| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1248705048-22607-4-git-send-email-joerg.roedel@amd.com>
Date: Mon, 27 Jul 2009 16:30:44 +0200
From: Joerg Roedel <joerg.roedel@....com>
To: Avi Kivity <avi@...hat.com>, Marcelo Tosatti <marcelo@...ck.org>
CC: linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
Joerg Roedel <joerg.roedel@....com>
Subject: [PATCH 3/7] kvm/mmu: make direct mapping paths aware of mapping levels
Signed-off-by: Joerg Roedel <joerg.roedel@....com>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/mmu.c | 74 ++++++++++++++++++++++----------------
arch/x86/kvm/paging_tmpl.h | 6 ++--
3 files changed, 47 insertions(+), 35 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e210b21..e09dc26 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -315,7 +315,7 @@ struct kvm_vcpu_arch {
struct {
gfn_t gfn; /* presumed gfn during guest pte update */
pfn_t pfn; /* pfn corresponding to that gfn */
- int largepage;
+ int level;
unsigned long mmu_seq;
} update_pte;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7a03216..ffea432 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -257,7 +257,7 @@ static int is_last_spte(u64 pte, int level)
{
if (level == PT_PAGE_TABLE_LEVEL)
return 1;
- if (level == PT_DIRECTORY_LEVEL && is_large_pte(pte))
+ if (is_large_pte(pte))
return 1;
return 0;
}
@@ -746,7 +746,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
int (*handler)(struct kvm *kvm, unsigned long *rmapp))
{
- int i;
+ int i, j;
int retval = 0;
/*
@@ -765,11 +765,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
end = start + (memslot->npages << PAGE_SHIFT);
if (hva >= start && hva < end) {
gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
- int idx = gfn_offset /
- KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL);
+
retval |= handler(kvm, &memslot->rmap[gfn_offset]);
- retval |= handler(kvm,
- &memslot->lpage_info[0][idx].rmap_pde);
+
+ for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
+ int idx = gfn_offset;
+ idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j);
+ retval |= handler(kvm,
+ &memslot->lpage_info[j][idx].rmap_pde);
+ }
}
}
@@ -1714,7 +1718,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pte_access, int user_fault,
- int write_fault, int dirty, int largepage,
+ int write_fault, int dirty, int level,
gfn_t gfn, pfn_t pfn, bool speculative,
bool can_unsync)
{
@@ -1737,7 +1741,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
spte |= shadow_nx_mask;
if (pte_access & ACC_USER_MASK)
spte |= shadow_user_mask;
- if (largepage)
+ if (level > PT_PAGE_TABLE_LEVEL)
spte |= PT_PAGE_SIZE_MASK;
if (tdp_enabled)
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
@@ -1748,7 +1752,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
if ((pte_access & ACC_WRITE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
- if (largepage && has_wrprotected_page(vcpu->kvm, gfn, 1)) {
+ if (level > PT_PAGE_TABLE_LEVEL &&
+ has_wrprotected_page(vcpu->kvm, gfn, level)) {
ret = 1;
spte = shadow_trap_nonpresent_pte;
goto set_pte;
@@ -1786,7 +1791,7 @@ set_pte:
static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pt_access, unsigned pte_access,
int user_fault, int write_fault, int dirty,
- int *ptwrite, int largepage, gfn_t gfn,
+ int *ptwrite, int level, gfn_t gfn,
pfn_t pfn, bool speculative)
{
int was_rmapped = 0;
@@ -1802,7 +1807,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
* If we overwrite a PTE page pointer with a 2MB PMD, unlink
* the parent of the now unreachable PTE.
*/
- if (largepage && !is_large_pte(*sptep)) {
+ if (level > PT_PAGE_TABLE_LEVEL &&
+ !is_large_pte(*sptep)) {
struct kvm_mmu_page *child;
u64 pte = *sptep;
@@ -1815,8 +1821,9 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
} else
was_rmapped = 1;
}
+
if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
- dirty, largepage, gfn, pfn, speculative, true)) {
+ dirty, level, gfn, pfn, speculative, true)) {
if (write_fault)
*ptwrite = 1;
kvm_x86_ops->tlb_flush(vcpu);
@@ -1852,7 +1859,7 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
}
static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
- int largepage, gfn_t gfn, pfn_t pfn)
+ int level, gfn_t gfn, pfn_t pfn)
{
struct kvm_shadow_walk_iterator iterator;
struct kvm_mmu_page *sp;
@@ -1860,11 +1867,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
gfn_t pseudo_gfn;
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
- if (iterator.level == PT_PAGE_TABLE_LEVEL
- || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) {
+ if (iterator.level == level) {
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
0, write, 1, &pt_write,
- largepage, gfn, pfn, false);
+ level, gfn, pfn, false);
++vcpu->stat.pf_fixed;
break;
}
@@ -1892,14 +1898,20 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
{
int r;
- int largepage = 0;
+ int level;
pfn_t pfn;
unsigned long mmu_seq;
- if (mapping_level(vcpu, gfn) == PT_DIRECTORY_LEVEL) {
- gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
- largepage = 1;
- }
+ level = mapping_level(vcpu, gfn);
+
+ /*
+ * This path builds a PAE pagetable - so we can map 2mb pages at
+ * maximum. Therefore check if the level is larger than that.
+ */
+ if (level > PT_DIRECTORY_LEVEL)
+ level = PT_DIRECTORY_LEVEL;
+
+ gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
@@ -1915,7 +1927,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
if (mmu_notifier_retry(vcpu, mmu_seq))
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
- r = __direct_map(vcpu, v, write, largepage, gfn, pfn);
+ r = __direct_map(vcpu, v, write, level, gfn, pfn);
spin_unlock(&vcpu->kvm->mmu_lock);
@@ -2091,7 +2103,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
{
pfn_t pfn;
int r;
- int largepage = 0;
+ int level;
gfn_t gfn = gpa >> PAGE_SHIFT;
unsigned long mmu_seq;
@@ -2102,10 +2114,10 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
if (r)
return r;
- if (mapping_level(vcpu, gfn) == PT_DIRECTORY_LEVEL) {
- gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
- largepage = 1;
- }
+ level = mapping_level(vcpu, gfn);
+
+ gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
pfn = gfn_to_pfn(vcpu->kvm, gfn);
@@ -2118,7 +2130,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
- largepage, gfn, pfn);
+ level, gfn, pfn);
spin_unlock(&vcpu->kvm->mmu_lock);
return r;
@@ -2425,7 +2437,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
const void *new)
{
if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
- if (!vcpu->arch.update_pte.largepage ||
+ if (vcpu->arch.update_pte.level == PT_PAGE_TABLE_LEVEL ||
sp->role.glevels == PT32_ROOT_LEVEL) {
++vcpu->kvm->stat.mmu_pde_zapped;
return;
@@ -2475,7 +2487,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
u64 gpte = 0;
pfn_t pfn;
- vcpu->arch.update_pte.largepage = 0;
+ vcpu->arch.update_pte.level = PT_PAGE_TABLE_LEVEL;
if (bytes != 4 && bytes != 8)
return;
@@ -2507,7 +2519,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
if (is_large_pte(gpte) &&
(mapping_level(vcpu, gfn) == PT_DIRECTORY_LEVEL)) {
gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
- vcpu->arch.update_pte.largepage = 1;
+ vcpu->arch.update_pte.level = PT_DIRECTORY_LEVEL;
}
vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 44f0346..b167f0d 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -253,7 +253,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
pt_element_t gpte;
unsigned pte_access;
pfn_t pfn;
- int largepage = vcpu->arch.update_pte.largepage;
+ int level = vcpu->arch.update_pte.level;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
@@ -272,7 +272,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
return;
kvm_get_pfn(pfn);
mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
- gpte & PT_DIRTY_MASK, NULL, largepage,
+ gpte & PT_DIRTY_MASK, NULL, level,
gpte_to_gfn(gpte), pfn, true);
}
@@ -306,7 +306,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
gw->pte_access & access,
user_fault, write_fault,
gw->ptes[gw->level-1] & PT_DIRTY_MASK,
- ptwrite, largepage,
+ ptwrite, level,
gw->gfn, pfn, false);
break;
}
--
1.6.3.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists