| 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: <4E4A1257.5080204@cn.fujitsu.com>
Date: Tue, 16 Aug 2011 14:46:47 +0800
From: Xiao Guangrong <xiaoguangrong@...fujitsu.com>
To: Avi Kivity <avi@...hat.com>
CC: Marcelo Tosatti <mtosatti@...hat.com>,
LKML <linux-kernel@...r.kernel.org>, KVM <kvm@...r.kernel.org>
Subject: [PATCH 11/11] KVM: MMU: improve write flooding detected
Detecting write-flooding does not work well, when we handle page written, if
the last speculative spte is not accessed, we treat the page is
write-flooding, however, we can speculative spte on many path, such as pte
prefetch, page synced, that means the last speculative spte may be not point
to the written page and the written page can be accessed via other sptes, so
depends on the Accessed bit of the last speculative spte is not enough
Instead of detected page accessed, we can detect whether the spte is accessed
or not, if the spte is not accessed but it is written frequently, we treat is
not a page table or it not used for a long time
Signed-off-by: Xiao Guangrong <xiaoguangrong@...fujitsu.com>
---
arch/x86/include/asm/kvm_host.h | 6 +---
arch/x86/kvm/mmu.c | 48 +++++++++------------------------------
arch/x86/kvm/paging_tmpl.h | 9 +-----
3 files changed, 15 insertions(+), 48 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 927ba73..9d17238 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -239,6 +239,8 @@ struct kvm_mmu_page {
int clear_spte_count;
#endif
+ int write_flooding_count;
+
struct rcu_head rcu;
};
@@ -353,10 +355,6 @@ struct kvm_vcpu_arch {
struct kvm_mmu_memory_cache mmu_page_cache;
struct kvm_mmu_memory_cache mmu_page_header_cache;
- gfn_t last_pt_write_gfn;
- int last_pt_write_count;
- u64 *last_pte_updated;
-
struct fpu guest_fpu;
u64 xcr0;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index adaa160..3230f84 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1695,6 +1695,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
} else if (sp->unsync)
kvm_mmu_mark_parents_unsync(sp);
+ sp->write_flooding_count = 0;
trace_kvm_mmu_get_page(sp, false);
return sp;
}
@@ -1847,15 +1848,6 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
mmu_page_remove_parent_pte(sp, parent_pte);
}
-static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm)
-{
- int i;
- struct kvm_vcpu *vcpu;
-
- kvm_for_each_vcpu(i, vcpu, kvm)
- vcpu->arch.last_pte_updated = NULL;
-}
-
static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
u64 *parent_pte;
@@ -1915,7 +1907,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
}
sp->role.invalid = 1;
- kvm_mmu_reset_last_pte_updated(kvm);
return ret;
}
@@ -2360,8 +2351,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
}
}
kvm_release_pfn_clean(pfn);
- if (speculative)
- vcpu->arch.last_pte_updated = sptep;
}
static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
@@ -3522,13 +3511,6 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
kvm_mmu_flush_tlb(vcpu);
}
-static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
-{
- u64 *spte = vcpu->arch.last_pte_updated;
-
- return !!(spte && (*spte & shadow_accessed_mask));
-}
-
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
const u8 *new, int *bytes)
{
@@ -3569,22 +3551,14 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
* If we're seeing too many writes to a page, it may no longer be a page table,
* or we may be forking, in which case it is better to unmap the page.
*/
-static bool detect_write_flooding(struct kvm_vcpu *vcpu, gfn_t gfn)
+static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte)
{
- bool flooded = false;
-
- if (gfn == vcpu->arch.last_pt_write_gfn
- && !last_updated_pte_accessed(vcpu)) {
- ++vcpu->arch.last_pt_write_count;
- if (vcpu->arch.last_pt_write_count >= 3)
- flooded = true;
- } else {
- vcpu->arch.last_pt_write_gfn = gfn;
- vcpu->arch.last_pt_write_count = 1;
- vcpu->arch.last_pte_updated = NULL;
- }
+ if (spte && !(*spte & shadow_accessed_mask))
+ sp->write_flooding_count++;
+ else
+ sp->write_flooding_count = 0;
- return flooded;
+ return sp->write_flooding_count >= 3;
}
/*
@@ -3656,7 +3630,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
- bool remote_flush, local_flush, zap_page, flooded, misaligned;
+ bool remote_flush, local_flush, zap_page;
/*
* If we don't have indirect shadow pages, it means no page is
@@ -3675,12 +3649,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
++vcpu->kvm->stat.mmu_pte_write;
trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
- flooded = detect_write_flooding(vcpu, gfn);
mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) {
- misaligned = detect_write_misaligned(sp, gpa, bytes);
+ spte = get_written_sptes(sp, gpa, &npte);
- if (misaligned || flooded) {
+ if (detect_write_misaligned(sp, gpa, bytes) ||
+ detect_write_flooding(sp, spte)) {
zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
&invalid_list);
++vcpu->kvm->stat.mmu_flooded;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index bdc2241..ec5c1b4 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -599,11 +599,9 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
*/
if (!r) {
pgprintk("%s: guest page fault\n", __func__);
- if (!prefault) {
+ if (!prefault)
inject_page_fault(vcpu, &walker.fault);
- /* reset fork detector */
- vcpu->arch.last_pt_write_count = 0;
- }
+
return 0;
}
@@ -641,9 +639,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__,
sptep, *sptep, emulate);
- if (!emulate)
- vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
-
++vcpu->stat.pf_fixed;
trace_kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
spin_unlock(&vcpu->kvm->mmu_lock);
--
1.7.5.4
--
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