summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/mmu/paging_tmpl.h
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/mmu/paging_tmpl.h')
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h126
1 files changed, 75 insertions, 51 deletions
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index db80f7ccaa4e..f5958071220c 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -16,25 +16,21 @@
*/
/*
- * We need the mmu code to access both 32-bit and 64-bit guest ptes,
- * so the code in this file is compiled twice, once per pte size.
+ * The MMU needs to be able to access/walk 32-bit and 64-bit guest page tables,
+ * as well as guest EPT tables, so the code in this file is compiled thrice,
+ * once per guest PTE type. The per-type defines are #undef'd at the end.
*/
#if PTTYPE == 64
#define pt_element_t u64
#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
- #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
- #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
- #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
- #define PT_INDEX(addr, level) PT64_INDEX(addr, level)
- #define PT_LEVEL_BITS PT64_LEVEL_BITS
+ #define PT_LEVEL_BITS 9
#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
#define PT_HAVE_ACCESSED_DIRTY(mmu) true
#ifdef CONFIG_X86_64
#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
- #define CMPXCHG "cmpxchgq"
#else
#define PT_MAX_FULL_LEVELS 2
#endif
@@ -42,36 +38,35 @@
#define pt_element_t u32
#define guest_walker guest_walker32
#define FNAME(name) paging##32_##name
- #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
- #define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl)
- #define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl)
- #define PT_INDEX(addr, level) PT32_INDEX(addr, level)
- #define PT_LEVEL_BITS PT32_LEVEL_BITS
+ #define PT_LEVEL_BITS 10
#define PT_MAX_FULL_LEVELS 2
#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
#define PT_HAVE_ACCESSED_DIRTY(mmu) true
- #define CMPXCHG "cmpxchgl"
+
+ #define PT32_DIR_PSE36_SIZE 4
+ #define PT32_DIR_PSE36_SHIFT 13
+ #define PT32_DIR_PSE36_MASK \
+ (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
#elif PTTYPE == PTTYPE_EPT
#define pt_element_t u64
#define guest_walker guest_walkerEPT
#define FNAME(name) ept_##name
- #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
- #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
- #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
- #define PT_INDEX(addr, level) PT64_INDEX(addr, level)
- #define PT_LEVEL_BITS PT64_LEVEL_BITS
+ #define PT_LEVEL_BITS 9
#define PT_GUEST_DIRTY_SHIFT 9
#define PT_GUEST_ACCESSED_SHIFT 8
#define PT_HAVE_ACCESSED_DIRTY(mmu) (!(mmu)->cpu_role.base.ad_disabled)
- #ifdef CONFIG_X86_64
- #define CMPXCHG "cmpxchgq"
- #endif
#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
#else
#error Invalid PTTYPE value
#endif
+/* Common logic, but per-type values. These also need to be undefined. */
+#define PT_BASE_ADDR_MASK ((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
+#define PT_LVL_ADDR_MASK(lvl) __PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
+#define PT_LVL_OFFSET_MASK(lvl) __PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
+#define PT_INDEX(addr, lvl) __PT_INDEX(addr, lvl, PT_LEVEL_BITS)
+
#define PT_GUEST_DIRTY_MASK (1 << PT_GUEST_DIRTY_SHIFT)
#define PT_GUEST_ACCESSED_MASK (1 << PT_GUEST_ACCESSED_SHIFT)
@@ -97,6 +92,15 @@ struct guest_walker {
struct x86_exception fault;
};
+#if PTTYPE == 32
+static inline gfn_t pse36_gfn_delta(u32 gpte)
+{
+ int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;
+
+ return (gpte & PT32_DIR_PSE36_MASK) << shift;
+}
+#endif
+
static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
{
return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
@@ -374,7 +378,7 @@ retry_walk:
* information to fix the exit_qualification or exit_info_1
* fields.
*/
- if (unlikely(real_gpa == UNMAPPED_GVA))
+ if (unlikely(real_gpa == INVALID_GPA))
return 0;
host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
@@ -421,11 +425,13 @@ retry_walk:
gfn = gpte_to_gfn_lvl(pte, walker->level);
gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;
- if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
+#if PTTYPE == 32
+ if (walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
gfn += pse36_gfn_delta(pte);
+#endif
real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault);
- if (real_gpa == UNMAPPED_GVA)
+ if (real_gpa == INVALID_GPA)
return 0;
walker->gfn = real_gpa >> PAGE_SHIFT;
@@ -589,7 +595,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
if (sp->role.direct)
return __direct_pte_prefetch(vcpu, sp, sptep);
- i = (sptep - sp->spt) & ~(PTE_PREFETCH_NUM - 1);
+ i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1);
spte = sp->spt + i;
for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
@@ -642,14 +648,13 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
gfn_t table_gfn;
clear_sp_write_flooding_count(it.sptep);
- drop_large_spte(vcpu, it.sptep);
-
- sp = NULL;
- if (!is_shadow_present_pte(*it.sptep)) {
- table_gfn = gw->table_gfn[it.level - 2];
- access = gw->pt_access[it.level - 2];
- sp = kvm_mmu_get_page(vcpu, table_gfn, fault->addr,
- it.level-1, false, access);
+
+ table_gfn = gw->table_gfn[it.level - 2];
+ access = gw->pt_access[it.level - 2];
+ sp = kvm_mmu_get_child_sp(vcpu, it.sptep, table_gfn,
+ false, access);
+
+ if (sp != ERR_PTR(-EEXIST)) {
/*
* We must synchronize the pagetable before linking it
* because the guest doesn't need to flush tlb when
@@ -678,7 +683,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
if (FNAME(gpte_changed)(vcpu, gw, it.level - 1))
goto out_gpte_changed;
- if (sp)
+ if (sp != ERR_PTR(-EEXIST))
link_shadow_page(vcpu, it.sptep, sp);
}
@@ -702,16 +707,15 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
validate_direct_spte(vcpu, it.sptep, direct_access);
- drop_large_spte(vcpu, it.sptep);
+ sp = kvm_mmu_get_child_sp(vcpu, it.sptep, base_gfn,
+ true, direct_access);
+ if (sp == ERR_PTR(-EEXIST))
+ continue;
- if (!is_shadow_present_pte(*it.sptep)) {
- sp = kvm_mmu_get_page(vcpu, base_gfn, fault->addr,
- it.level - 1, true, direct_access);
- link_shadow_page(vcpu, it.sptep, sp);
- if (fault->huge_page_disallowed &&
- fault->req_level >= it.level)
- account_huge_nx_page(vcpu->kvm, sp);
- }
+ link_shadow_page(vcpu, it.sptep, sp);
+ if (fault->huge_page_disallowed &&
+ fault->req_level >= it.level)
+ account_huge_nx_page(vcpu->kvm, sp);
}
if (WARN_ON_ONCE(it.level != fault->goal_level))
@@ -888,7 +892,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
WARN_ON(sp->role.level != PG_LEVEL_4K);
if (PTTYPE == 32)
- offset = sp->role.quadrant << PT64_LEVEL_BITS;
+ offset = sp->role.quadrant << SPTE_LEVEL_BITS;
return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
}
@@ -929,7 +933,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
break;
pte_gpa = FNAME(get_level1_sp_gpa)(sp);
- pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
+ pte_gpa += spte_index(sptep) * sizeof(pt_element_t);
mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL);
if (is_shadow_present_pte(old_spte))
@@ -958,7 +962,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
struct x86_exception *exception)
{
struct guest_walker walker;
- gpa_t gpa = UNMAPPED_GVA;
+ gpa_t gpa = INVALID_GPA;
int r;
#ifndef CONFIG_X86_64
@@ -978,7 +982,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
}
/*
- * Using the cached information from sp->gfns is safe because:
+ * Using the information in sp->shadowed_translation (kvm_mmu_page_get_gfn()) is
+ * safe because:
* - The spte has a reference to the struct page, so the pfn for a given gfn
* can't change unless all sptes pointing to it are nuked first.
*
@@ -1023,7 +1028,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
- for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
u64 *sptep, spte;
struct kvm_memory_slot *slot;
unsigned pte_access;
@@ -1053,12 +1058,23 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access))
continue;
- if (gfn != sp->gfns[i]) {
+ /*
+ * Drop the SPTE if the new protections would result in a RWX=0
+ * SPTE or if the gfn is changing. The RWX=0 case only affects
+ * EPT with execute-only support, i.e. EPT without an effective
+ * "present" bit, as all other paging modes will create a
+ * read-only SPTE if pte_access is zero.
+ */
+ if ((!pte_access && !shadow_present_mask) ||
+ gfn != kvm_mmu_page_get_gfn(sp, i)) {
drop_spte(vcpu->kvm, &sp->spt[i]);
flush = true;
continue;
}
+ /* Update the shadowed access bits in case they changed. */
+ kvm_mmu_page_set_access(sp, i, pte_access);
+
sptep = &sp->spt[i];
spte = *sptep;
host_writable = spte & shadow_host_writable_mask;
@@ -1070,6 +1086,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
flush |= mmu_spte_update(sptep, spte);
}
+ /*
+ * Note, any flush is purely for KVM's correctness, e.g. when dropping
+ * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier
+ * unmap or dirty logging event doesn't fail to flush. The guest is
+ * responsible for flushing the TLB to ensure any changes in protection
+ * bits are recognized, i.e. until the guest flushes or page faults on
+ * a relevant address, KVM is architecturally allowed to let vCPUs use
+ * cached translations with the old protection bits.
+ */
return flush;
}
@@ -1084,7 +1109,6 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
#undef PT_MAX_FULL_LEVELS
#undef gpte_to_gfn
#undef gpte_to_gfn_lvl
-#undef CMPXCHG
#undef PT_GUEST_ACCESSED_MASK
#undef PT_GUEST_DIRTY_MASK
#undef PT_GUEST_DIRTY_SHIFT
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-18 17:26:43 +0300