3.16.51-rc1 review patch. If anyone has any objections, please let me know.
------------------
From: Boqun Feng <boqun.feng@xxxxxxxxx>
commit a2b7861bb33b2538420bb5d8554153484d3f961f upstream.
Currently, in PREEMPT_COUNT=n kernel, kvm_async_pf_task_wait() could call
schedule() to reschedule in some cases. This could result in
accidentally ending the current RCU read-side critical section early,
causing random memory corruption in the guest, or otherwise preempting
the currently running task inside between preempt_disable and
preempt_enable.
The difficulty to handle this well is because we don't know whether an
async PF delivered in a preemptible section or RCU read-side critical section
for PREEMPT_COUNT=n, since preempt_disable()/enable() and rcu_read_lock/unlock()
are both no-ops in that case.
To cure this, we treat any async PF interrupting a kernel context as one
that cannot be preempted, preventing kvm_async_pf_task_wait() from choosing
the schedule() path in that case.
To do so, a second parameter for kvm_async_pf_task_wait() is introduced,
so that we know whether it's called from a context interrupting the
kernel, and the parameter is set properly in all the callsites.
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
Signed-off-by: Boqun Feng <boqun.feng@xxxxxxxxx>
Signed-off-by: Radim Krčmář <rkrcmar@xxxxxxxxxx>
[bwh: Backported to 3.16:
- Use user_mode_vm() as equivalent to upstream user_mode()
- Adjust filename, context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
arch/x86/include/asm/kvm_para.h | 4 ++--
arch/x86/kernel/kvm.c | 14 ++++++++++----
arch/x86/kvm/svm.c | 2 +-
3 files changed, 13 insertions(+), 7 deletions(-)
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -95,7 +95,7 @@ static inline long kvm_hypercall4(unsign
bool kvm_para_available(void);
unsigned int kvm_arch_para_features(void);
void __init kvm_guest_init(void);
-void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
void kvm_async_pf_task_wake(u32 token);
u32 kvm_read_and_reset_pf_reason(void);
extern void kvm_disable_steal_time(void);
@@ -110,7 +110,7 @@ static inline void kvm_spinlock_init(voi
#else /* CONFIG_KVM_GUEST */
#define kvm_guest_init() do {} while (0)
-#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wait(T, I) do {} while(0)
#define kvm_async_pf_task_wake(T) do {} while(0)
static inline bool kvm_para_available(void)
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -116,7 +116,11 @@ static struct kvm_task_sleep_node *_find
return NULL;
}
-void kvm_async_pf_task_wait(u32 token)
+/*
+ * @interrupt_kernel: Is this called from a routine which interrupts the kernel
+ * (other than user space)?
+ */
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
{
u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
@@ -139,8 +143,10 @@ void kvm_async_pf_task_wait(u32 token)
n.token = token;
n.cpu = smp_processor_id();
- n.halted = is_idle_task(current) || preempt_count() > 1 ||
- rcu_preempt_depth();
+ n.halted = is_idle_task(current) ||
+ (IS_ENABLED(CONFIG_PREEMPT_COUNT)
+ ? preempt_count() > 1 || rcu_preempt_depth()
+ : interrupt_kernel);
init_waitqueue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
spin_unlock(&b->lock);
@@ -269,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs
/* page is swapped out by the host. */
prev_state = exception_enter();
exit_idle();
- kvm_async_pf_task_wait((u32)read_cr2());
+ kvm_async_pf_task_wait((u32)read_cr2(), !user_mode_vm(regs));
exception_exit(prev_state);
break;
case KVM_PV_REASON_PAGE_READY:
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1718,7 +1718,7 @@ static int pf_interception(struct vcpu_s
case KVM_PV_REASON_PAGE_NOT_PRESENT:
svm->apf_reason = 0;
local_irq_disable();
- kvm_async_pf_task_wait(fault_address);
+ kvm_async_pf_task_wait(fault_address, 0);
local_irq_enable();
break;
case KVM_PV_REASON_PAGE_READY: