From: isaku.yamahata@intel.com
To: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
"H . Peter Anvin" <hpa@zytor.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
erdemaktas@google.com, Connor Kuehl <ckuehl@redhat.com>,
Sean Christopherson <seanjc@google.com>,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
Sean Christopherson <sean.j.christopherson@intel.com>
Subject: [RFC PATCH v3 34/59] KVM: x86/mmu: Allow non-zero init value for shadow PTE
Date: Wed, 24 Nov 2021 16:20:17 -0800 [thread overview]
Message-ID: <0c4325595029876a7bfa0d1fc3d5ff93bb6b026e.1637799475.git.isaku.yamahata@intel.com> (raw)
In-Reply-To: <cover.1637799475.git.isaku.yamahata@intel.com>
From: Sean Christopherson <sean.j.christopherson@intel.com>
TDX will run with EPT violation #VEs enabled, which means KVM needs to
set the "suppress #VE" bit in unused PTEs to avoid unintentionally
reflecting not-present EPT violations into the guest.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
arch/x86/kvm/mmu.h | 1 +
arch/x86/kvm/mmu/mmu.c | 50 +++++++++++++++++++++++++++++++++++------
arch/x86/kvm/mmu/spte.c | 10 +++++++++
arch/x86/kvm/mmu/spte.h | 2 ++
4 files changed, 56 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 583483bb6f71..79ccee8bbc38 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -66,6 +66,7 @@ static __always_inline u64 rsvd_bits(int s, int e)
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);
+void kvm_mmu_set_spte_init_value(u64 init_value);
void kvm_init_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 01569913f1f0..510991c2e94e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -623,9 +623,9 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
int level = sptep_to_sp(sptep)->role.level;
if (!spte_has_volatile_bits(old_spte))
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, shadow_init_value);
else
- old_spte = __update_clear_spte_slow(sptep, 0ull);
+ old_spte = __update_clear_spte_slow(sptep, shadow_init_value);
if (!is_shadow_present_pte(old_spte))
return old_spte;
@@ -657,7 +657,7 @@ static int 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_init_value);
}
static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -743,6 +743,42 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
}
}
+static inline void kvm_init_shadow_page(void *page)
+{
+#ifdef CONFIG_X86_64
+ int ign;
+
+ asm volatile (
+ "rep stosq\n\t"
+ : "=c"(ign), "=D"(page)
+ : "a"(shadow_init_value), "c"(4096/8), "D"(page)
+ : "memory"
+ );
+#else
+ BUG();
+#endif
+}
+
+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;
+
+ if (shadow_init_value)
+ start = kvm_mmu_memory_cache_nr_free_objects(mc);
+
+ r = kvm_mmu_topup_memory_cache(mc, PT64_ROOT_MAX_LEVEL);
+ if (r)
+ return r;
+
+ if (shadow_init_value) {
+ end = kvm_mmu_memory_cache_nr_free_objects(mc);
+ for (i = start; i < end; i++)
+ kvm_init_shadow_page(mc->objects[i]);
+ }
+ return 0;
+}
+
static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
{
int r;
@@ -752,8 +788,7 @@ 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) {
@@ -3165,7 +3200,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
struct kvm_mmu_page *sp;
int ret = RET_PF_INVALID;
- u64 spte = 0ull;
+ u64 spte = shadow_init_value;
u64 *sptep = NULL;
uint retry_count = 0;
@@ -5584,7 +5619,8 @@ 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;
+ if (!shadow_init_value)
+ 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/spte.c b/arch/x86/kvm/mmu/spte.c
index 0c76c45fdb68..bb45e71eb105 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -34,6 +34,7 @@ u64 __read_mostly shadow_mmio_access_mask;
u64 __read_mostly shadow_present_mask;
u64 __read_mostly shadow_me_mask;
