[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <dee30f0562d8be0102547d8eb9fc77736eae679d.1673539699.git.isaku.yamahata@intel.com>
Date: Thu, 12 Jan 2023 08:31:38 -0800
From: isaku.yamahata@...el.com
To: kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Cc: isaku.yamahata@...el.com, isaku.yamahata@...il.com,
Paolo Bonzini <pbonzini@...hat.com>, erdemaktas@...gle.com,
Sean Christopherson <seanjc@...gle.com>,
Sagi Shahar <sagis@...gle.com>,
David Matlack <dmatlack@...gle.com>,
Sean Christopherson <sean.j.christopherson@...el.com>
Subject: [PATCH v11 030/113] KVM: x86/mmu: Replace hardcoded value 0 for the initial value for SPTE
From: Isaku Yamahata <isaku.yamahata@...el.com>
The TDX support will need the "suppress #VE" bit (bit 63) set as the
initial value for SPTE. To reduce code change size, introduce a new macro
SHADOW_NONPRESENT_VALUE for the initial value for the shadow page table
entry (SPTE) and replace hard-coded value 0 for it. Initialize shadow page
tables with their value.
The plan is to unconditionally set the "suppress #VE" bit for both AMD and
Intel as: 1) AMD hardware uses the bit 63 as NX for present SPTE and
ignored for non-present SPTE; 2) for conventional VMX guests, KVM never
enables the "EPT-violation #VE" in VMCS control and "suppress #VE" bit is
ignored by hardware.
Signed-off-by: Sean Christopherson <sean.j.christopherson@...el.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@...el.com>
---
arch/x86/kvm/mmu/mmu.c | 50 ++++++++++++++++++++++++++++++----
arch/x86/kvm/mmu/paging_tmpl.h | 3 +-
arch/x86/kvm/mmu/spte.h | 2 ++
arch/x86/kvm/mmu/tdp_mmu.c | 15 +++++-----
4 files changed, 56 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 15d0e8f11d53..59befdfeec23 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -540,9 +540,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
if (!is_shadow_present_pte(old_spte) ||
!spte_has_volatile_bits(old_spte))
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
else
- old_spte = __update_clear_spte_slow(sptep, 0ull);
+ old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE);
if (!is_shadow_present_pte(old_spte))
return old_spte;
@@ -576,7 +576,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
*/
static void mmu_spte_clear_no_track(u64 *sptep)
{
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
}
static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -644,6 +644,39 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
}
}
+#ifdef CONFIG_X86_64
+static inline void kvm_init_shadow_page(void *page)
+{
+ memset64(page, SHADOW_NONPRESENT_VALUE, 4096 / 8);
+}
+
+static int mmu_topup_shadow_page_cache(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_memory_cache *mc = &vcpu->arch.mmu_shadow_page_cache;
+ int start, end, i, r;
+
+ start = kvm_mmu_memory_cache_nr_free_objects(mc);
+ r = kvm_mmu_topup_memory_cache(mc, PT64_ROOT_MAX_LEVEL);
+
+ /*
+ * Note, topup may have allocated objects even if it failed to allocate
+ * the minimum number of objects required to make forward progress _at
+ * this time_. Initialize newly allocated objects even on failure, as
+ * userspace can free memory and rerun the vCPU in response to -ENOMEM.
+ */
+ end = kvm_mmu_memory_cache_nr_free_objects(mc);
+ for (i = start; i < end; i++)
+ kvm_init_shadow_page(mc->objects[i]);
+ return r;
+}
+#else
+static int mmu_topup_shadow_page_cache(struct kvm_vcpu *vcpu)
+{
+ return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
+ PT64_ROOT_MAX_LEVEL);
+}
+#endif /* CONFIG_X86_64 */
+
static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
{
int r;
@@ -653,8 +686,7 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM);
if (r)
return r;
- r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
- PT64_ROOT_MAX_LEVEL);
+ r = mmu_topup_shadow_page_cache(vcpu);
if (r)
return r;
if (maybe_indirect) {
@@ -5920,7 +5952,13 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
- vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+ /*
+ * When X86_64, initial SEPT entries are initialized with
+ * SHADOW_NONPRESENT_VALUE. Otherwise zeroed. See
+ * mmu_topup_shadow_page_cache().
+ */
+ if (!IS_ENABLED(CONFIG_X86_64))
+ vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
vcpu->arch.mmu = &vcpu->arch.root_mmu;
vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 0f6455072055..42d7106c7350 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -1036,7 +1036,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
gpa_t pte_gpa;
gfn_t gfn;
- if (!sp->spt[i])
+ /* spt[i] has initial value of shadow page table allocation */
+ if (sp->spt[i] == SHADOW_NONPRESENT_VALUE)
continue;
pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 0d8deefee66c..f190eaf6b2b5 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -148,6 +148,8 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11);
#define MMIO_SPTE_GEN_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+#define SHADOW_NONPRESENT_VALUE 0ULL
+
extern u64 __read_mostly shadow_host_writable_mask;
extern u64 __read_mostly shadow_mmu_writable_mask;
extern u64 __read_mostly shadow_nx_mask;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 12e430a4ebc3..9cf5844dd34a 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -701,7 +701,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
* here since the SPTE is going from non-present to non-present. Use
* the raw write helper to avoid an unnecessary check on volatile bits.
*/
- __kvm_tdp_mmu_write_spte(iter->sptep, 0);
+ __kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
return 0;
}
@@ -878,8 +878,8 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
continue;
if (!shared)
- tdp_mmu_set_spte(kvm, &iter, 0);
- else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+ tdp_mmu_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
+ else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE))
goto retry;
}
}
@@ -935,8 +935,9 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
return false;
- __tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
- sp->gfn, sp->role.level + 1, true, true);
+ __tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte,
+ SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1,
+ true, true);
return true;
}
@@ -970,7 +971,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
!is_last_spte(iter.old_spte, iter.level))
continue;
- tdp_mmu_set_spte(kvm, &iter, 0);
+ tdp_mmu_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
flush = true;
}
@@ -1339,7 +1340,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
* invariant that the PFN of a present * leaf SPTE can never change.
* See __handle_changed_spte().
*/
- tdp_mmu_set_spte(kvm, iter, 0);
+ tdp_mmu_set_spte(kvm, iter, SHADOW_NONPRESENT_VALUE);
if (!pte_write(range->pte)) {
new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
--
2.25.1
Powered by blists - more mailing lists