From: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
To: gleb@redhat.com
Cc: avi.kivity@gmail.com, mtosatti@redhat.com, pbonzini@redhat.com,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Subject: [PATCH v3 12/15] KVM: MMU: check last spte with unawareness of mapping level
Date: Wed, 23 Oct 2013 21:29:30 +0800 [thread overview]
Message-ID: <1382534973-13197-13-git-send-email-xiaoguangrong@linux.vnet.ibm.com> (raw)
In-Reply-To: <1382534973-13197-1-git-send-email-xiaoguangrong@linux.vnet.ibm.com>
The sptes on the middle level should obey these rules:
- they are always writable
- they are not pointing to process's page, so that SPTE_HOST_WRITEABLE has
no chance to be set
So we can check last spte by using PT_WRITABLE_MASK and SPTE_HOST_WRITEABLE
that can be got from spte, then we can let is_last_spte() do not depend on
the mapping level anymore
This is important to implement lockless write-protection since only spte is
available at that time
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
---
arch/x86/kvm/mmu.c | 25 ++++++++++++-------------
arch/x86/kvm/mmu_audit.c | 6 +++---
arch/x86/kvm/paging_tmpl.h | 6 ++----
3 files changed, 17 insertions(+), 20 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5b42858..8b96d96 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -337,13 +337,13 @@ static int is_rmap_spte(u64 pte)
return is_shadow_present_pte(pte);
}
-static int is_last_spte(u64 pte, int level)
+static int is_last_spte(u64 pte)
{
- if (level == PT_PAGE_TABLE_LEVEL)
- return 1;
- if (is_large_pte(pte))
- return 1;
- return 0;
+ /*
+ * All the sptes on the middle level are writable but
+ * SPTE_HOST_WRITEABLE is not set.
+ */
+ return !(is_writable_pte(pte) && !(pte & SPTE_HOST_WRITEABLE));
}
static pfn_t spte_to_pfn(u64 pte)
@@ -2203,7 +2203,7 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator,
u64 spte)
{
- if (is_last_spte(spte, iterator->level)) {
+ if (is_last_spte(spte)) {
iterator->level = 0;
return;
}
@@ -2255,15 +2255,14 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
}
}
-static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
- u64 *spte)
+static bool mmu_page_zap_pte(struct kvm *kvm, u64 *spte)
{
u64 pte;
struct kvm_mmu_page *child;
pte = *spte;
if (is_shadow_present_pte(pte)) {
- if (is_last_spte(pte, sp->role.level)) {
+ if (is_last_spte(pte)) {
drop_spte(kvm, spte);
if (is_large_pte(pte))
--kvm->stat.lpages;
@@ -2286,7 +2285,7 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm,
unsigned i;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
- mmu_page_zap_pte(kvm, sp, sp->spt + i);
+ mmu_page_zap_pte(kvm, sp->spt + i);
}
static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
@@ -3068,7 +3067,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
}
sp = page_header(__pa(iterator.sptep));
- if (!is_last_spte(spte, sp->role.level))
+ if (!is_last_spte(spte))
goto exit;
/*
@@ -4316,7 +4315,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
local_flush = true;
while (npte--) {
entry = *spte;
- mmu_page_zap_pte(vcpu->kvm, sp, spte);
+ mmu_page_zap_pte(vcpu->kvm, spte);
if (gentry &&
!((sp->role.word ^ vcpu->arch.mmu.base_role.word)
& mask.word) && rmap_can_add(vcpu))
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index daff69e..d54e2ad 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -45,7 +45,7 @@ static void __mmu_spte_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
fn(vcpu, ent + i, level);
if (is_shadow_present_pte(ent[i]) &&
- !is_last_spte(ent[i], level)) {
+ !is_last_spte(ent[i])) {
struct kvm_mmu_page *child;
child = page_header(ent[i] & PT64_BASE_ADDR_MASK);
@@ -110,7 +110,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
}
}
- if (!is_shadow_present_pte(*sptep) || !is_last_spte(*sptep, level))
+ if (!is_shadow_present_pte(*sptep) || !is_last_spte(*sptep))
return;
gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
@@ -158,7 +158,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
static void audit_sptes_have_rmaps(struct kvm_vcpu *vcpu, u64 *sptep, int level)
{
- if (is_shadow_present_pte(*sptep) && is_last_spte(*sptep, level))
+ if (is_shadow_present_pte(*sptep) && is_last_spte(*sptep))
inspect_spte_has_rmap(vcpu->kvm, sptep);
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index ad75d77..33f0216 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -809,7 +809,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
{
struct kvm_shadow_walk_iterator iterator;
struct kvm_mmu_page *sp;
- int level;
u64 *sptep;
vcpu_clear_mmio_info(vcpu, gva);
