent_or_rsvd_lower_gfn_mask =
+ GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
}
static int is_cpuid_PSE36(void)
if (cache->nobjs >= min)
return 0;
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
- page = (void *)__get_free_page(GFP_KERNEL);
+ page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
if (!page)
return -ENOMEM;
cache->objects[cache->nobjs++] = page;
static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
{
- if (sp->role.direct)
- BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index));
- else
+ 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);
}
/*
kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
+static 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;
kvm_mmu_gfn_allow_lpage(slot, gfn);
}
+static 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 bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
struct kvm_memory_slot *slot)
{
return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
}
-static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
+static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn)
{
unsigned long page_size;
int i, ret = 0;
- page_size = kvm_host_page_size(kvm, gfn);
+ page_size = kvm_host_page_size(vcpu, gfn);
for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
if (page_size >= KVM_HPAGE_SIZE(i))
if (unlikely(*force_pt_level))
return PT_PAGE_TABLE_LEVEL;
- host_level = host_mapping_level(vcpu->kvm, large_gfn);
+ host_level = host_mapping_level(vcpu, large_gfn);
if (host_level == PT_PAGE_TABLE_LEVEL)
return host_level;
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
kvm_reload_remote_mmus(kvm);
}
+ if (sp->lpage_disallowed)
+ unaccount_huge_nx_page(kvm, sp);
+
sp->role.invalid = 1;
return ret;
}
* 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 int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
LIST_HEAD(invalid_list);
static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
{
if (pfn_valid(pfn))
- return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+ return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) &&
+ /*
+ * Some reserved pages, such as those from NVDIMM
+ * DAX devices, are not for MMIO, and can be mapped
+ * with cached memory type for better performance.
+ * However, the above check misconceives those pages
+ * as MMIO, and results in KVM mapping them with UC
+ * memory type, which would hurt the performance.
+ * Therefore, we check the host memory type in addition
+ * and only treat UC/UC-/WC pages as MMIO.
+ */
+ (!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));
return true;
}
if (!speculative)
spte |= spte_shadow_accessed_mask(spte);
+ if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) &&
+ is_nx_huge_page_enabled()) {
+ pte_access &= ~ACC_EXEC_MASK;
+ }
+
if (pte_access & ACC_EXEC_MASK)
spte |= shadow_x_mask;
else
else
pte_access &= ~ACC_WRITE_MASK;
+ if (!kvm_is_mmio_pfn(pfn))
+ spte |= shadow_me_mask;
+
spte |= (u64)pfn << PAGE_SHIFT;
- spte |= shadow_me_mask;
if (pte_access & ACC_WRITE_MASK) {
ret = RET_PF_EMULATE;
pgprintk("%s: setting spte %llx\n", __func__, *sptep);
- pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n",
- is_large_pte(*sptep)? "2MB" : "4kB",
- *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn,
- *sptep, sptep);
+ trace_kvm_mmu_set_spte(level, gfn, sptep);
if (!was_rmapped && is_large_pte(*sptep))
++vcpu->kvm->stat.lpages;
}
}
- kvm_release_pfn_clean(pfn);
-
return ret;
}
if (ret <= 0)
return -1;
- for (i = 0; i < ret; i++, gfn++, start++)
+ for (i = 0; i < ret; i++, gfn++, start++) {
mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
page_to_pfn(pages[i]), true, true);
+ put_page(pages[i]);
+ }
return 0;
}
__direct_pte_prefetch(vcpu, sp, sptep);
}
-static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
- int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault)
+static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
+ gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
{
- struct kvm_shadow_walk_iterator iterator;
+ int level = *levelp;
+ u64 spte = *it.sptep;
+
+ if (it.level == level && level > PT_PAGE_TABLE_LEVEL &&
+ is_nx_huge_page_enabled() &&
+ is_shadow_present_pte(spte) &&
+ !is_large_pte(spte)) {
+ /*
+ * A small SPTE exists for this pfn, but FNAME(fetch)
+ * and __direct_map would like to create a large PTE
+ * instead: just force them to go down another level,
+ * patching back for them into pfn the next 9 bits of
+ * the address.
