* [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2
@ 2018-07-27 16:56 Paolo Bonzini
2018-07-27 16:56 ` [PATCH 1/4] x86/kvm/mmu: make vcpu->mmu a pointer to the current MMU Paolo Bonzini
` (4 more replies)
0 siblings, 5 replies; 7+ messages in thread
From: Paolo Bonzini @ 2018-07-27 16:56 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: vkuznets
This is a rebased version of Vitaly's RFC series. This isn't
quite ready for application as I haven't yet thought through
the interactions between the root_mmu/guest_mmu split and
the multi-root caching.
Speaking of the multi-root caching, it is a bit of a duplicate work
with Vitaly's last three patches that avoided reinitialization if
the parameters and CR3 matched, so the series got smaller too.
The scalability improvement on the nested CPUID benchamrk is sensible:
-smp 1 -smp 16 -smp 48
4.18 18k 86k
kvm/queue 18k 68k
+gup_fast 18k 42k
+guest_mmu 18k 26k 42k
The slowdown between -smp 16 and -smp 48 is partly due to SMT,
because the machine has 28 cores.
Paolo
Vitaly Kuznetsov (4):
x86/kvm/mmu: make vcpu->mmu a pointer to the current MMU
x86/kvm/mmu.c: set get_pdptr hook in kvm_init_shadow_ept_mmu()
x86/kvm/mmu.c: add kvm_mmu parameter to kvm_mmu_free_roots()
x86/kvm/mmu: introduce guest_mmu
arch/x86/include/asm/kvm_host.h | 11 ++-
arch/x86/kvm/mmu.c | 183 +++++++++++++++++++++-------------------
arch/x86/kvm/mmu.h | 8 +-
arch/x86/kvm/mmu_audit.c | 12 +--
arch/x86/kvm/paging_tmpl.h | 15 ++--
arch/x86/kvm/svm.c | 14 +--
arch/x86/kvm/vmx.c | 43 ++++++----
arch/x86/kvm/x86.c | 20 ++---
8 files changed, 168 insertions(+), 138 deletions(-)
--
1.8.3.1
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH 1/4] x86/kvm/mmu: make vcpu->mmu a pointer to the current MMU
2018-07-27 16:56 [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Paolo Bonzini
@ 2018-07-27 16:56 ` Paolo Bonzini
2018-07-27 16:56 ` [PATCH 2/4] x86/kvm/mmu.c: set get_pdptr hook in kvm_init_shadow_ept_mmu() Paolo Bonzini
` (3 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: Paolo Bonzini @ 2018-07-27 16:56 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: vkuznets
From: Vitaly Kuznetsov <vkuznets@redhat.com>
As a preparation to full MMU split between L1 and L2 make vcpu->arch.mmu
a pointer to the currently used mmu. For now, this is always
vcpu->arch.root_mmu. No functional change.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 5 +-
arch/x86/kvm/mmu.c | 165 ++++++++++++++++++++--------------------
arch/x86/kvm/mmu.h | 8 +-
arch/x86/kvm/mmu_audit.c | 12 +--
arch/x86/kvm/paging_tmpl.h | 15 ++--
arch/x86/kvm/svm.c | 14 ++--
arch/x86/kvm/vmx.c | 15 ++--
arch/x86/kvm/x86.c | 20 ++---
8 files changed, 130 insertions(+), 124 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 150937e64f63..7ae8ae58f3bd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -533,7 +533,10 @@ struct kvm_vcpu_arch {
* the paging mode of the l1 guest. This context is always used to
* handle faults.
