From: Avi Kivity <avi@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 44/46] KVM: MMU: shadow support for 1gb pages
Date: Sun, 23 Aug 2009 14:56:43 +0300 [thread overview]
Message-ID: <1251028605-31977-45-git-send-email-avi@redhat.com> (raw)
In-Reply-To: <1251028605-31977-1-git-send-email-avi@redhat.com>
From: Joerg Roedel <joerg.roedel@amd.com>
This patch adds support for shadow paging to the 1gb page table code in KVM.
With this code the guest can use 1gb pages even if the host does not support
them.
[ Marcelo: fix shadow page collision on pmd level if a guest 1gb page is mapped
with 4kb ptes on host level ]
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 1 -
arch/x86/kvm/mmu.c | 14 +----------
arch/x86/kvm/paging_tmpl.h | 43 ++++++++++++++++++--------------------
3 files changed, 22 insertions(+), 36 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e09dc26..c9fb2bc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -315,7 +315,6 @@ struct kvm_vcpu_arch {
struct {
gfn_t gfn; /* presumed gfn during guest pte update */
pfn_t pfn; /* pfn corresponding to that gfn */
- int level;
unsigned long mmu_seq;
} update_pte;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 09ab643..1249c12 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2478,11 +2478,8 @@ 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.level == PT_PAGE_TABLE_LEVEL ||
- sp->role.glevels == PT32_ROOT_LEVEL) {
- ++vcpu->kvm->stat.mmu_pde_zapped;
- return;
- }
+ ++vcpu->kvm->stat.mmu_pde_zapped;
+ return;
}
++vcpu->kvm->stat.mmu_pte_updated;
@@ -2528,8 +2525,6 @@ 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.level = PT_PAGE_TABLE_LEVEL;
-
if (bytes != 4 && bytes != 8)
return;
@@ -2557,11 +2552,6 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
return;
gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
- 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.level = PT_DIRECTORY_LEVEL;
- }
vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
pfn = gfn_to_pfn(vcpu->kvm, gfn);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 578276e..d2fec9c 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -256,7 +256,6 @@ 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 level = vcpu->arch.update_pte.level;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
@@ -275,7 +274,7 @@ 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, level,
+ gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL,
gpte_to_gfn(gpte), pfn, true);
}
@@ -284,7 +283,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
*/
static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct guest_walker *gw,
- int user_fault, int write_fault, int largepage,
+ int user_fault, int write_fault, int hlevel,
int *ptwrite, pfn_t pfn)
{
unsigned access = gw->pt_access;
@@ -303,8 +302,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
for_each_shadow_entry(vcpu, addr, iterator) {
level = iterator.level;
sptep = iterator.sptep;
- if (level == PT_PAGE_TABLE_LEVEL
- || (largepage && level == PT_DIRECTORY_LEVEL)) {
+ if (iterator.level == hlevel) {
mmu_set_spte(vcpu, sptep, access,
gw->pte_access & access,
user_fault, write_fault,
@@ -323,12 +321,15 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
kvm_flush_remote_tlbs(vcpu->kvm);
}
- if (level == PT_DIRECTORY_LEVEL
- && gw->level == PT_DIRECTORY_LEVEL) {
+ if (level <= gw->level) {
+ int delta = level - gw->level + 1;
direct = 1;
- if (!is_dirty_gpte(gw->ptes[level - 1]))
+ if (!is_dirty_gpte(gw->ptes[level - delta]))
access &= ~ACC_WRITE_MASK;
- table_gfn = gpte_to_gfn(gw->ptes[level - 1]);
+ table_gfn = gpte_to_gfn(gw->ptes[level - delta]);
+ /* advance table_gfn when emulating 1gb pages with 4k */
+ if (delta == 0)
+ table_gfn += PT_INDEX(addr, level);
} else {
direct = 0;
table_gfn = gw->table_gfn[level - 2];
@@ -381,7 +382,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
int write_pt = 0;
int r;
pfn_t pfn;
- int largepage = 0;
+ int level = PT_PAGE_TABLE_LEVEL;
unsigned long mmu_seq;
pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
@@ -407,15 +408,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
return 0;
}
- if (walker.level == PT_DIRECTORY_LEVEL) {
- gfn_t large_gfn;
- large_gfn = walker.gfn &
- ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
- if (mapping_level(vcpu, large_gfn) == PT_DIRECTORY_LEVEL) {
- walker.gfn = large_gfn;
- largepage = 1;
- }
+ if (walker.level >= PT_DIRECTORY_LEVEL) {
+ level = min(walker.level, mapping_level(vcpu, walker.gfn));
+ walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
}
+
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
@@ -432,8 +429,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
- largepage, &write_pt, pfn);
-
+ level, &write_pt, pfn);
pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
sptep, *sptep, write_pt);
@@ -468,8 +464,9 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
sptep = iterator.sptep;
/* FIXME: properly handle invlpg on large guest pages */
- if (level == PT_PAGE_TABLE_LEVEL ||
- ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
+ if (level == PT_PAGE_TABLE_LEVEL ||
+ ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
+ ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
struct kvm_mmu_page *sp = page_header(__pa(sptep));
pte_gpa = (sp->gfn << PAGE_SHIFT);
@@ -599,7 +596,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
nr_present++;
pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
- is_dirty_gpte(gpte), 0, gfn,
+ is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
spte_to_pfn(sp->spt[i]), true, false);
}
--
1.6.4.1
next prev parent reply other threads:[~2009-08-23 11:58 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-23 11:55 [PATCH 00/46] KVM updates for 2.6.32 merge window (3/4) Avi Kivity
2009-08-23 11:56 ` [PATCH 01/46] KVM: Trace irq level and source id Avi Kivity
2009-08-23 11:56 ` [PATCH 02/46] KVM: Ignore PCI ECS I/O enablement Avi Kivity
2009-08-23 11:56 ` [PATCH 03/46] KVM: Trace mmio Avi Kivity
2009-08-23 11:56 ` [PATCH 04/46] KVM: Trace apic registers using their symbolic names Avi Kivity
2009-08-23 11:56 ` [PATCH 05/46] KVM: Add Directed EOI support to APIC emulation Avi Kivity
2009-08-23 11:56 ` [PATCH 06/46] KVM: x2apic interface to lapic Avi Kivity
2009-08-23 11:56 ` [PATCH 07/46] KVM: Use temporary variable to shorten lines Avi Kivity
2009-08-23 11:56 ` [PATCH 08/46] KVM: Fix apic_mmio_write return for unaligned write Avi Kivity
2009-08-23 11:56 ` [PATCH 09/46] KVM: handle AMD microcode MSR Avi Kivity
2009-08-23 11:56 ` [PATCH 10/46] Revert "KVM: x86: check for cr3 validity in ioctl_set_sregs" Avi Kivity
2009-08-23 11:56 ` [PATCH 11/46] KVM: MMU: Trace guest pagetable walker Avi Kivity
2009-08-23 11:56 ` [PATCH 12/46] KVM: Document basic API Avi Kivity
2009-08-23 11:56 ` [PATCH 13/46] KVM: Trace shadow page lifecycle Avi Kivity
2009-08-23 11:56 ` [PATCH 14/46] KVM: fix MMIO_CONF_BASE MSR access Avi Kivity
2009-08-23 11:56 ` [PATCH 15/46] KVM: ignore msi request if !level Avi Kivity
2009-08-23 11:56 ` [PATCH 16/46] KVM: Add trace points in irqchip code Avi Kivity
2009-08-23 11:56 ` [PATCH 17/46] KVM: No need to kick cpu if not in a guest mode Avi Kivity
2009-08-23 11:56 ` [PATCH 18/46] KVM: Always report x2apic as supported feature Avi Kivity
2009-08-23 11:56 ` [PATCH 19/46] KVM: PIT support for HPET legacy mode Avi Kivity
2009-08-23 11:56 ` [PATCH 20/46] KVM: add module parameters documentation Avi Kivity
2009-08-23 11:56 ` [PATCH 21/46] KVM: make io_bus interface more robust Avi Kivity
2009-08-23 11:56 ` [PATCH 22/46] KVM: add ioeventfd support Avi Kivity
2009-08-23 11:56 ` [PATCH 23/46] KVM: MMU: Fix MMU_DEBUG compile breakage Avi Kivity
2009-08-23 11:56 ` [PATCH 24/46] KVM: Move exception handling to the same place as other events Avi Kivity
2009-08-23 11:56 ` [PATCH 25/46] KVM: Move kvm_cpu_get_interrupt() declaration to x86 code Avi Kivity
2009-08-23 11:56 ` [PATCH 26/46] KVM: Reduce runnability interface with arch support code Avi Kivity
2009-08-23 11:56 ` [PATCH 27/46] KVM: silence lapic kernel messages that can be triggered by a guest Avi Kivity
2009-08-23 11:56 ` [PATCH 28/46] KVM: Discard unnecessary kvm_mmu_flush_tlb() in kvm_mmu_load() Avi Kivity
2009-08-23 11:56 ` [PATCH 29/46] KVM: MMU: fix missing locking in alloc_mmu_pages Avi Kivity
2009-08-23 11:56 ` [PATCH 30/46] KVM: s390: remove unused structs Avi Kivity
2009-08-23 11:56 ` [PATCH 31/46] KVM: x86: use get_desc_base() and get_desc_limit() Avi Kivity
2009-08-23 11:56 ` [PATCH 32/46] KVM: x86: use kvm_get_gdt() and kvm_read_ldt() Avi Kivity
2009-08-23 11:56 ` [PATCH 33/46] KVM: VMX: Introduce KVM_SET_IDENTITY_MAP_ADDR ioctl Avi Kivity
2009-08-23 11:56 ` [PATCH 34/46] KVM: PIT: Unregister ack notifier callback when freeing Avi Kivity
2009-08-23 11:56 ` [PATCH 35/46] KVM: Drop obsolete cpu_get/put in make_all_cpus_request Avi Kivity
2009-08-23 11:56 ` [PATCH 36/46] KVM: VMX: Avoid to return ENOTSUPP to userland Avi Kivity
2009-08-23 11:56 ` [PATCH 37/46] KVM: Align cr8 threshold when userspace changes cr8 Avi Kivity
2009-08-23 11:56 ` [PATCH 38/46] KVM: limit lapic periodic timer frequency Avi Kivity
2009-08-23 11:56 ` [PATCH 39/46] KVM: fix kvm_init() error handling Avi Kivity
2009-08-23 11:56 ` [PATCH 40/46] KVM: MMU: make rmap code aware of mapping levels Avi Kivity
2009-08-23 11:56 ` [PATCH 41/46] KVM: MMU: rename is_largepage_backed to mapping_level Avi Kivity
2009-08-23 11:56 ` [PATCH 42/46] KVM: MMU: make direct mapping paths aware of mapping levels Avi Kivity
2009-08-23 11:56 ` [PATCH 43/46] KVM: MMU: make page walker " Avi Kivity
2009-08-23 11:56 ` Avi Kivity [this message]
2009-08-23 11:56 ` [PATCH 45/46] KVM: MMU: enable gbpages by increasing nr of pagesizes Avi Kivity
2009-08-23 11:56 ` [PATCH 46/46] KVM: report 1GB page support to userspace Avi Kivity
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=1251028605-31977-45-git-send-email-avi@redhat.com \
--to=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/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