| 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: <20220310140911.50924-10-chao.p.peng@linux.intel.com>
Date: Thu, 10 Mar 2022 22:09:07 +0800
From: Chao Peng <chao.p.peng@...ux.intel.com>
To: kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, linux-fsdevel@...r.kernel.org,
linux-api@...r.kernel.org, qemu-devel@...gnu.org
Cc: Paolo Bonzini <pbonzini@...hat.com>,
Jonathan Corbet <corbet@....net>,
Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
Hugh Dickins <hughd@...gle.com>,
Jeff Layton <jlayton@...nel.org>,
"J . Bruce Fields" <bfields@...ldses.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Mike Rapoport <rppt@...nel.org>,
Steven Price <steven.price@....com>,
"Maciej S . Szmigiero" <mail@...iej.szmigiero.name>,
Vlastimil Babka <vbabka@...e.cz>,
Vishal Annapurve <vannapurve@...gle.com>,
Yu Zhang <yu.c.zhang@...ux.intel.com>,
Chao Peng <chao.p.peng@...ux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
luto@...nel.org, jun.nakajima@...el.com, dave.hansen@...el.com,
ak@...ux.intel.com, david@...hat.com
Subject: [PATCH v5 09/13] KVM: Handle page fault for private memory
When page fault happens for a memslot with KVM_MEM_PRIVATE, we use
kvm_memfile_get_pfn() which further calls into memfile_pfn_ops callbacks
defined for each memslot to request the pfn from the memory backing store.
One assumption is that private pages are persistent and pre-allocated in
the private memory fd (backing store) so KVM uses this information as an
indicator for a page is private or shared (i.e. the private fd is the
final source of truth as to whether or not a GPA is private).
Depending on the access is private or shared, we go different paths:
- For private access, KVM checks if the page is already allocated in
the memory backing store, if yes KVM establishes the mapping,
otherwise exits to userspace to convert a shared page to private one.
- For shared access, KVM also checks if the page is already allocated
in the memory backing store, if yes then exit to userspace to
convert a private page to shared one, otherwise it's treated as a
traditional hva-based shared memory, KVM lets existing code to obtain
a pfn with get_user_pages() and establish the mapping.
Signed-off-by: Yu Zhang <yu.c.zhang@...ux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@...ux.intel.com>
---
arch/x86/kvm/mmu/mmu.c | 73 ++++++++++++++++++++++++++++++++--
arch/x86/kvm/mmu/paging_tmpl.h | 11 +++--
2 files changed, 77 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3b8da8b0745e..f04c823ea09a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2844,6 +2844,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
if (max_level == PG_LEVEL_4K)
return PG_LEVEL_4K;
+ if (kvm_slot_is_private(slot))
+ return max_level;
+
host_level = host_pfn_mapping_level(kvm, gfn, pfn, slot);
return min(host_level, max_level);
}
@@ -3890,7 +3893,59 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
-static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, int *r)
+static bool kvm_vcpu_is_private_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ /*
+ * At this time private gfn has not been supported yet. Other patch
+ * that enables it should change this.
+ */
+ return false;
+}
+
+static bool kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault,
+ bool *is_private_pfn, int *r)
+{
+ int order;
+ unsigned int flags = 0;
+ struct kvm_memory_slot *slot = fault->slot;
+ long pfn = kvm_memfile_get_pfn(slot, fault->gfn, &order);
+
+ if (kvm_vcpu_is_private_gfn(vcpu, fault->addr >> PAGE_SHIFT)) {
+ if (pfn < 0)
+ flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
+ else {
+ fault->pfn = pfn;
+ if (slot->flags & KVM_MEM_READONLY)
+ fault->map_writable = false;
+ else
+ fault->map_writable = true;
+
+ if (order == 0)
+ fault->max_level = PG_LEVEL_4K;
+ *is_private_pfn = true;
+ *r = RET_PF_FIXED;
+ return true;
+ }
+ } else {
+ if (pfn < 0)
+ return false;
+
+ kvm_memfile_put_pfn(slot, pfn);
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_ERROR;
+ vcpu->run->memory.flags = flags;
+ vcpu->run->memory.padding = 0;
+ vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
+ vcpu->run->memory.size = PAGE_SIZE;
+ fault->pfn = -1;
+ *r = -1;
+ return true;
+}
+
+static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+ bool *is_private_pfn, int *r)
{
struct kvm_memory_slot *slot = fault->slot;
bool async;
@@ -3924,6 +3979,10 @@ static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
}
}
+ if (kvm_slot_is_private(slot) &&
+ kvm_faultin_pfn_private(vcpu, fault, is_private_pfn, r))
+ return *r == RET_PF_FIXED ? false : true;
+
async = false;
fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
fault->write, &fault->map_writable,
@@ -3984,6 +4043,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
unsigned long mmu_seq;
+ bool is_private_pfn = false;
int r;
fault->gfn = fault->addr >> PAGE_SHIFT;
@@ -4003,7 +4063,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
- if (kvm_faultin_pfn(vcpu, fault, &r))
+ if (kvm_faultin_pfn(vcpu, fault, &is_private_pfn, &r))
return r;
if (handle_abnormal_pfn(vcpu, fault, ACC_ALL, &r))
@@ -4016,7 +4076,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
else
write_lock(&vcpu->kvm->mmu_lock);
- if (is_page_fault_stale(vcpu, fault, mmu_seq))
+ if (!is_private_pfn && is_page_fault_stale(vcpu, fault, mmu_seq))
goto out_unlock;
r = make_mmu_pages_available(vcpu);
@@ -4033,7 +4093,12 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
read_unlock(&vcpu->kvm->mmu_lock);
else
write_unlock(&vcpu->kvm->mmu_lock);
- kvm_release_pfn_clean(fault->pfn);
+
+ if (is_private_pfn)
+ kvm_memfile_put_pfn(fault->slot, fault->pfn);
+ else
+ kvm_release_pfn_clean(fault->pfn);
+
return r;
}
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 252c77805eb9..6a5736699c0a 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -825,6 +825,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
int r;
unsigned long mmu_seq;
bool is_self_change_mapping;
+ bool is_private_pfn = false;
+
pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code);
WARN_ON_ONCE(fault->is_tdp);
@@ -873,7 +875,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
- if (kvm_faultin_pfn(vcpu, fault, &r))
+ if (kvm_faultin_pfn(vcpu, fault, &is_private_pfn, &r))
return r;
if (handle_abnormal_pfn(vcpu, fault, walker.pte_access, &r))
@@ -901,7 +903,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
r = RET_PF_RETRY;
write_lock(&vcpu->kvm->mmu_lock);
- if (is_page_fault_stale(vcpu, fault, mmu_seq))
+ if (!is_private_pfn && is_page_fault_stale(vcpu, fault, mmu_seq))
goto out_unlock;
r = make_mmu_pages_available(vcpu);
@@ -911,7 +913,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
out_unlock:
write_unlock(&vcpu->kvm->mmu_lock);
- kvm_release_pfn_clean(fault->pfn);
+ if (is_private_pfn)
+ kvm_memfile_put_pfn(fault->slot, fault->pfn);
+ else
+ kvm_release_pfn_clean(fault->pfn);
return r;
}
--
2.17.1
Powered by blists - more mailing lists