*/
- struct kvm_mmu mmu;
+ struct kvm_mmu *mmu;
+
+ /* Non-nested MMU for L1 */
+ struct kvm_mmu root_mmu;
/*
* Paging state of an L2 guest (used for nested npt)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 22a7984c68a5..0a40afd71d74 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2137,7 +2137,7 @@ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
if (sp->role.cr4_pae != !!is_pae(vcpu)
- || vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
+ || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
return false;
}
@@ -2331,14 +2331,14 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
int collisions = 0;
LIST_HEAD(invalid_list);
- role = vcpu->arch.mmu.base_role;
+ role = vcpu->arch.mmu->base_role;
role.level = level;
role.direct = direct;
if (role.direct)
role.cr4_pae = 0;
role.access = access;
- if (!vcpu->arch.mmu.direct_map
- && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
+ if (!vcpu->arch.mmu->direct_map
+ && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
@@ -2413,11 +2413,11 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
{
iterator->addr = addr;
iterator->shadow_addr = root;
- iterator->level = vcpu->arch.mmu.shadow_root_level;
+ iterator->level = vcpu->arch.mmu->shadow_root_level;
if (iterator->level == PT64_ROOT_4LEVEL &&
- vcpu->arch.mmu.root_level < PT64_ROOT_4LEVEL &&
- !vcpu->arch.mmu.direct_map)
+ vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
+ !vcpu->arch.mmu->direct_map)
--iterator->level;
if (iterator->level == PT32E_ROOT_LEVEL) {
@@ -2425,10 +2425,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
* prev_root is currently only used for 64-bit hosts. So only
* the active root_hpa is valid here.
*/
- BUG_ON(root != vcpu->arch.mmu.root_hpa);
+ BUG_ON(root != vcpu->arch.mmu->root_hpa);
iterator->shadow_addr
- = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+ = vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
--iterator->level;
if (!iterator->shadow_addr)
@@ -2439,7 +2439,7 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
struct kvm_vcpu *vcpu, u64 addr)
{
- shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu.root_hpa,
+ shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root_hpa,
addr);
}
@@ -3050,7 +3050,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
int emulate = 0;
gfn_t pseudo_gfn;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return 0;
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
@@ -3265,7 +3265,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
u64 spte = 0ull;
uint retry_count = 0;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return false;
if (!page_fault_can_be_fast(error_code))
@@ -3439,7 +3439,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free)
{
int i;
LIST_HEAD(invalid_list);
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);
@@ -3499,20 +3499,20 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
struct kvm_mmu_page *sp;
unsigned i;
- if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
+ if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
spin_lock(&vcpu->kvm->mmu_lock);
if(make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, 0, 0,
- vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
+ vcpu->arch.mmu->shadow_root_level, 1, ACC_ALL);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.root_hpa = __pa(sp->spt);
- } else if (vcpu->arch.mmu.shadow_root_level == PT32E_ROOT_LEVEL) {
+ vcpu->arch.mmu->root_hpa = __pa(sp->spt);
+ } else if (vcpu->arch.mmu->shadow_root_level == PT32E_ROOT_LEVEL) {
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
MMU_WARN_ON(VALID_PAGE(root));
spin_lock(&vcpu->kvm->mmu_lock);
@@ -3525,9 +3525,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
+ vcpu->arch.mmu->pae_root[i] = root | PT_PRESENT_MASK;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
} else
BUG();
@@ -3541,7 +3541,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
gfn_t root_gfn;
int i;
- root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> PAGE_SHIFT;
+ root_gfn = vcpu->arch.mmu->get_cr3(vcpu) >> PAGE_SHIFT;
if (mmu_check_root(vcpu, root_gfn))
return 1;
@@ -3550,8 +3550,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* Do we shadow a long mode page table? If so we need to
* write-protect the guests page table root.
*/
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
MMU_WARN_ON(VALID_PAGE(root));
@@ -3561,11 +3561,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
- vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
+ vcpu->arch.mmu->shadow_root_level, 0, ACC_ALL);
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.root_hpa = root;
+ vcpu->arch.mmu->root_hpa = root;
return 0;
}
@@ -3575,17 +3575,17 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* the shadow page table may be a PAE or a long mode page table.
*/
pm_mask = PT_PRESENT_MASK;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL)
+ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
MMU_WARN_ON(VALID_PAGE(root));
- if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
- pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
+ if (vcpu->arch.mmu->root_level == PT32E_ROOT_LEVEL) {
+ pdptr = vcpu->arch.mmu->get_pdptr(vcpu, i);
if (!(pdptr & PT_PRESENT_MASK)) {
- vcpu->arch.mmu.pae_root[i] = 0;
+ vcpu->arch.mmu->pae_root[i] = 0;
continue;
}
root_gfn = pdptr >> PAGE_SHIFT;
@@ -3603,16 +3603,16 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.pae_root[i] = root | pm_mask;
+ vcpu->arch.mmu->pae_root[i] = root | pm_mask;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
/*
* If we shadow a 32 bit page table with a long mode page
* table we enter this path.
*/
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL) {
- if (vcpu->arch.mmu.lm_root == NULL) {
+ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
+ if (vcpu->arch.mmu->lm_root == NULL) {
/*
* The additional page necessary for this is only
* allocated on demand.
@@ -3624,12 +3624,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
if (lm_root == NULL)
return 1;
- lm_root[0] = __pa(vcpu->arch.mmu.pae_root) | pm_mask;
+ lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;
- vcpu->arch.mmu.lm_root = lm_root;
+ vcpu->arch.mmu->lm_root = lm_root;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.lm_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
}
return 0;
@@ -3637,7 +3637,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return mmu_alloc_direct_roots(vcpu);
else
return mmu_alloc_shadow_roots(vcpu);
@@ -3648,17 +3648,16 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
int i;
struct kvm_mmu_page *sp;
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
-
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
sp = page_header(root);
/*
@@ -3689,7 +3688,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
@@ -3763,7 +3762,7 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
int root, leaf;
bool reserved = false;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
goto exit;
walk_shadow_page_lockless_begin(vcpu);
@@ -3780,7 +3779,7 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
if (!is_shadow_present_pte(spte))
break;
- reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+ reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte,
iterator.level);
}
@@ -3859,7 +3858,7 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
struct kvm_shadow_walk_iterator iterator;
u64 spte;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
walk_shadow_page_lockless_begin(vcpu);
@@ -3886,7 +3885,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
if (r)
return r;
- MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
return nonpaging_map(vcpu, gva & PAGE_MASK,
@@ -3899,8 +3898,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
arch.gfn = gfn;
- arch.direct_map = vcpu->arch.mmu.direct_map;
- arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
+ arch.direct_map = vcpu->arch.mmu->direct_map;
+ arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
@@ -4005,7 +4004,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
int write = error_code & PFERR_WRITE_MASK;
bool map_writable;
- MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
if (page_fault_handle_page_track(vcpu, error_code, gfn))
return RET_PF_EMULATE;
@@ -4081,7 +4080,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3,
{
uint i;
struct kvm_mmu_root_info root;
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
root.cr3 = mmu->get_cr3(vcpu);
root.hpa = mmu->root_hpa;
@@ -4104,7 +4103,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
union kvm_mmu_page_role new_role,
bool skip_tlb_flush)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
/*
* For now, limit the fast switch to 64-bit hosts+VMs in order to avoid
@@ -4173,7 +4172,7 @@ static unsigned long get_cr3(struct kvm_vcpu *vcpu)
static void inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
- vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+ vcpu->arch.mmu->inject_page_fault(vcpu, fault);
}
static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
@@ -4694,7 +4693,7 @@ static void paging32E_init_context(struct kvm_vcpu *vcpu,
static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
context->base_role.word = mmu_base_role_mask.word &
kvm_calc_tdp_mmu_root_page_role(vcpu).word;
@@ -4766,7 +4765,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
if (!is_paging(vcpu))
nonpaging_init_context(vcpu, context);
@@ -4786,7 +4785,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
static union kvm_mmu_page_role
kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
{
- union kvm_mmu_page_role role = vcpu->arch.mmu.base_role;
+ union kvm_mmu_page_role role = vcpu->arch.mmu->base_role;
role.level = PT64_ROOT_4LEVEL;
role.direct = false;
@@ -4800,7 +4799,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty, gpa_t new_eptp)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
union kvm_mmu_page_role root_page_role =
kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty);
@@ -4827,7 +4826,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
kvm_init_shadow_mmu(vcpu);
context->set_cr3 = kvm_x86_ops->set_cr3;
@@ -4845,7 +4844,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
g_context->inject_page_fault = kvm_inject_page_fault;
/*
- * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using
+ * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using
* L1's nested page tables (e.g. EPT12). The nested translation
* of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
* L2's page tables as the first level of translation and L1's
@@ -4884,10 +4883,10 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots)
if (reset_roots) {
uint i;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.mmu->root_hpa = INVALID_PAGE;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+ vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
}
if (mmu_is_nested(vcpu))
@@ -4936,7 +4935,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
kvm_mmu_free_roots(vcpu, KVM_MMU_ROOTS_ALL);
- WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ WARN_ON(VALID_PAGE(vcpu->arch.mmu->root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);
@@ -4950,7 +4949,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
}
++vcpu->kvm->stat.mmu_pte_updated;
- vcpu->arch.mmu.update_pte(vcpu, sp, spte, new);
+ vcpu->arch.mmu->update_pte(vcpu, sp, spte, new);
}
static bool need_remote_flush(u64 old, u64 new)
@@ -5130,7 +5129,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
entry = *spte;
mmu_page_zap_pte(vcpu->kvm, sp, spte);
if (gentry &&
- !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
+ !((sp->role.word ^ vcpu->arch.mmu->base_role.word)
& mmu_base_role_mask.word) && rmap_can_add(vcpu))
mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
if (need_remote_flush(entry, *spte))
@@ -5148,7 +5147,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
gpa_t gpa;
int r;
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return 0;
gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
@@ -5184,10 +5183,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
{
int r, emulation_type = EMULTYPE_RETRY;
enum emulation_result er;
- bool direct = vcpu->arch.mmu.direct_map;
+ bool direct = vcpu->arch.mmu->direct_map;
/* With shadow page tables, fault_address contains a GVA or nGPA. */
- if (vcpu->arch.mmu.direct_map) {
+ if (vcpu->arch.mmu->direct_map) {
vcpu->arch.gpa_available = true;
vcpu->arch.gpa_val = cr2;
}
@@ -5202,8 +5201,9 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
}
if (r == RET_PF_INVALID) {
- r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
- false);
+ r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+ lower_32_bits(error_code),
+ false);
WARN_ON(r == RET_PF_INVALID);
}
@@ -5219,7 +5219,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
* paging in both guests. If true, we simply unprotect the page
* and resume the guest.
*/
- if (vcpu->arch.mmu.direct_map &&
+ if (vcpu->arch.mmu->direct_map &&
(error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
return 1;
@@ -5256,7 +5256,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
int i;
/* INVLPG on a * non-canonical address is a NOP according to the SDM. */
@@ -5287,7 +5287,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
bool tlb_flush = false;
uint i;
@@ -5331,8 +5331,8 @@ void kvm_disable_tdp(void)
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
- free_page((unsigned long)vcpu->arch.mmu.pae_root);
- free_page((unsigned long)vcpu->arch.mmu.lm_root);
+ free_page((unsigned long)vcpu->arch.mmu->pae_root);
+ free_page((unsigned long)vcpu->arch.mmu->lm_root);
}
static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
@@ -5349,9 +5349,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
if (!page)
return -ENOMEM;
- vcpu->arch.mmu.pae_root = page_address(page);
+ vcpu->arch.mmu->pae_root = page_address(page);
for (i = 0; i < 4; ++i)
- vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
+ vcpu->arch.mmu->pae_root[i] = INVALID_PAGE;
return 0;
}
@@ -5360,20 +5360,21 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
{
uint i;
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
- vcpu->arch.mmu.translate_gpa = translate_gpa;
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.root_mmu.translate_gpa = translate_gpa;
vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+ vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
return alloc_mmu_pages(vcpu);
}
void kvm_mmu_setup(struct kvm_vcpu *vcpu)
{
- MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu->root_hpa));
kvm_init_mmu(vcpu, true);
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 1fab69c0b2f3..f602b26140a3 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -80,7 +80,7 @@ static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
- if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE))
+ if (likely(vcpu->arch.mmu->root_hpa != INVALID_PAGE))
return 0;
return kvm_mmu_load(vcpu);
@@ -102,9 +102,9 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu)
{
- if (VALID_PAGE(vcpu->arch.mmu.root_hpa))
- vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa |
- kvm_get_active_pcid(vcpu));
+ if (VALID_PAGE(vcpu->arch.mmu->root_hpa))
+ vcpu->arch.mmu->set_cr3(vcpu, vcpu->arch.mmu->root_hpa |
+ kvm_get_active_pcid(vcpu));
}
/*
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 1272861e77b9..abac7e208853 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -59,19 +59,19 @@ static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
int i;
struct kvm_mmu_page *sp;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
sp = page_header(root);
- __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu.root_level);
+ __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu->root_level);
return;
}
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
@@ -122,7 +122,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
hpa = pfn << PAGE_SHIFT;
if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
audit_printk(vcpu->kvm, "levels %d pfn %llx hpa %llx "
- "ent %llxn", vcpu->arch.mmu.root_level, pfn,
+ "ent %llxn", vcpu->arch.mmu->root_level, pfn,
hpa, *sptep);
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 14ffd973df54..7cf2185b7eb5 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -158,14 +158,15 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *spte,