u64 __read_mostly shadow_acc_track_mask;
+u64 __read_mostly shadow_init_value;
u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
@@ -221,6 +222,14 @@ u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
return new_spte;
}
+void kvm_mmu_set_spte_init_value(u64 init_value)
+{
+ if (WARN_ON(!IS_ENABLED(CONFIG_X86_64) && init_value))
+ init_value = 0;
+ shadow_init_value = init_value;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_spte_init_value);
+
static u8 kvm_get_shadow_phys_bits(void)
{
/*
@@ -365,6 +374,7 @@ void kvm_mmu_reset_all_pte_masks(void)
shadow_present_mask = PT_PRESENT_MASK;
shadow_acc_track_mask = 0;
shadow_me_mask = sme_me_mask;
+ shadow_init_value = 0;
shadow_host_writable_mask = DEFAULT_SPTE_HOST_WRITEABLE;
shadow_mmu_writable_mask = DEFAULT_SPTE_MMU_WRITEABLE;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 56b6dd750fb1..b53b301301dc 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -146,6 +146,8 @@ extern u64 __read_mostly shadow_mmio_access_mask;
extern u64 __read_mostly shadow_present_mask;
extern u64 __read_mostly shadow_me_mask;
+extern u64 __read_mostly shadow_init_value;
+
/*
* SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED_MASK;
* shadow_acc_track_mask is the set of bits to be cleared in non-accessed
--
2.25.1
next prev parent reply other threads:[~2021-11-25 0:24 UTC|newest]
Thread overview: 123+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-25 0:19 [RFC PATCH v3 00/59] KVM: X86: TDX support isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 01/59] x86/mktme: move out MKTME related constatnts/macro to msr-index.h isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 02/59] x86/mtrr: mask out keyid bits from variable mtrr mask register isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 03/59] KVM: TDX: Define TDX architectural definitions isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 04/59] KVM: TDX: Add TDX "architectural" error codes isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 05/59] KVM: TDX: add a helper function for kvm to call seamcall isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 06/59] KVM: TDX: Add C wrapper functions for TDX SEAMCALLs isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 07/59] KVM: TDX: Add helper functions to print TDX SEAMCALL error isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 08/59] KVM: Export kvm_io_bus_read for use by TDX for PV MMIO isaku.yamahata
2021-11-25 17:14 ` Thomas Gleixner
2021-11-25 0:19 ` [RFC PATCH v3 09/59] KVM: Enable hardware before doing arch VM initialization isaku.yamahata
2021-11-25 19:02 ` Thomas Gleixner
2021-11-25 0:19 ` [RFC PATCH v3 10/59] KVM: x86: Split core of hypercall emulation to helper function isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 11/59] KVM: x86: Export kvm_mmio tracepoint for use by TDX for PV MMIO isaku.yamahata
2021-11-25 0:19 ` [RFC PATCH v3 12/59] KVM: x86/mmu: Zap only leaf SPTEs for deleted/moved memslot by default isaku.yamahata
2021-11-25 19:04 ` Thomas Gleixner
2021-11-25 0:19 ` [RFC PATCH v3 13/59] KVM: Add max_vcpus field in common 'struct kvm' isaku.yamahata
2021-11-25 19:06 ` Thomas Gleixner
2021-11-25 0:19 ` [RFC PATCH v3 14/59] KVM: x86: Add vm_type to differentiate legacy VMs from protected VMs isaku.yamahata
2021-11-25 19:08 ` Thomas Gleixner
2021-11-29 17:35 ` Sean Christopherson
2021-12-01 19:37 ` Isaku Yamahata
2021-12-03 16:14 ` Sean Christopherson
2021-11-25 0:19 ` [RFC PATCH v3 15/59] KVM: x86: Introduce "protected guest" concept and block disallowed ioctls isaku.yamahata
2021-11-25 19:26 ` Thomas Gleixner
2021-11-25 0:19 ` [RFC PATCH v3 16/59] KVM: x86: Add per-VM flag to disable direct IRQ injection isaku.yamahata
