From: Avi Kivity <avi@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 42/46] KVM: MMU: make direct mapping paths aware of mapping levels
Date: Sun, 23 Aug 2009 14:56:41 +0300 [thread overview]
Message-ID: <1251028605-31977-43-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>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/mmu.c | 83 +++++++++++++++++++++++----------------
arch/x86/kvm/paging_tmpl.h | 6 +-
3 files changed, 53 insertions(+), 38 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 c707936..110c224 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;
}
@@ -753,7 +753,7 @@ 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;
/*
@@ -772,11 +772,15 @@ 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);
+ }
}
}
@@ -814,12 +818,15 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
#define RMAP_RECYCLE_THRESHOLD 1000
-static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage)
+static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
unsigned long *rmapp;
+ struct kvm_mmu_page *sp;
+
+ sp = page_header(__pa(spte));
gfn = unalias_gfn(vcpu->kvm, gfn);
- rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
kvm_unmap_rmapp(vcpu->kvm, rmapp);
kvm_flush_remote_tlbs(vcpu->kvm);
@@ -1734,7 +1741,7 @@ 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)
{
@@ -1757,7 +1764,7 @@ 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,
@@ -1768,7 +1775,8 @@ 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;
@@ -1806,7 +1814,7 @@ 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;
@@ -1823,7 +1831,8 @@ 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;
@@ -1836,8 +1845,9 @@ 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);
@@ -1857,7 +1867,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
if (!is_rmap_spte(*sptep))
kvm_release_pfn_clean(pfn);
if (rmap_count > RMAP_RECYCLE_THRESHOLD)
- rmap_recycle(vcpu, gfn, largepage);
+ rmap_recycle(vcpu, sptep, gfn);
} else {
if (was_writeble)
kvm_release_pfn_dirty(pfn);
@@ -1875,7 +1885,7 @@ 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;
@@ -1883,11 +1893,10 @@ 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;
}
@@ -1915,14 +1924,20 @@ 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();
@@ -1938,7 +1953,7 @@ 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);
@@ -2114,7 +2129,7 @@ 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;
@@ -2125,10 +2140,10 @@ 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);
@@ -2141,7 +2156,7 @@ 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;
@@ -2448,7 +2463,7 @@ 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;
@@ -2498,7 +2513,7 @@ 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;
@@ -2530,7 +2545,7 @@ 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;
}
--
1.6.4.1
next prev parent reply other threads:[~2009-08-23 11:57 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 ` Avi Kivity [this message]
2009-08-23 11:56 ` [PATCH 43/46] KVM: MMU: make page walker aware of mapping levels Avi Kivity
2009-08-23 11:56 ` [PATCH 44/46] KVM: MMU: shadow support for 1gb pages Avi Kivity
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=1251028605-31977-43-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