u64 gpte)
{
- if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+ if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
goto no_present;
if (!FNAME(is_present_gpte)(gpte))
goto no_present;
/* if accessed bit is not supported prefetch non accessed gpte */
- if (PT_HAVE_ACCESSED_DIRTY(&vcpu->arch.mmu) && !(gpte & PT_GUEST_ACCESSED_MASK))
+ if (PT_HAVE_ACCESSED_DIRTY(vcpu->arch.mmu) &&
+ !(gpte & PT_GUEST_ACCESSED_MASK))
goto no_present;
return false;
@@ -480,7 +481,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
static int FNAME(walk_addr)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, gva_t addr, u32 access)
{
- return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.mmu, addr,
+ return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
access);
}
@@ -509,7 +510,7 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access & FNAME(gpte_access)(gpte);
- FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
no_dirty_log && (pte_access & ACC_WRITE_MASK));
if (is_error_pfn(pfn))
@@ -604,7 +605,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
direct_access = gw->pte_access;
- top_level = vcpu->arch.mmu.root_level;
+ top_level = vcpu->arch.mmu->root_level;
if (top_level == PT32E_ROOT_LEVEL)
top_level = PT32_ROOT_LEVEL;
/*
@@ -616,7 +617,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
if (FNAME(gpte_changed)(vcpu, gw, top_level))
goto out_gpte_changed;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
goto out_gpte_changed;
for (shadow_walk_init(&it, vcpu, addr);
@@ -1004,7 +1005,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access;
pte_access &= FNAME(gpte_access)(gpte);
- FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
&nr_present))
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 73e27a98456f..f73a57ddbc57 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2919,18 +2919,18 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
{
WARN_ON(mmu_is_nested(vcpu));
kvm_init_shadow_mmu(vcpu);
- vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3;
- vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3;
- vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr;
- vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
- vcpu->arch.mmu.shadow_root_level = get_npt_level(vcpu);
- reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
+ vcpu->arch.mmu->set_cr3 = nested_svm_set_tdp_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_svm_get_tdp_cr3;
+ vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr;
+ vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
+ vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu);
+ reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu);
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
}
static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static int nested_svm_check_permissions(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 56c7c7a62a06..3ee8137b2026 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4819,9 +4819,10 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
bool invalidate_gpa)
{
if (enable_ept && (invalidate_gpa || !enable_vpid)) {
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
+ ept_sync_context(construct_eptp(vcpu,
+ vcpu->arch.mmu->root_hpa));
} else {
vpid_sync_context(vpid);
}
@@ -8888,7 +8889,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
}
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- if (kvm_get_pcid(vcpu, vcpu->arch.mmu.prev_roots[i].cr3)
+ if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3)
== operand.pcid)
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
@@ -10911,9 +10912,9 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
VMX_EPT_EXECUTE_ONLY_BIT,
nested_ept_ad_enabled(vcpu),
nested_ept_get_cr3(vcpu));
- vcpu->arch.mmu.set_cr3 = vmx_set_cr3;
- vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3;
- vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->set_cr3 = vmx_set_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3;
+ vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
return 0;
@@ -10921,7 +10922,7 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 153564db7980..b49091a55865 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -502,7 +502,7 @@ static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fau
if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
else
- vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+ vcpu->arch.mmu->inject_page_fault(vcpu, fault);
return fault->nested_page_fault;
}
@@ -601,7 +601,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if ((pdpte[i] & PT_PRESENT_MASK) &&
(pdpte[i] &
- vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+ vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) {
ret = 0;
goto out;
}
@@ -4761,7 +4761,7 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
/* NPT walks are always user-walks */
access |= PFERR_USER_MASK;
- t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
+ t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception);
return t_gpa;
}
@@ -5841,7 +5841,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
if (emulation_type & EMULTYPE_NO_REEXECUTE)
return false;
- if (!vcpu->arch.mmu.direct_map) {
+ if (!vcpu->arch.mmu->direct_map) {
/*
* Write permission should be allowed since only
* write access need to be emulated.
@@ -5874,7 +5874,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
kvm_release_pfn_clean(pfn);
/* The instructions are well-emulated on direct mmu. */
- if (vcpu->arch.mmu.direct_map) {
+ if (vcpu->arch.mmu->direct_map) {
unsigned int indirect_shadow_pages;
spin_lock(&vcpu->kvm->mmu_lock);
@@ -5938,7 +5938,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
vcpu->arch.last_retry_eip = ctxt->eip;
vcpu->arch.last_retry_addr = cr2;
- if (!vcpu->arch.mmu.direct_map)
+ if (!vcpu->arch.mmu->direct_map)
gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
@@ -9236,7 +9236,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
{
int r;
- if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
+ if ((vcpu->arch.mmu->direct_map != work->arch.direct_map) ||
work->wakeup_all)
return;
@@ -9244,11 +9244,11 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
if (unlikely(r))
return;
- if (!vcpu->arch.mmu.direct_map &&
- work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu))
+ if (!vcpu->arch.mmu->direct_map &&
+ work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
return;
- vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true);
+ vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
}
static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
--
1.8.3.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH 2/4] x86/kvm/mmu.c: set get_pdptr hook in kvm_init_shadow_ept_mmu()
2018-07-27 16:56 [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Paolo Bonzini
2018-07-27 16:56 ` [PATCH 1/4] x86/kvm/mmu: make vcpu->mmu a pointer to the current MMU Paolo Bonzini
@ 2018-07-27 16:56 ` Paolo Bonzini
2018-07-27 16:56 ` [PATCH 3/4] x86/kvm/mmu.c: add kvm_mmu parameter to kvm_mmu_free_roots() Paolo Bonzini
` (2 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: Paolo Bonzini @ 2018-07-27 16:56 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: vkuznets
From: Vitaly Kuznetsov <vkuznets@redhat.com>
kvm_init_shadow_ept_mmu() doesn't set get_pdptr() hook and is this
not a problem just because MMU context is already initialized and this
hook points to kvm_pdptr_read(). As we're intended to use a dedicated
MMU for shadow EPT MMU set this hook explicitly.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/mmu.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 0a40afd71d74..b013aec73d46 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4816,6 +4816,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
context->root_level = PT64_ROOT_4LEVEL;
context->direct_map = false;
context->base_role.word = root_page_role.word & mmu_base_role_mask.word;
+ context->get_pdptr = kvm_pdptr_read;
+
update_permission_bitmask(vcpu, context, true);
update_pkru_bitmask(vcpu, context, true);
update_last_nonleaf_level(vcpu, context);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH 3/4] x86/kvm/mmu.c: add kvm_mmu parameter to kvm_mmu_free_roots()
2018-07-27 16:56 [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Paolo Bonzini
2018-07-27 16:56 ` [PATCH 1/4] x86/kvm/mmu: make vcpu->mmu a pointer to the current MMU Paolo Bonzini
2018-07-27 16:56 ` [PATCH 2/4] x86/kvm/mmu.c: set get_pdptr hook in kvm_init_shadow_ept_mmu() Paolo Bonzini
@ 2018-07-27 16:56 ` Paolo Bonzini
2018-07-27 16:56 ` [PATCH 4/4] x86/kvm/mmu: introduce guest_mmu Paolo Bonzini
2018-07-31 15:58 ` [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Vitaly Kuznetsov
4 siblings, 0 replies; 7+ messages in thread
From: Paolo Bonzini @ 2018-07-27 16:56 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: vkuznets
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Add an option to specify which MMU root we want to free. This will
be used when nested and non-nested MMUs for L1 are split.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 3 ++-
arch/x86/kvm/mmu.c | 9 +++++----
arch/x86/kvm/vmx.c | 2 +-
3 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7ae8ae58f3bd..7b157cd43e1f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1325,7 +1325,8 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state,
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free);
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ ulong roots_to_free);
gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b013aec73d46..1bcab6f9d1c8 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3435,11 +3435,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
}
/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free)
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ ulong roots_to_free)
{
int i;
LIST_HEAD(invalid_list);
- struct kvm_mmu *mmu = vcpu->arch.mmu;
bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);
@@ -4154,7 +4154,8 @@ static void __kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3,
bool skip_tlb_flush)
{
if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush))
- kvm_mmu_free_roots(vcpu, KVM_MMU_ROOT_CURRENT);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu,
+ KVM_MMU_ROOT_CURRENT);
}
void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush)
@@ -4936,7 +4937,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
- kvm_mmu_free_roots(vcpu, KVM_MMU_ROOTS_ALL);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOTS_ALL);
WARN_ON(VALID_PAGE(vcpu->arch.mmu->root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3ee8137b2026..362842f9b523 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8893,7 +8893,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
== operand.pcid)
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
- kvm_mmu_free_roots(vcpu, roots_to_free);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
/*
* If neither the current cr3 nor any of the prev_roots use the
* given PCID, then nothing needs to be done here because a
--
1.8.3.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH 4/4] x86/kvm/mmu: introduce guest_mmu
2018-07-27 16:56 [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Paolo Bonzini
` (2 preceding siblings ...)
