summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt19
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/kernel/cpu/bugs.c13
-rw-r--r--arch/x86/kvm/mmu.c141
-rw-r--r--arch/x86/kvm/paging_tmpl.h29
-rw-r--r--arch/x86/kvm/x86.c9
6 files changed, 200 insertions, 13 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d16b3d41ffe5..496bc24733a6 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1852,6 +1852,19 @@
KVM MMU at runtime.
Default is 0 (off)
+ kvm.nx_huge_pages=
+ [KVM] Controls the software workaround for the
+ X86_BUG_ITLB_MULTIHIT bug.
+ force : Always deploy workaround.
+ off : Never deploy workaround.
+ auto : Deploy workaround based on the presence of
+ X86_BUG_ITLB_MULTIHIT.
+
+ Default is 'auto'.
+
+ If the software workaround is enabled for the host,
+ guests do need not to enable it for nested guests.
+
kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
Default is 1 (enabled)
@@ -2410,6 +2423,12 @@
l1tf=off [X86]
mds=off [X86]
tsx_async_abort=off [X86]
+ kvm.nx_huge_pages=off [X86]
+
+ Exceptions:
+ This does not have any effect on
+ kvm.nx_huge_pages when
+ kvm.nx_huge_pages=force.
auto (default)
Mitigate all CPU vulnerabilities, but leave SMT
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 00c12158a5dc..9751feab5149 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -289,6 +289,7 @@ struct kvm_mmu_page {
/* hold the gfn of each spte inside spt */
gfn_t *gfns;
bool unsync;
+ bool lpage_disallowed; /* Can't be replaced by an equiv large page */
int root_count; /* Currently serving as active root */
unsigned int unsync_children;
struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
@@ -867,6 +868,7 @@ struct kvm_vm_stat {
ulong mmu_unsync;
ulong remote_tlb_flush;
ulong lpages;
+ ulong nx_lpage_splits;
ulong max_mmu_page_hash_collisions;
};
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ee558f70d549..8596811843cc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1225,6 +1225,9 @@ void x86_spec_ctrl_setup_ap(void)
x86_amd_ssb_disable();
}
+bool itlb_multihit_kvm_mitigation;
+EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation);
+
#undef pr_fmt
#define pr_fmt(fmt) "L1TF: " fmt
@@ -1380,17 +1383,25 @@ static ssize_t l1tf_show_state(char *buf)
l1tf_vmx_states[l1tf_vmx_mitigation],
sched_smt_active() ? "vulnerable" : "disabled");
}
+
+static ssize_t itlb_multihit_show_state(char *buf)
+{
+ if (itlb_multihit_kvm_mitigation)
+ return sprintf(buf, "KVM: Mitigation: Split huge pages\n");
+ else
+ return sprintf(buf, "KVM: Vulnerable\n");
+}
#else
static ssize_t l1tf_show_state(char *buf)
{
return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
}
-#endif
static ssize_t itlb_multihit_show_state(char *buf)
{
return sprintf(buf, "Processor vulnerable\n");
}
+#endif
static ssize_t mds_show_state(char *buf)
{
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d2c4d7615aa2..e3492160aed0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -48,6 +48,20 @@
#include <asm/kvm_page_track.h>
#include "trace.h"
+extern bool itlb_multihit_kvm_mitigation;
+
+static int __read_mostly nx_huge_pages = -1;
+
+static int set_nx_huge_pages(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,
+};
+
+module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages, "bool");
+
/*
* When setting this variable to true it enables Two-Dimensional-Paging
* where the hardware walks 2 page tables:
@@ -266,6 +280,11 @@ static inline bool spte_ad_enabled(u64 spte)
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);
@@ -1078,6 +1097,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
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;
+ sp->lpage_disallowed = true;
+}
+
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
@@ -1095,6 +1123,12 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
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;
+}
+
static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
struct kvm_memory_slot *slot)
{
@@ -2642,6 +2676,9 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
kvm_reload_remote_mmus(kvm);
}
+ if (sp->lpage_disallowed)
+ unaccount_huge_nx_page(kvm, sp);
+
sp->role.invalid = 1;
return ret;
}
@@ -2796,6 +2833,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
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
@@ -3009,9 +3051,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
__direct_pte_prefetch(vcpu, sp, sptep);
}
+static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
+ gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
+{
+ 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 prefault, bool lpage_disallowed)
{
struct kvm_shadow_walk_iterator it;
struct kvm_mmu_page *sp;
@@ -3024,6 +3089,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
