Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1280186
| From | Xiao Guangrong <guangrong.xiao@linux.intel.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH 08/11] KVM: MMU: use page track for non-leaf shadow pages |
| Date | 2015-11-30 19:40 +0100 |
| Message-ID | <qABwL-7d9-35@gated-at.bofh.it> (permalink) |
| References | <qABwJ-7d9-5@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
non-leaf shadow pages are always write protected, it can be the user
of page track
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
---
arch/x86/include/asm/kvm_page_track.h | 8 +++++
arch/x86/kvm/mmu.c | 26 +++++++++++++---
arch/x86/kvm/page_track.c | 58 +++++++++++++++++++++++------------
3 files changed, 67 insertions(+), 25 deletions(-)
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 6744234..3447dac 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -41,8 +41,16 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
+void
+kvm_slot_page_track_add_page_nolock(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode);
void kvm_page_track_add_page(struct kvm *kvm, gfn_t gfn,
enum kvm_page_track_mode mode);
+void kvm_slot_page_track_remove_page_nolock(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn,
+ enum kvm_page_track_mode mode);
void kvm_page_track_remove_page(struct kvm *kvm, gfn_t gfn,
enum kvm_page_track_mode mode);
bool kvm_page_track_check_mode(struct kvm_vcpu *vcpu, gfn_t gfn,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b23f9fc..5a2ca73 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -806,11 +806,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
struct kvm_memory_slot *slot;
gfn_t gfn;
+ kvm->arch.indirect_shadow_pages++;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
+
+ /* the non-leaf shadow pages are keeping readonly. */
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_add_page_nolock(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
kvm_mmu_gfn_disallow_lpage(slot, gfn);
- kvm->arch.indirect_shadow_pages++;
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -819,11 +825,15 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
struct kvm_memory_slot *slot;
gfn_t gfn;
+ kvm->arch.indirect_shadow_pages--;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_remove_page_nolock(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
kvm_mmu_gfn_allow_lpage(slot, gfn);
- kvm->arch.indirect_shadow_pages--;
}
static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
@@ -2140,12 +2150,18 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
hlist_add_head(&sp->hash_link,
&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
if (!direct) {
- if (rmap_write_protect(vcpu, gfn))
+ /*
+ * we should do write protection before syncing pages
+ * otherwise the content of the synced shadow page may
+ * be inconsistent with guest page table.
+ */
+ account_shadowed(vcpu->kvm, sp);
+
+ if (level == PT_PAGE_TABLE_LEVEL &&
+ rmap_write_protect(vcpu, gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
if (level > PT_PAGE_TABLE_LEVEL && need_sync)
kvm_sync_pages(vcpu, gfn);
-
- account_shadowed(vcpu->kvm, sp);
}
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
init_shadow_page_table(sp);
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 84420df..87554d3 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -77,6 +77,26 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
WARN_ON(val < 0);
}
+void
+kvm_slot_page_track_add_page_nolock(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode)
+{
+ WARN_ON(!check_mode(mode));
+
+ update_gfn_track(slot, gfn, mode, 1);
+
+ /*
+ * new track stops large page mapping for the
+ * tracked page.
+ */
+ kvm_mmu_gfn_disallow_lpage(slot, gfn);
+
+ if (mode == KVM_PAGE_TRACK_WRITE)
+ if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn))
+ kvm_flush_remote_tlbs(kvm);
+}
+
/*
* add guest page to the tracking pool so that corresponding access on that
* page will be intercepted.
@@ -101,21 +121,27 @@ void kvm_page_track_add_page(struct kvm *kvm, gfn_t gfn,
slot = __gfn_to_memslot(slots, gfn);
spin_lock(&kvm->mmu_lock);
- update_gfn_track(slot, gfn, mode, 1);
-
- /*
- * new track stops large page mapping for the
- * tracked page.
- */
- kvm_mmu_gfn_disallow_lpage(slot, gfn);
-
- if (mode == KVM_PAGE_TRACK_WRITE)
- if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn))
- kvm_flush_remote_tlbs(kvm);
+ kvm_slot_page_track_add_page_nolock(kvm, slot, gfn, mode);
spin_unlock(&kvm->mmu_lock);
}
}
+void kvm_slot_page_track_remove_page_nolock(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn,
+ enum kvm_page_track_mode mode)
+{
+ WARN_ON(!check_mode(mode));
+
+ update_gfn_track(slot, gfn, mode, -1);
+
+ /*
+ * allow large page mapping for the tracked page
+ * after the tracker is gone.
+ */
+ kvm_mmu_gfn_allow_lpage(slot, gfn);
+}
+
/*
* remove the guest page from the tracking pool which stops the interception
* of corresponding access on that page. It is the opposed operation of
@@ -134,20 +160,12 @@ void kvm_page_track_remove_page(struct kvm *kvm, gfn_t gfn,
struct kvm_memory_slot *slot;
int i;
- WARN_ON(!check_mode(mode));
-
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
slots = __kvm_memslots(kvm, i);
slot = __gfn_to_memslot(slots, gfn);
spin_lock(&kvm->mmu_lock);
- update_gfn_track(slot, gfn, mode, -1);
-
- /*
- * allow large page mapping for the tracked page
- * after the tracker is gone.
- */
- kvm_mmu_gfn_allow_lpage(slot, gfn);
+ kvm_slot_page_track_remove_page_nolock(kvm, slot, gfn, mode);
spin_unlock(&kvm->mmu_lock);
}
}
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH 00/11] KVM: x86: track guest page access Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 05/11] KVM: page track: introduce kvm_page_track_{add,remove}_page Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 07/11] KVM: page track: add notifier support Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 02/11] KVM: MMU: introduce kvm_mmu_gfn_{allow,disallow}_lpage Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 08/11] KVM: MMU: use page track for non-leaf shadow pages Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 10/11] KVM: MMU: clear write-flooding on the fast path of tracked page Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 01/11] KVM: MMU: rename has_wrprotected_page to mmu_gfn_lpage_is_disallowed Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
[PATCH 11/11] KVM: MMU: apply page track notifier Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-11-30 19:40 +0100
Re: [PATCH 00/11] KVM: x86: track guest page access Paolo Bonzini <pbonzini@redhat.com> - 2015-12-01 11:20 +0100
Re: [PATCH 00/11] KVM: x86: track guest page access Paolo Bonzini <pbonzini@redhat.com> - 2015-12-01 16:10 +0100
Re: [PATCH 00/11] KVM: x86: track guest page access Andrea Arcangeli <aarcange@redhat.com> - 2015-12-01 16:10 +0100
Re: [PATCH 00/11] KVM: x86: track guest page access Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-12-01 18:10 +0100
Re: [PATCH 00/11] KVM: x86: track guest page access Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2015-12-05 18:10 +0100
csiph-web