2018-07-27 16:56 ` [PATCH 3/4] x86/kvm/mmu.c: add kvm_mmu parameter to kvm_mmu_free_roots() Paolo Bonzini
@ 2018-07-27 16:56 ` Paolo Bonzini
2018-07-31 15:58 ` [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Vitaly Kuznetsov
4 siblings, 0 replies; 7+ messages in thread
From: Paolo Bonzini @ 2018-07-27 16:56 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: vkuznets
From: Vitaly Kuznetsov <vkuznets@redhat.com>
When EPT is used for nested guest we need to re-init MMU as shadow
EPT MMU (nested_ept_init_mmu_context() does that). When we return back
from L2 to L1 kvm_mmu_reset_context() in nested_vmx_load_cr3() resets
MMU back to normal TDP mode. Add a special 'guest_mmu' so we can use
separate root caches; the improved hit rate is not very important for
single vCPU performance, but it avoids contention on the mmu_lock for
many vCPUs.
On the nested CPUID benchmark, with 16 vCPUs, an L2->L1->L2 vmexit
goes from 42k to 26k cycles.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 3 +++
arch/x86/kvm/mmu.c | 15 +++++++++++----
arch/x86/kvm/vmx.c | 26 ++++++++++++++++++--------
3 files changed, 32 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7b157cd43e1f..932c3285739f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -538,6 +538,9 @@ struct kvm_vcpu_arch {
/* Non-nested MMU for L1 */
struct kvm_mmu root_mmu;
+ /* L1 MMU when running nested */
+ struct kvm_mmu guest_mmu;
+
/*
* Paging state of an L2 guest (used for nested npt)
*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1bcab6f9d1c8..3e3c351b5c61 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4937,8 +4937,10 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
- kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOTS_ALL);
- WARN_ON(VALID_PAGE(vcpu->arch.mmu->root_hpa));
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa));
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);
@@ -5365,13 +5367,18 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
vcpu->arch.mmu = &vcpu->arch.root_mmu;
vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+
vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
vcpu->arch.root_mmu.translate_gpa = translate_gpa;
- vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
-
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+ vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+
+ vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
return alloc_mmu_pages(vcpu);
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 362842f9b523..644a8e009947 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8175,8 +8175,10 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
* Free whatever needs to be freed from vmx->nested when L1 goes down, or
* just stops using VMX.
*/
-static void free_nested(struct vcpu_vmx *vmx)
+static void free_nested(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
@@ -8209,6 +8211,8 @@ static void free_nested(struct vcpu_vmx *vmx)
vmx->nested.pi_desc = NULL;
}
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
free_loaded_vmcs(&vmx->nested.vmcs02);
}
@@ -8217,7 +8221,7 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
{
if (!nested_vmx_check_permission(vcpu))
return 1;
- free_nested(to_vmx(vcpu));
+ free_nested(vcpu);
nested_vmx_succeed(vcpu);
return kvm_skip_emulated_instruction(vcpu);
}
@@ -8248,6 +8252,8 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vmx);
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
kvm_vcpu_write_guest(vcpu,
vmptr + offsetof(struct vmcs12, launch_state),
&zero, sizeof(zero));
@@ -8631,6 +8637,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
}
nested_release_vmcs12(vmx);
+
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
/*
* Load VMCS12 from guest memory since it is not already
* cached.