+ */
+ u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1);
+ *pfnp |= gfn & page_mask;
+ (*levelp)--;
+ }
+}
+
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
+ int map_writable, int level, kvm_pfn_t pfn,
+ bool prefault, bool lpage_disallowed)
+{
+ struct kvm_shadow_walk_iterator it;
struct kvm_mmu_page *sp;
- int emulate = 0;
- gfn_t pseudo_gfn;
+ int ret;
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ gfn_t base_gfn = gfn;
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
- return 0;
+ return RET_PF_RETRY;
- for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
- if (iterator.level == level) {
- emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
- write, level, gfn, pfn, prefault,
- map_writable);
- direct_pte_prefetch(vcpu, iterator.sptep);
- ++vcpu->stat.pf_fixed;
- break;
- }
+ trace_kvm_mmu_spte_requested(gpa, level, pfn);
+ for_each_shadow_entry(vcpu, gpa, it) {
+ /*
+ * We cannot overwrite existing page tables with an NX
+ * large page, as the leaf could be executable.
+ */
+ disallowed_hugepage_adjust(it, gfn, &pfn, &level);
- drop_large_spte(vcpu, iterator.sptep);
- if (!is_shadow_present_pte(*iterator.sptep)) {
- u64 base_addr = iterator.addr;
+ base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+ if (it.level == level)
+ break;
- base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
- pseudo_gfn = base_addr >> PAGE_SHIFT;
- sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
- iterator.level - 1, 1, ACC_ALL);
+ drop_large_spte(vcpu, it.sptep);
+ if (!is_shadow_present_pte(*it.sptep)) {
+ sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr,
+ it.level - 1, true, ACC_ALL);
- link_shadow_page(vcpu, iterator.sptep, sp);
+ link_shadow_page(vcpu, it.sptep, sp);
+ if (lpage_disallowed)
+ account_huge_nx_page(vcpu->kvm, sp);
}
}
- return emulate;
+
+ ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL,
+ write, level, base_gfn, pfn, prefault,
+ map_writable);
+ direct_pte_prefetch(vcpu, it.sptep);
+ ++vcpu->stat.pf_fixed;
+ return ret;
}
static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
}
static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
- gfn_t *gfnp, kvm_pfn_t *pfnp,
+ gfn_t gfn, kvm_pfn_t *pfnp,
int *levelp)
{
kvm_pfn_t pfn = *pfnp;
- gfn_t gfn = *gfnp;
int level = *levelp;
/*
* here.
*/
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
- level == PT_PAGE_TABLE_LEVEL &&
+ !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
PageTransCompoundMap(pfn_to_page(pfn)) &&
!mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
mask = KVM_PAGES_PER_HPAGE(level) - 1;
VM_BUG_ON((gfn & mask) != (pfn & mask));
if (pfn & mask) {
- gfn &= ~mask;
- *gfnp = gfn;
kvm_release_pfn_clean(pfn);
pfn &= ~mask;
kvm_get_pfn(pfn);
* - true: let the vcpu to access on the same address again.
* - false: let the real page fault path to fix it.
*/
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
+static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level,
u32 error_code)
{
struct kvm_shadow_walk_iterator iterator;
do {
u64 new_spte;
- for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
+ for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
if (!is_shadow_present_pte(spte) ||
iterator.level < level)
break;
} while (true);
- trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
+ trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
spte, fault_handled);
walk_shadow_page_lockless_end(vcpu);
}
static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
- gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
+ gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+ bool *writable);
static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
-static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
+static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
gfn_t gfn, bool prefault)
{
int r;
int level;
- bool force_pt_level = false;
+ bool force_pt_level;
kvm_pfn_t pfn;
unsigned long mmu_seq;
bool map_writable, write = error_code & PFERR_WRITE_MASK;
+ bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+ is_nx_huge_page_enabled();
+ force_pt_level = lpage_disallowed;
level = mapping_level(vcpu, gfn, &force_pt_level);
if (likely(!force_pt_level)) {
/*
gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
}
- if (fast_page_fault(vcpu, v, level, error_code))
+ if (fast_page_fault(vcpu, gpa, level, error_code))
return RET_PF_RETRY;
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
- if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
+ if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
return RET_PF_RETRY;
- if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
+ if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r))
return r;
+ r = RET_PF_RETRY;
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
goto out_unlock;
if (make_mmu_pages_available(vcpu) < 0)
goto out_unlock;
if (likely(!force_pt_level))
- transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
- r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
- spin_unlock(&vcpu->kvm->mmu_lock);
-
- return r;
-
+ transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
+ r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
+ prefault, false);
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
- return RET_PF_RETRY;
+ return r;
}
}
EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
u32 access, struct x86_exception *exception)
{
if (exception)
return vaddr;
}
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
u32 access,
struct x86_exception *exception)
{
walk_shadow_page_lockless_end(vcpu);
}
-static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
u32 error_code, bool prefault)
{
- gfn_t gfn = gva >> PAGE_SHIFT;
+ gfn_t gfn = gpa >> PAGE_SHIFT;
int r;
- pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
+ /* Note, paging is disabled, ergo gva == gpa. */
+ pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
if (page_fault_handle_page_track(vcpu, error_code, gfn))
return RET_PF_EMULATE;
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- return nonpaging_map(vcpu, gva & PAGE_MASK,
+ return nonpaging_map(vcpu, gpa & PAGE_MASK,
error_code, gfn, prefault);
}
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+ gfn_t gfn)
{
struct kvm_arch_async_pf arch;
arch.direct_map = vcpu->arch.mmu.direct_map;
arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
- return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+ return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+ kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
{
if (unlikely(!lapic_in_kernel(vcpu) ||
- kvm_event_needs_reinjection(vcpu)))
+ kvm_event_needs_reinjection(vcpu) ||
+ vcpu->arch.exception.pending))
return false;
if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
}
static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
- gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
+ gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+ bool *writable)
{
struct kvm_memory_slot *slot;
bool async;
return false; /* *pfn has correct page already */
if (!prefault && kvm_can_do_async_pf(vcpu)) {
- trace_kvm_try_async_get_page(gva, gfn);
+ trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
if (kvm_find_async_pf_gfn(vcpu, gfn)) {
- trace_kvm_async_pf_doublefault(gva, gfn);
+ trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
kvm_make_request(KVM_REQ_APF_HALT, vcpu);
return true;
- } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn))
+ } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
return true;
}
{
int r = 1;
+#ifndef CONFIG_X86_64
+ /* A 64-bit CR2 should be impossible on 32-bit KVM. */
+ if (WARN_ON_ONCE(fault_address >> 32))
+ return -EFAULT;
+#endif
+
+ vcpu->arch.l1tf_flush_l1d = true;
switch (vcpu->arch.apf.host_apf_reason) {
default:
trace_kvm_page_fault(fault_address, error_code);
return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
}
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
bool prefault)
{
kvm_pfn_t pfn;
unsigned long mmu_seq;
int write = error_code & PFERR_WRITE_MASK;
bool map_writable;
+ bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+ is_nx_huge_page_enabled();
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
if (r)
return r;
- force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
- PT_DIRECTORY_LEVEL);
+ force_pt_level =
+ lpage_disallowed ||
+ !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
level = mapping_level(vcpu, gfn, &force_pt_level);
if (likely(!force_pt_level)) {
if (level > PT_DIRECTORY_LEVEL &&
if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r))
return r;
+ r = RET_PF_RETRY;
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
goto out_unlock;
if (make_mmu_pages_available(vcpu) < 0)
goto out_unlock;
if (likely(!force_pt_level))
- transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
- r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
- spin_unlock(&vcpu->kvm->mmu_lock);
-
- return r;
-
+ transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
+ r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
+ prefault, lpage_disallowed);
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
- return RET_PF_RETRY;
+ return r;
}
static void nonpaging_init_context(struct kvm_vcpu *vcpu,
*/
/* Faults from writes to non-writable pages */
- u8 wf = (pfec & PFERR_WRITE_MASK) ? ~w : 0;
+ u8 wf = (pfec & PFERR_WRITE_MASK) ? (u8)~w : 0;
/* Faults from user mode accesses to supervisor pages */
- u8 uf = (pfec & PFERR_USER_MASK) ? ~u : 0;
+ u8 uf = (pfec & PFERR_USER_MASK) ? (u8)~u : 0;
/* Faults from fetches of non-executable pages*/
- u8 ff = (pfec & PFERR_FETCH_MASK) ? ~x : 0;
+ u8 ff = (pfec & PFERR_FETCH_MASK) ? (u8)~x : 0;
/* Faults from kernel mode fetches of user pages */
u8 smepf = 0;
/* Faults from kernel mode accesses of user pages */
}
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
- const u8 *new, int *bytes)
+ int *bytes)
{
- u64 gentry;
