| 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: Tue, 16 Jun 2020 17:48:45 -0400
From: Vivek Goyal <vgoyal@...hat.com>
To: kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Cc: virtio-fs@...hat.com, miklos@...redi.hu, stefanha@...hat.com,
dgilbert@...hat.com, vgoyal@...hat.com, vkuznets@...hat.com,
pbonzini@...hat.com, wanpengli@...cent.com,
sean.j.christopherson@...el.com
Subject: [PATCH 1/3] kvm,x86: Force sync fault if previous attempts failed
Page fault error handling behavior in kvm seems little inconsistent when
page fault reports error. If we are doing fault synchronously
then we capture error (-EFAULT) returned by __gfn_to_pfn_memslot() and
exit to user space and qemu reports error, "error: kvm run failed Bad address".
But if we are doing async page fault, then async_pf_execute() will simply
ignore the error reported by get_user_pages_remote(). It is assumed that
page fault was successful and either a page ready event is injected in
guest or guest is brought out of artificial halt state and run again.
In both the cases when guest retries the instruction, it takes exit
again as page fault was not successful in previous attempt. And then
this infinite loop continues forever.
This patch tries to make this behavior consistent. That is instead of
getting into infinite loop of retrying page fault, exit to user space
and stop VM if page fault error happens. This can be improved by
injecting errors in guest when it is allowed. Later patches can
inject error when a process in guest triggered page fault and
in that case guest process will receive SIGBUS. Currently we don't
have a way to inject errors when guest is in kernel mode. Once we
have race free method to do so, we should be able to inject errors
and guest can do fixup_exception() if caller set it up so (virtio-fs).
When async pf encounters error then save that pfn and when next time
guest retries, do a sync fault instead of async fault. So that if error
is encountered, we exit to qemu and avoid infinite loop.
As of now only one error pfn is stored and that means it could be
overwritten before next a retry from guest happens. But this is
just a hint and if we miss it, some other time we will catch it.
If this becomes an issue, we could maintain an array of error
gfn later to help ease the issue.
Signed-off-by: Vivek Goyal <vgoyal@...hat.com>
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/mmu.h | 2 +-
arch/x86/kvm/mmu/mmu.c | 2 +-
arch/x86/kvm/x86.c | 19 +++++++++++++++++--
include/linux/kvm_host.h | 1 +
virt/kvm/async_pf.c | 8 ++++++--
6 files changed, 27 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 938497a6ebd7..348a73106556 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -778,6 +778,7 @@ struct kvm_vcpu_arch {
unsigned long nested_apf_token;
bool delivery_as_pf_vmexit;
bool pageready_pending;
+ gfn_t error_gfn;
} apf;
/* OSVW MSRs (AMD only) */
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 0ad06bfe2c2c..6fa085ff07a3 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -60,7 +60,7 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty, gpa_t new_eptp);
-bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address, char *insn, int insn_len);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 15984dfde427..e207900ab303 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4078,7 +4078,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
if (!async)
return false; /* *pfn has correct page already */
- if (!prefault && kvm_can_do_async_pf(vcpu)) {
+ if (!prefault && kvm_can_do_async_pf(vcpu, cr2_or_gpa >> PAGE_SHIFT)) {
trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
if (kvm_find_async_pf_gfn(vcpu, gfn)) {
trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 697d1b273a2f..4c5205434b9c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10513,7 +10513,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
return true;
}
-bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu, gfn_t gfn)
{
if (unlikely(!lapic_in_kernel(vcpu) ||
kvm_event_needs_reinjection(vcpu) ||
@@ -10527,7 +10527,13 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
* If interrupts are off we cannot even use an artificial
* halt state.
*/
- return kvm_arch_interrupt_allowed(vcpu);
+ if (!kvm_arch_interrupt_allowed(vcpu))
+ return false;
+
+ if (vcpu->arch.apf.error_gfn == gfn)
+ return false;
+
+ return true;
}
bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
@@ -10583,6 +10589,15 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
kvm_apic_set_irq(vcpu, &irq, NULL);
}
+ if (work->error_code) {
+ /*
+ * Page fault failed and we don't have a way to report
+ * errors back to guest yet. So save this pfn and force
+ * sync page fault next time.
+ */
+ vcpu->arch.apf.error_gfn = work->cr2_or_gpa >> PAGE_SHIFT;
+ }
+
vcpu->arch.apf.halted = false;
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 216cdb6581e2..b8558334b184 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -207,6 +207,7 @@ struct kvm_async_pf {
struct kvm_arch_async_pf arch;
bool wakeup_all;
bool notpresent_injected;
+ int error_code;
};
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index a36828fbf40a..6b30374a4de1 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -52,6 +52,7 @@ static void async_pf_execute(struct work_struct *work)
gpa_t cr2_or_gpa = apf->cr2_or_gpa;
int locked = 1;
bool first;
+ long ret;
might_sleep();
@@ -61,11 +62,14 @@ static void async_pf_execute(struct work_struct *work)
* access remotely.
*/
down_read(&mm->mmap_sem);
- get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL,
- &locked);
+ ret = get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL,
+ &locked);
if (locked)
up_read(&mm->mmap_sem);
+ if (ret < 0)
+ apf->error_code = ret;
+
if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
kvm_arch_async_page_present(vcpu, apf);
--
2.25.4
Powered by blists - more mailing lists