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);
+
base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
if (it.level == level)
break;
@@ -3034,6 +3105,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
it.level - 1, true, ACC_ALL);
link_shadow_page(vcpu, it.sptep, sp);
+ if (lpage_disallowed)
+ account_huge_nx_page(vcpu->kvm, sp);
}
}
@@ -3333,11 +3406,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
{
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)) {
/*
@@ -3371,7 +3447,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
- r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault);
+ r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+ prefault, false);
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
@@ -3921,6 +3998,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
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));
@@ -3931,8 +4010,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
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 &&
@@ -3961,7 +4041,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
- r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault);
+ 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);
@@ -5524,8 +5605,56 @@ static void mmu_destroy_caches(void)
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);
+ }
+ mutex_unlock(&kvm_lock);
+ }
+
+ return 0;
+}
+
int kvm_mmu_module_init(void)
{
+ 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",
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index b6b0fb60e0a7..8cf7a09bdd73 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -596,13 +596,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct guest_walker *gw,
int write_fault, int hlevel,
- kvm_pfn_t pfn, bool map_writable, bool prefault)
+ kvm_pfn_t pfn, bool map_writable, bool prefault,
+ bool lpage_disallowed)
{
struct kvm_mmu_page *sp = NULL;
struct kvm_shadow_walk_iterator it;
unsigned direct_access, access = gw->pt_access;
int top_level, ret;
- gfn_t base_gfn;
+ gfn_t gfn, base_gfn;
direct_access = gw->pte_access;
@@ -647,13 +648,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
link_shadow_page(vcpu, it.sptep, sp);
}
- base_gfn = gw->gfn;
+ /*
+ * FNAME(page_fault) might have clobbered the bottom bits of
+ * gw->gfn, restore them from the virtual address.
+ */
+ gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
+ base_gfn = gfn;
trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
clear_sp_write_flooding_count(it.sptep);
- base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+
+ /*
+ * We cannot overwrite existing page tables with an NX
+ * large page, as the leaf could be executable.
+ */
+ disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
+
+ base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
if (it.level == hlevel)
break;
@@ -665,6 +678,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
it.level - 1, true, direct_access);
link_shadow_page(vcpu, it.sptep, sp);
+ if (lpage_disallowed)
+ account_huge_nx_page(vcpu->kvm, sp);
}
}
@@ -741,9 +756,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
int r;
kvm_pfn_t pfn;
int level = PT_PAGE_TABLE_LEVEL;
- bool force_pt_level = false;
unsigned long mmu_seq;
bool map_writable, is_self_change_mapping;
+ bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+ is_nx_huge_page_enabled();
+ bool force_pt_level = lpage_disallowed;
pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
@@ -833,7 +850,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
if (!force_pt_level)
transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
- level, pfn, map_writable, prefault);
+ level, pfn, map_writable, prefault, lpage_disallowed);
kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
out_unlock:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 06d7df4331b1..0804ad3326dc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -192,6 +192,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmu_unsync", VM_STAT(mmu_unsync) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
{ "largepages", VM_STAT(lpages, .mode = 0444) },
+ { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
{ "max_mmu_page_hash_collisions",
VM_STAT(max_mmu_page_hash_collisions) },
{ NULL }
@@ -1070,6 +1071,14 @@ u64 kvm_get_arch_capabilities(void)
rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
/*
+ * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+ * the nested hypervisor runs with NX huge pages. If it is not,
+ * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+ * L1 guests, so it need not worry about its own (L2) guests.
+ */
+ data |= ARCH_CAP_PSCHANGE_MC_NO;
+
+ /*
* If we're doing cache flushes (either "always" or "cond")
* we will do one whenever the guest does a vmlaunch/vmresume.
* If an outer hypervisor is doing the cache flush for us