+ u64 gentry = 0;
int r;
/*
/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
*gpa &= ~(gpa_t)7;
*bytes = 8;
- r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8);
- if (r)
- gentry = 0;
- new = (const u8 *)&gentry;
}
- switch (*bytes) {
- case 4:
- gentry = *(const u32 *)new;
- break;
- case 8:
- gentry = *(const u64 *)new;
- break;
- default:
- gentry = 0;
- break;
+ if (*bytes == 4 || *bytes == 8) {
+ r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes);
+ if (r)
+ gentry = 0;
}
return gentry;
pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
- gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes);
-
/*
* No need to care whether allocation memory is successful
* or not since pte prefetch is skiped if it does not have
mmu_topup_memory_caches(vcpu);
spin_lock(&vcpu->kvm->mmu_lock);
+
+ gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);
+
++vcpu->kvm->stat.mmu_pte_write;
kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
return 0;
}
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len)
{
int r, emulation_type = EMULTYPE_RETRY;
/* With shadow page tables, fault_address contains a GVA or nGPA. */
if (vcpu->arch.mmu.direct_map) {
vcpu->arch.gpa_available = true;
- vcpu->arch.gpa_val = cr2;
+ vcpu->arch.gpa_val = cr2_or_gpa;
}
r = RET_PF_INVALID;
if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, cr2, direct);
+ r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
if (r == RET_PF_EMULATE) {
emulation_type = 0;
goto emulate;
}
if (r == RET_PF_INVALID) {
- r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
- false);
+ r = vcpu->arch.mmu.page_fault(vcpu, cr2_or_gpa,
+ lower_32_bits(error_code),
+ false);
WARN_ON(r == RET_PF_INVALID);
}
*/
if (vcpu->arch.mmu.direct_map &&
(error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
- kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+ kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
return 1;
}
- if (mmio_info_in_cache(vcpu, cr2, direct))
+ if (mmio_info_in_cache(vcpu, cr2_or_gpa, direct))
emulation_type = 0;
emulate:
- er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
+ /*
+ * On AMD platforms, under certain conditions insn_len may be zero on #NPF.
+ * This can happen if a guest gets a page-fault on data access but the HW
+ * table walker is not able to read the instruction page (e.g instruction
+ * page is not present in memory). In those cases we simply restart the
+ * guest.
+ */
+ if (unlikely(insn && !insn_len))
+ return 1;
+
+ er = x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len);
switch (er) {
case EMULATE_DONE:
typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
/* The caller should hold mmu-lock before calling this function. */
-static bool
+static __always_inline bool
slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
slot_level_handler fn, int start_level, int end_level,
gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)
return flush;
}
-static bool
+static __always_inline bool
slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
slot_level_handler fn, int start_level, int end_level,
bool lock_flush_tlb)
lock_flush_tlb);
}
-static bool
+static __always_inline bool
slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
slot_level_handler fn, bool lock_flush_tlb)
{
PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
}
-static bool
+static __always_inline bool
slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
slot_level_handler fn, bool lock_flush_tlb)
{
PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
}
-static bool
+static __always_inline bool
slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
slot_level_handler fn, bool lock_flush_tlb)
{
* the guest, and the guest page table is using 4K page size
* mapping if the indirect sp has level = 1.
*/
- if (sp->role.direct &&
- !kvm_is_reserved_pfn(pfn) &&
- PageTransCompoundMap(pfn_to_page(pfn))) {
+ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
+ !kvm_is_zone_device_pfn(pfn) &&
+ PageTransCompoundMap(pfn_to_page(pfn))) {
drop_spte(kvm, sptep);
need_tlb_flush = 1;
goto restart;
return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
}
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots)
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
{
+ gen &= MMIO_GEN_MASK;
+
+ /*
+ * Shift to eliminate the "update in-progress" flag, which isn't
+ * included in the spte's generation number.
+ */
+ gen >>= 1;
+
/*
- * The very rare case: if the generation-number is round,
+ * Generation numbers are incremented in multiples of the number of
+ * address spaces in order to provide unique generations across all
+ * address spaces. Strip what is effectively the address space
+ * modifier prior to checking for a wrap of the MMIO generation so
+ * that a wrap in any address space is detected.
+ */
+ gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+
+ /*
+ * The very rare case: if the MMIO generation number has wrapped,
* zap all shadow pages.
*/
- if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) {
+ if (unlikely(gen == 0)) {
kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n");
kvm_mmu_invalidate_zap_all_pages(kvm);
}
int nr_to_scan = sc->nr_to_scan;
unsigned long freed = 0;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
int idx;
break;
}
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
return freed;
}
kmem_cache_destroy(mmu_page_header_cache);
}
+static bool get_nx_auto_mode(void)
+{
+ /* Return true when CPU has the bug, and mitigations are ON */
+ return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
+}
+
+static void __set_nx_huge_pages(bool val)
+{
+ nx_huge_pages = itlb_multihit_kvm_mitigation = val;
+}
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
+{
+ bool old_val = nx_huge_pages;
+ bool new_val;
+
+ /* In "auto" mode deploy workaround only if CPU has the bug. */
+ if (sysfs_streq(val, "off"))
+ new_val = 0;
+ else if (sysfs_streq(val, "force"))
+ new_val = 1;
+ else if (sysfs_streq(val, "auto"))
+ new_val = get_nx_auto_mode();
+ else if (strtobool(val, &new_val) < 0)
+ return -EINVAL;
+
+ __set_nx_huge_pages(new_val);
+
+ if (new_val != old_val) {
+ struct kvm *kvm;
+ int idx;
+
+ mutex_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ idx = srcu_read_lock(&kvm->srcu);
+ kvm_mmu_invalidate_zap_all_pages(kvm);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+ }
+ mutex_unlock(&kvm_lock);
+ }
+
+ return 0;
+}
+
int kvm_mmu_module_init(void)
{
- kvm_mmu_clear_all_pte_masks();
+ int ret = -ENOMEM;
+
+ if (nx_huge_pages == -1)
+ __set_nx_huge_pages(get_nx_auto_mode());
+
+ kvm_mmu_reset_all_pte_masks();
pte_list_desc_cache = kmem_cache_create("pte_list_desc",
sizeof(struct pte_list_desc),
0, SLAB_ACCOUNT, NULL);
if (!pte_list_desc_cache)
- goto nomem;
+ goto out;
mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
sizeof(struct kvm_mmu_page),
0, SLAB_ACCOUNT, NULL);
if (!mmu_page_header_cache)
- goto nomem;
+ goto out;
if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
- goto nomem;
+ goto out;
- register_shrinker(&mmu_shrinker);
+ ret = register_shrinker(&mmu_shrinker);
+ if (ret)
+ goto out;
return 0;
-nomem:
+out:
mmu_destroy_caches();
- return -ENOMEM;
+ return ret;
}
/*
* Caculate mmu pages needed for kvm.
*/
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
{
- unsigned int nr_mmu_pages;
- unsigned int nr_pages = 0;
+ unsigned long nr_mmu_pages;
+ unsigned long nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i;
}
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
- nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
unregister_shrinker(&mmu_shrinker);
mmu_audit_disable();
}
+
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp)
+{
+ unsigned int old_val;
+ int err;
+
+ old_val = nx_huge_pages_recovery_ratio;
+ err = param_set_uint(val, kp);
+ if (err)
+ return err;
+
+ if (READ_ONCE(nx_huge_pages) &&
+ !old_val && nx_huge_pages_recovery_ratio) {
+ struct kvm *kvm;
+
+ mutex_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list)
+ wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+
+ mutex_unlock(&kvm_lock);
+ }
+
+ return err;
+}
+
+static void kvm_recover_nx_lpages(struct kvm *kvm)
+{
+ int rcu_idx;
+ struct kvm_mmu_page *sp;
+ unsigned int ratio;
+ LIST_HEAD(invalid_list);
+ ulong to_zap;
+
+ rcu_idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+
+ ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+ to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
+ while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
+ /*
+ * We use a separate list instead of just using active_mmu_pages
+ * because the number of lpage_disallowed pages is expected to
+ * be relatively small compared to the total.
+ */
+ sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+ struct kvm_mmu_page,
+ lpage_disallowed_link);
+ WARN_ON_ONCE(!sp->lpage_disallowed);
+ kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+ WARN_ON_ONCE(sp->lpage_disallowed);
+
+ if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ if (to_zap)
+ cond_resched_lock(&kvm->mmu_lock);
+ }
+ }
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, rcu_idx);
+}
+
+static long get_nx_lpage_recovery_timeout(u64 start_time)
+{
+ return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio)
+ ? start_time + 60 * HZ - get_jiffies_64()
+ : MAX_SCHEDULE_TIMEOUT;
+}
+
+static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+{
+ u64 start_time;
+ long remaining_time;
+
+ while (true) {
+ start_time = get_jiffies_64();
+ remaining_time = get_nx_lpage_recovery_timeout(start_time);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop() && remaining_time > 0) {
+ schedule_timeout(remaining_time);
+ remaining_time = get_nx_lpage_recovery_timeout(start_time);
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+
+ set_current_state(TASK_RUNNING);
+
+ if (kthread_should_stop())
+ return 0;
+
+ kvm_recover_nx_lpages(kvm);
+ }
+}
+
+int kvm_mmu_post_init_vm(struct kvm *kvm)
+{
+ int err;
+
+ err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+ "kvm-nx-lpage-recovery",
+ &kvm->arch.nx_lpage_recovery_thread);
+ if (!err)
+ kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+
+ return err;
+}
+
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
+{
+ if (kvm->arch.nx_lpage_recovery_thread)
+ kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+}