@@ -822,11 +821,10 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
spin_lock(&vcpu->kvm->mmu_lock);
for_each_shadow_entry(vcpu, gva, iterator) {
- level = iterator.level;
sptep = iterator.sptep;
sp = page_header(__pa(sptep));
- if (is_last_spte(*sptep, level)) {
+ if (is_last_spte(*sptep)) {
pt_element_t gpte;
gpa_t pte_gpa;
@@ -836,7 +834,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
pte_gpa = FNAME(get_level1_sp_gpa)(sp);
pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
- if (mmu_page_zap_pte(vcpu->kvm, sp, sptep))
+ if (mmu_page_zap_pte(vcpu->kvm, sptep))
kvm_flush_remote_tlbs(vcpu->kvm);
if (!rmap_can_add(vcpu))
--
1.8.1.4
next prev parent reply other threads:[~2013-10-23 13:32 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-10-23 13:29 [PATCH v3 00/15] KVM: MMU: locklessly write-protect Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 01/15] KVM: MMU: properly check last spte in fast_page_fault() Xiao Guangrong
2013-11-12 0:25 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 02/15] KVM: MMU: lazily drop large spte Xiao Guangrong
2013-11-12 22:44 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 03/15] KVM: MMU: flush tlb if the spte can be locklessly modified Xiao Guangrong
2013-11-13 0:10 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 04/15] KVM: MMU: flush tlb out of mmu lock when write-protect the sptes Xiao Guangrong
2013-11-14 0:36 ` Marcelo Tosatti
2013-11-14 5:15 ` Xiao Guangrong
2013-11-14 18:39 ` Marcelo Tosatti
2013-11-15 7:09 ` Xiao Guangrong
2013-11-19 0:19 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 05/15] KVM: MMU: update spte and add it into rmap before dirty log Xiao Guangrong
2013-11-15 0:08 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 06/15] KVM: MMU: redesign the algorithm of pte_list Xiao Guangrong
2013-11-19 0:48 ` Marcelo Tosatti
2013-10-23 13:29 ` [PATCH v3 07/15] KVM: MMU: introduce nulls desc Xiao Guangrong
2013-11-22 19:14 ` Marcelo Tosatti
2013-11-25 6:11 ` Xiao Guangrong
2013-11-25 6:29 ` Xiao Guangrong
2013-11-25 18:12 ` Marcelo Tosatti
2013-11-26 3:21 ` Xiao Guangrong
2013-11-26 10:12 ` Gleb Natapov
2013-11-26 19:31 ` Marcelo Tosatti
2013-11-28 8:53 ` Xiao Guangrong
2013-12-03 7:10 ` Xiao Guangrong
2013-12-05 13:50 ` Marcelo Tosatti
2013-12-05 15:30 ` Xiao Guangrong
2013-12-06 0:15 ` Marcelo Tosatti
2013-12-06 0:22 ` Marcelo Tosatti
2013-12-10 6:58 ` Xiao Guangrong
2013-11-25 10:19 ` Gleb Natapov
2013-11-25 10:25 ` Xiao Guangrong
2013-11-25 12:48 ` Avi Kivity
2013-11-25 14:23 ` Marcelo Tosatti
2013-11-25 14:29 ` Gleb Natapov
2013-11-25 18:06 ` Marcelo Tosatti
2013-11-26 3:10 ` Xiao Guangrong
2013-11-26 10:15 ` Gleb Natapov
2013-11-26 19:58 ` Marcelo Tosatti
2013-11-28 8:32 ` Xiao Guangrong
2013-11-25 14:08 ` Marcelo Tosatti
2013-11-26 3:02 ` Xiao Guangrong
2013-11-25 9:31 ` Peter Zijlstra
2013-11-25 10:59 ` Xiao Guangrong
2013-11-25 11:05 ` Peter Zijlstra
2013-11-25 11:29 ` Peter Zijlstra
2013-10-23 13:29 ` [PATCH v3 08/15] KVM: MMU: introduce pte-list lockless walker Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 09/15] KVM: MMU: initialize the pointers in pte_list_desc properly Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 10/15] KVM: MMU: allocate shadow pages from slab Xiao Guangrong
2013-10-24 9:19 ` Gleb Natapov
2013-10-24 9:29 ` Xiao Guangrong
2013-10-24 9:52 ` Gleb Natapov
2013-10-24 10:10 ` Xiao Guangrong
2013-10-24 10:39 ` Gleb Natapov
2013-10-24 11:01 ` Xiao Guangrong
2013-10-24 12:32 ` Gleb Natapov
2013-10-28 3:16 ` Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 11/15] KVM: MMU: locklessly access shadow page under rcu protection Xiao Guangrong
2013-10-23 13:29 ` Xiao Guangrong [this message]
2013-10-23 13:29 ` [PATCH v3 13/15] KVM: MMU: locklessly write-protect the page Xiao Guangrong
2013-10-24 9:17 ` Gleb Natapov
2013-10-24 9:24 ` Xiao Guangrong
2013-10-24 9:32 ` Gleb Natapov
2013-10-23 13:29 ` [PATCH v3 14/15] KVM: MMU: clean up spte_write_protect Xiao Guangrong
2013-10-23 13:29 ` [PATCH v3 15/15] KVM: MMU: use rcu functions to access the pointer Xiao Guangrong
2013-11-03 12:29 ` [PATCH v3 00/15] KVM: MMU: locklessly write-protect Gleb Natapov
2013-11-11 5:33 ` Xiao Guangrong
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=1382534973-13197-13-git-send-email-xiaoguangrong@linux.vnet.ibm.com \
--to=xiaoguangrong@linux.vnet.ibm.com \
--cc=avi.kivity@gmail.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@redhat.com \
/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;
as well as URLs for NNTP newsgroup(s).