2021-11-25 19:31 ` Thomas Gleixner
2021-11-29 2:49 ` Lai Jiangshan
2021-11-25 0:20 ` [RFC PATCH v3 17/59] KVM: x86: Add flag to disallow #MC injection / KVM_X86_SETUP_MCE isaku.yamahata
2021-11-25 19:33 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 18/59] KVM: x86: Add flag to mark TSC as immutable (for TDX) isaku.yamahata
2021-11-25 19:40 ` Thomas Gleixner
2021-11-29 18:05 ` Sean Christopherson
2021-11-25 0:20 ` [RFC PATCH v3 19/59] KVM: Add per-VM flag to mark read-only memory as unsupported isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 20/59] KVM: Add per-VM flag to disable dirty logging of memslots for TDs isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 21/59] KVM: x86: Add per-VM flag to disable in-kernel I/O APIC and level routes isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 22/59] KVM: x86: add per-VM flags to disable SMI/INIT/SIPI isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 23/59] KVM: x86: Allow host-initiated WRMSR to set X2APIC regardless of CPUID isaku.yamahata
2021-11-25 19:41 ` Thomas Gleixner
2021-11-26 8:18 ` Paolo Bonzini
2021-11-29 21:21 ` Sean Christopherson
2021-11-25 0:20 ` [RFC PATCH v3 24/59] KVM: x86: Add kvm_x86_ops .cache_gprs() and .flush_gprs() isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 25/59] KVM: x86: Add support for vCPU and device-scoped KVM_MEMORY_ENCRYPT_OP isaku.yamahata
2021-11-25 19:42 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 26/59] KVM: x86: Introduce vm_teardown() hook in kvm_arch_vm_destroy() isaku.yamahata
2021-11-25 19:46 ` Thomas Gleixner
2021-11-25 20:54 ` Paolo Bonzini
2021-11-25 21:11 ` Thomas Gleixner
2021-11-29 18:16 ` Sean Christopherson
2021-11-25 0:20 ` [RFC PATCH v3 27/59] KVM: x86: Add a switch_db_regs flag to handle TDX's auto-switched behavior isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 28/59] KVM: x86: Check for pending APICv interrupt in kvm_vcpu_has_events() isaku.yamahata
2021-11-25 20:50 ` Paolo Bonzini
2021-11-29 19:20 ` Sean Christopherson
2021-11-25 0:20 ` [RFC PATCH v3 29/59] KVM: x86: Add option to force LAPIC expiration wait isaku.yamahata
2021-11-25 19:53 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 30/59] KVM: x86: Add guest_supported_xss placholder isaku.yamahata
2021-11-25 19:55 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 31/59] KVM: x86: Add infrastructure for stolen GPA bits isaku.yamahata
2021-11-25 20:00 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 32/59] KVM: x86/mmu: Explicitly check for MMIO spte in fast page fault isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 33/59] KVM: x86/mmu: Ignore bits 63 and 62 when checking for "present" SPTEs isaku.yamahata
2021-11-25 0:20 ` isaku.yamahata [this message]
2021-11-25 0:20 ` [RFC PATCH v3 35/59] KVM: x86/mmu: Return old SPTE from mmu_spte_clear_track_bits() isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 36/59] KVM: x86/mmu: Frame in support for private/inaccessible shadow pages isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 37/59] KVM: x86/mmu: Introduce kvm_mmu_map_tdp_page() for use by TDX isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 38/59] KVM: x86/mmu: Allow per-VM override of the TDP max page level isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 39/59] KVM: VMX: Modify NMI and INTR handlers to take intr_info as param isaku.yamahata
2021-11-25 20:06 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 40/59] KVM: VMX: Move NMI/exception handler to common helper isaku.yamahata
2021-11-25 20:06 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 41/59] KVM: VMX: Split out guts of EPT violation to common/exposed function isaku.yamahata