@@ -10576,12 +10584,12 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
*/
static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
- vcpu_load(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- free_nested(vmx);
- vcpu_put(vcpu);
+ vcpu_load(vcpu);
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ free_nested(vcpu);
+ vcpu_put(vcpu);
}
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
@@ -10907,6 +10915,7 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu)))
return 1;
+ vcpu->arch.mmu = &vcpu->arch.guest_mmu;
kvm_init_shadow_ept_mmu(vcpu,
to_vmx(vcpu)->nested.msrs.ept_caps &
VMX_EPT_EXECUTE_ONLY_BIT,
@@ -10922,6 +10931,7 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
@@ -12960,7 +12970,7 @@ static void vmx_leave_nested(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
}
- free_nested(to_vmx(vcpu));
+ free_nested(vcpu);
}
/*
--
1.8.3.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2
2018-07-27 16:56 [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Paolo Bonzini
` (3 preceding siblings ...)
2018-07-27 16:56 ` [PATCH 4/4] x86/kvm/mmu: introduce guest_mmu Paolo Bonzini
@ 2018-07-31 15:58 ` Vitaly Kuznetsov
2018-07-31 16:52 ` Paolo Bonzini
4 siblings, 1 reply; 7+ messages in thread
From: Vitaly Kuznetsov @ 2018-07-31 15:58 UTC (permalink / raw)
To: Paolo Bonzini; +Cc: linux-kernel, kvm
Paolo Bonzini <pbonzini@redhat.com> writes:
> This is a rebased version of Vitaly's RFC series. This isn't
> quite ready for application as I haven't yet thought through
> the interactions between the root_mmu/guest_mmu split and
> the multi-root caching.
>
> Speaking of the multi-root caching, it is a bit of a duplicate work
> with Vitaly's last three patches that avoided reinitialization if
> the parameters and CR3 matched, so the series got smaller too.
>
Thank you for the rebase,
it seems that with multi-root caching this series should just ignore CR3
changes for both root_mmu and guest_mmu: we now have two separate
'prev_roots' caches and these work well. However, we still can optimize
MMU re-initialization on L1->L2 and L2->L1 switches out using e.g. my
'scache' idea (which can be orthogonal to page_role check on CR3).
In my Hyper-V-on-KVM environment I'm seeing an additional 1000 CPU
cycles win for a nested vmexit.
I'll pull things together and re-send the whole series.
--
Vitaly
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2
2018-07-31 15:58 ` [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Vitaly Kuznetsov
@ 2018-07-31 16:52 ` Paolo Bonzini
0 siblings, 0 replies; 7+ messages in thread
From: Paolo Bonzini @ 2018-07-31 16:52 UTC (permalink / raw)
To: Vitaly Kuznetsov; +Cc: linux-kernel, kvm
On 31/07/2018 17:58, Vitaly Kuznetsov wrote:
> Thank you for the rebase,
>
> it seems that with multi-root caching this series should just ignore CR3
> changes for both root_mmu and guest_mmu: we now have two separate
> 'prev_roots' caches and these work well. However, we still can optimize
> MMU re-initialization on L1->L2 and L2->L1 switches out using e.g. my
> 'scache' idea (which can be orthogonal to page_role check on CR3).
Indeed, though if possible the scache should be based on the role to
avoid duplicating code and data structures.
(Also I didn't quite have time to figure out _why_ without
root_mmu/guest_mmu there is still contention, it's probably something
trivial).
Paolo
> In my Hyper-V-on-KVM environment I'm seeing an additional 1000 CPU
> cycles win for a nested vmexit.
>
> I'll pull things together and re-send the whole series.
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2018-07-31 16:52 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-07-27 16:56 [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Paolo Bonzini
2018-07-27 16:56 ` [PATCH 1/4] x86/kvm/mmu: make vcpu->mmu a pointer to the current MMU Paolo Bonzini
2018-07-27 16:56 ` [PATCH 2/4] x86/kvm/mmu.c: set get_pdptr hook in kvm_init_shadow_ept_mmu() Paolo Bonzini
2018-07-27 16:56 ` [PATCH 3/4] x86/kvm/mmu.c: add kvm_mmu parameter to kvm_mmu_free_roots() Paolo Bonzini
2018-07-27 16:56 ` [PATCH 4/4] x86/kvm/mmu: introduce guest_mmu Paolo Bonzini
2018-07-31 15:58 ` [PATCH rebase/RFC 0/4] x86/kvm/nVMX: optimize MMU switch between L1 and L2 Vitaly Kuznetsov
2018-07-31 16:52 ` Paolo Bonzini
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).