aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kvm/mmu/spte.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/mmu/spte.c')
-rw-r--r--arch/x86/kvm/mmu/spte.c71
1 files changed, 58 insertions, 13 deletions
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index b5960bbde7f7..2e08b2a45361 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -20,7 +20,9 @@
#include <asm/vmx.h>
bool __read_mostly enable_mmio_caching = true;
+static bool __ro_after_init allow_mmio_caching;
module_param_named(mmio_caching, enable_mmio_caching, bool, 0444);
+EXPORT_SYMBOL_GPL(enable_mmio_caching);
u64 __read_mostly shadow_host_writable_mask;
u64 __read_mostly shadow_mmu_writable_mask;
@@ -33,6 +35,7 @@ u64 __read_mostly shadow_mmio_value;
u64 __read_mostly shadow_mmio_mask;
u64 __read_mostly shadow_mmio_access_mask;
u64 __read_mostly shadow_present_mask;
+u64 __read_mostly shadow_memtype_mask;
u64 __read_mostly shadow_me_value;
u64 __read_mostly shadow_me_mask;
u64 __read_mostly shadow_acc_track_mask;
@@ -42,6 +45,18 @@ u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
u8 __read_mostly shadow_phys_bits;
+void __init kvm_mmu_spte_module_init(void)
+{
+ /*
+ * Snapshot userspace's desire to allow MMIO caching. Whether or not
+ * KVM can actually enable MMIO caching depends on vendor-specific
+ * hardware capabilities and other module params that can't be resolved
+ * until the vendor module is loaded, i.e. enable_mmio_caching can and
+ * will change when the vendor module is (re)loaded.
+ */
+ allow_mmio_caching = enable_mmio_caching;
+}
+
static u64 generation_mmio_spte_mask(u64 gen)
{
u64 mask;
@@ -129,6 +144,8 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
u64 spte = SPTE_MMU_PRESENT_MASK;
bool wrprot = false;
+ WARN_ON_ONCE(!pte_access && !shadow_present_mask);
+
if (sp->role.ad_disabled)
spte |= SPTE_TDP_AD_DISABLED_MASK;
else if (kvm_mmu_page_ad_need_write_protect(sp))
@@ -145,7 +162,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
spte |= spte_shadow_accessed_mask(spte);
if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) &&
- is_nx_huge_page_enabled()) {
+ is_nx_huge_page_enabled(vcpu->kvm)) {
pte_access &= ~ACC_EXEC_MASK;
}
@@ -159,10 +176,10 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (level > PG_LEVEL_4K)
spte |= PT_PAGE_SIZE_MASK;
- if (tdp_enabled)
- spte |= static_call(kvm_x86_get_mt_mask)(vcpu, gfn,
- kvm_is_mmio_pfn(pfn));
+ if (shadow_memtype_mask)
+ spte |= static_call(kvm_x86_get_mt_mask)(vcpu, gfn,
+ kvm_is_mmio_pfn(pfn));
if (host_writable)
spte |= shadow_host_writable_mask;
else
@@ -244,10 +261,10 @@ static u64 make_spte_executable(u64 spte)
* This is used during huge page splitting to build the SPTEs that make up the
* new page table.
*/
-u64 make_huge_page_split_spte(u64 huge_spte, int huge_level, int index)
+u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte, union kvm_mmu_page_role role,
+ int index)
{
u64 child_spte;
- int child_level;
if (WARN_ON_ONCE(!is_shadow_present_pte(huge_spte)))
return 0;
@@ -256,23 +273,23 @@ u64 make_huge_page_split_spte(u64 huge_spte, int huge_level, int index)
return 0;
child_spte = huge_spte;
- child_level = huge_level - 1;
/*
* The child_spte already has the base address of the huge page being
* split. So we just have to OR in the offset to the page at the next
* lower level for the given index.
*/
- child_spte |= (index * KVM_PAGES_PER_HPAGE(child_level)) << PAGE_SHIFT;
+ child_spte |= (index * KVM_PAGES_PER_HPAGE(role.level)) << PAGE_SHIFT;
- if (child_level == PG_LEVEL_4K) {
+ if (role.level == PG_LEVEL_4K) {
child_spte &= ~PT_PAGE_SIZE_MASK;
/*
- * When splitting to a 4K page, mark the page executable as the
- * NX hugepage mitigation no longer applies.
+ * When splitting to a 4K page where execution is allowed, mark
+ * the page executable as the NX hugepage mitigation no longer
+ * applies.
*/
- if (is_nx_huge_page_enabled())
+ if ((role.access & ACC_EXEC_MASK) && is_nx_huge_page_enabled(kvm))
child_spte = make_spte_executable(child_spte);
}
@@ -299,7 +316,7 @@ u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
{
u64 new_spte;
- new_spte = old_spte & ~PT64_BASE_ADDR_MASK;
+ new_spte = old_spte & ~SPTE_BASE_ADDR_MASK;
new_spte |= (u64)new_pfn << PAGE_SHIFT;
new_spte &= ~PT_WRITABLE_MASK;
@@ -337,10 +354,24 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
BUG_ON((u64)(unsigned)access_mask != access_mask);
WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
+ /*
+ * Reset to the original module param value to honor userspace's desire
+ * to (dis)allow MMIO caching. Update the param itself so that
+ * userspace can see whether or not KVM is actually using MMIO caching.
+ */
+ enable_mmio_caching = allow_mmio_caching;
if (!enable_mmio_caching)
mmio_value = 0;
/*
+ * The mask must contain only bits that are carved out specifically for
+ * the MMIO SPTE mask, e.g. to ensure there's no overlap with the MMIO
+ * generation.
+ */
+ if (WARN_ON(mmio_mask & ~SPTE_MMIO_ALLOWED_MASK))
+ mmio_value = 0;
+
+ /*
* Disable MMIO caching if the MMIO value collides with the bits that
* are used to hold the relocated GFN when the L1TF mitigation is
* enabled. This should never fire as there is no known hardware that
@@ -389,6 +420,13 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
shadow_nx_mask = 0ull;
shadow_x_mask = VMX_EPT_EXECUTABLE_MASK;
shadow_present_mask = has_exec_only ? 0ull : VMX_EPT_READABLE_MASK;
+ /*
+ * EPT overrides the host MTRRs, and so KVM must program the desired
+ * memtype directly into the SPTEs. Note, this mask is just the mask
+ * of all bits that factor into the memtype, the actual memtype must be
+ * dynamically calculated, e.g. to ensure host MMIO is mapped UC.
+ */
+ shadow_memtype_mask = VMX_EPT_MT_MASK | VMX_EPT_IPAT_BIT;
shadow_acc_track_mask = VMX_EPT_RWX_MASK;
shadow_host_writable_mask = EPT_SPTE_HOST_WRITABLE;
shadow_mmu_writable_mask = EPT_SPTE_MMU_WRITABLE;
@@ -439,6 +477,13 @@ void kvm_mmu_reset_all_pte_masks(void)
shadow_nx_mask = PT64_NX_MASK;
shadow_x_mask = 0;
shadow_present_mask = PT_PRESENT_MASK;
+
+ /*
+ * For shadow paging and NPT, KVM uses PAT entry '0' to encode WB
+ * memtype in the SPTEs, i.e. relies on host MTRRs to provide the
+ * correct memtype (WB is the "weakest" memtype).
+ */
+ shadow_memtype_mask = 0;
shadow_acc_track_mask = 0;
shadow_me_mask = 0;
shadow_me_value = 0;