2021-11-25 20:07 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 42/59] KVM: VMX: Define EPT Violation architectural bits isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 43/59] KVM: VMX: Define VMCS encodings for shared EPT pointer isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 44/59] KVM: VMX: Add 'main.c' to wrap VMX and TDX isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 45/59] KVM: VMX: Move setting of EPT MMU masks to common VT-x code isaku.yamahata
2021-11-25 20:08 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 46/59] KVM: VMX: Move register caching logic to common code isaku.yamahata
2021-11-25 20:11 ` Thomas Gleixner
2021-11-25 20:17 ` Paolo Bonzini
2021-11-29 18:23 ` Sean Christopherson
2021-11-29 18:28 ` Paolo Bonzini
2021-11-25 0:20 ` [RFC PATCH v3 47/59] KVM: TDX: Define TDCALL exit reason isaku.yamahata
2021-11-25 20:19 ` Thomas Gleixner
2021-11-29 18:36 ` Sean Christopherson
2021-11-25 0:20 ` [RFC PATCH v3 48/59] KVM: TDX: Stub in tdx.h with structs, accessors, and VMCS helpers isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 49/59] KVM: VMX: Add macro framework to read/write VMCS for VMs and TDs isaku.yamahata
2021-11-25 20:24 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 50/59] KVM: VMX: Move AR_BYTES encoder/decoder helpers to common.h isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 51/59] KVM: VMX: MOVE GDT and IDT accessors to common code isaku.yamahata
2021-11-25 20:25 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 52/59] KVM: VMX: Move .get_interrupt_shadow() implementation to common VMX code isaku.yamahata
2021-11-25 20:26 ` Thomas Gleixner
2021-11-25 0:20 ` [RFC PATCH v3 53/59] KVM: x86: Add a helper function to restore 4 host MSRs on exit to user space isaku.yamahata
2021-11-25 20:34 ` Thomas Gleixner
2021-11-26 9:19 ` Chao Gao
2021-11-26 9:40 ` Paolo Bonzini
2021-11-29 7:08 ` Lai Jiangshan
2021-11-29 9:26 ` Chao Gao
2021-11-30 4:58 ` Lai Jiangshan
2021-11-30 8:19 ` Chao Gao
2021-11-30 11:18 ` Lai Jiangshan
2021-11-25 0:20 ` [RFC PATCH v3 54/59] KVM: X86: Introduce initial_tsc_khz in struct kvm_arch isaku.yamahata
2021-11-25 20:48 ` Paolo Bonzini
2021-11-25 21:05 ` Thomas Gleixner
2021-11-25 22:13 ` Paolo Bonzini
2021-11-25 22:59 ` Thomas Gleixner
2021-11-25 23:26 ` Thomas Gleixner
2021-11-26 7:56 ` Paolo Bonzini
2021-11-29 23:38 ` Sean Christopherson
2021-11-25 0:20 ` [RFC PATCH v3 55/59] KVM: TDX: Add "basic" support for building and running Trust Domains isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 56/59] KVM: TDX: Protect private mapping related SEAMCALLs with spinlock isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 57/59] KVM, x86/mmu: Support TDX private mapping for TDP MMU isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 58/59] KVM: TDX: exit to user space on GET_QUOTE, SETUP_EVENT_NOTIFY_INTERRUPT isaku.yamahata
2021-11-25 0:20 ` [RFC PATCH v3 59/59] Documentation/virtual/kvm: Add Trust Domain Extensions(TDX) isaku.yamahata
2021-11-25 2:12 ` [RFC PATCH v3 00/59] KVM: X86: TDX support Xiaoyao Li
2021-11-30 18:51 ` Sean Christopherson
2021-12-01 13:22 ` Kai Huang
2021-12-01 19:08 ` Isaku Yamahata
2021-12-01 19:32 ` Sean Christopherson
2021-12-01 20:28 ` Kai Huang
2021-12-01 15:05 ` Paolo Bonzini
2021-12-01 20:16 ` Kai Huang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=0c4325595029876a7bfa0d1fc3d5ff93bb6b026e.1637799475.git.isaku.yamahata@intel.com \
--to=isaku.yamahata@intel.com \
--cc=bp@alien8.de \
--cc=ckuehl@redhat.com \
--cc=erdemaktas@google.com \
--cc=hpa@zytor.com \
--cc=isaku.yamahata@gmail.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).