| 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
| ||
|
Date: Wed, 8 Jan 2020 12:24:46 -0800
From: Sean Christopherson <sean.j.christopherson@...el.com>
To: Paolo Bonzini <pbonzini@...hat.com>
Cc: Paul Mackerras <paulus@...abs.org>,
Sean Christopherson <sean.j.christopherson@...el.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Andy Lutomirski <luto@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Marc Zyngier <maz@...nel.org>,
James Morse <james.morse@....com>,
Julien Thierry <julien.thierry.kdev@...il.com>,
Suzuki K Poulose <suzuki.poulose@....com>,
kvm-ppc@...r.kernel.org, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
linux-arm-kernel@...ts.infradead.org, kvmarm@...ts.cs.columbia.edu,
syzbot+c9d1fb51ac9d0d10c39d@...kaller.appspotmail.com,
Andrea Arcangeli <aarcange@...hat.com>,
Dan Williams <dan.j.williams@...el.com>,
Barret Rhoden <brho@...gle.com>,
David Hildenbrand <david@...hat.com>,
Jason Zeng <jason.zeng@...el.com>,
Dave Jiang <dave.jiang@...el.com>,
Liran Alon <liran.alon@...cle.com>,
linux-nvdimm <linux-nvdimm@...ts.01.org>
Subject: [PATCH 12/14] KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust()
Fold max_mapping_level() into kvm_mmu_hugepage_adjust() now that HugeTLB
mappings are handled in kvm_mmu_hugepage_adjust(), i.e. there isn't a
need to pre-calculate the max mapping level. Co-locating all hugepage
checks eliminates a memslot lookup, at the cost of performing the
__mmu_gfn_lpage_is_disallowed() checks while holding mmu_lock.
The latency of lpage_is_disallowed() is likely negligible relative to
the rest of the code run while holding mmu_lock, and can be offset to
some extent by eliminating the mmu_gfn_lpage_is_disallowed() check in
set_spte() in a future patch. Eliminating the check in set_spte() is
made possible by performing the initial lpage_is_disallowed() checks
while holding mmu_lock.
Signed-off-by: Sean Christopherson <sean.j.christopherson@...el.com>
---
arch/x86/kvm/mmu/mmu.c | 60 ++++++++++++++--------------------
arch/x86/kvm/mmu/paging_tmpl.h | 2 --
2 files changed, 24 insertions(+), 38 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f93b0c5e4170..f2667fe0dc75 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1310,27 +1310,6 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
return slot;
}
-static int max_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
- int max_level)
-{
- struct kvm_memory_slot *slot;
-
- if (unlikely(max_level == PT_PAGE_TABLE_LEVEL))
- return PT_PAGE_TABLE_LEVEL;
-
- slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- if (!memslot_valid_for_gpte(slot, true))
- return PT_PAGE_TABLE_LEVEL;
-
- max_level = min(max_level, kvm_x86_ops->get_lpage_level());
- for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) {
- if (!__mmu_gfn_lpage_is_disallowed(gfn, max_level, slot))
- break;
- }
-
- return max_level;
-}
-
/*
* About rmap_head encoding:
*
@@ -3101,10 +3080,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
if (pte_access & ACC_WRITE_MASK) {
/*
- * Other vcpu creates new sp in the window between
- * max_mapping_level() and acquiring mmu-lock. We can
- * allow guest to retry the access, the mapping can
- * be fixed if guest refault.
+ * Legacy code to handle an obsolete scenario where a different
+ * vcpu creates new sp in the window between this vcpu's query
+ * of lpage_is_disallowed() and acquiring mmu_lock. No longer
+ * necessary now that lpage_is_disallowed() is called after
+ * acquiring mmu_lock.
*/
if (level > PT_PAGE_TABLE_LEVEL &&
mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
@@ -3295,9 +3275,8 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
}
static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
- kvm_pfn_t pfn)
+ kvm_pfn_t pfn, struct kvm_memory_slot *slot)
{
- struct kvm_memory_slot *slot;
unsigned long hva;
pte_t *pte;
int level;
@@ -3310,16 +3289,13 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
return PT_PAGE_TABLE_LEVEL;
/*
- * Manually do the equivalent of kvm_vcpu_gfn_to_hva() to avoid the
+ * Note, using the already-retrieved memslot and __gfn_to_hva_memslot()
+ * is not solely for performance, it's also necessary to avoid the
* "writable" check in __gfn_to_hva_many(), which will always fail on
* read-only memslots due to gfn_to_hva() assuming writes. Earlier
* page fault steps have already verified the guest isn't writing a
* read-only memslot.
*/
- slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- if (!memslot_valid_for_gpte(slot, true))
- return PT_PAGE_TABLE_LEVEL;
-
hva = __gfn_to_hva_memslot(slot, gfn);
pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level);
@@ -3332,18 +3308,32 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
int max_level, kvm_pfn_t *pfnp)
{
+ struct kvm_memory_slot *slot;
kvm_pfn_t pfn = *pfnp;
kvm_pfn_t mask;
int level;
- if (max_level == PT_PAGE_TABLE_LEVEL)
+ if (unlikely(max_level == PT_PAGE_TABLE_LEVEL))
return PT_PAGE_TABLE_LEVEL;
if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn) ||
kvm_is_zone_device_pfn(pfn))
return PT_PAGE_TABLE_LEVEL;
- level = host_pfn_mapping_level(vcpu, gfn, pfn);
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ if (!memslot_valid_for_gpte(slot, true))
+ return PT_PAGE_TABLE_LEVEL;
+
+ max_level = min(max_level, kvm_x86_ops->get_lpage_level());
+ for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) {
+ if (!__mmu_gfn_lpage_is_disallowed(gfn, max_level, slot))
+ break;
+ }
+
+ if (max_level == PT_PAGE_TABLE_LEVEL)
+ return PT_PAGE_TABLE_LEVEL;
+
+ level = host_pfn_mapping_level(vcpu, gfn, pfn, slot);
if (level == PT_PAGE_TABLE_LEVEL)
return level;
@@ -4182,8 +4172,6 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
if (lpage_disallowed)
max_level = PT_PAGE_TABLE_LEVEL;
- max_level = max_mapping_level(vcpu, gfn, max_level);
-
if (fast_page_fault(vcpu, gpa, error_code))
return RET_PF_RETRY;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 0560982eda8b..ea174d85700a 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -817,8 +817,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
else
max_level = walker.level;
- max_level = max_mapping_level(vcpu, walker.gfn, max_level);
-
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
--
2.24.1
Powered by blists - more mailing lists