From: Paul Durrant pdurrant@amazon.com
As described in [1] compiling with CONFIG_PROVE_RAW_LOCK_NESTING shows that kvm_xen_set_evtchn_fast() is blocking on pfncache locks in IRQ context. There is only actually blocking with PREEMPT_RT because the locks will turned into mutexes. There is no 'raw' version of rwlock_t that can be used to avoid that, so use read_trylock() and treat failure to lock the same as an invalid cache.
[1] https://lore.kernel.org/lkml/99771ef3a4966a01fefd3adbb2ba9c3a75f97cf2.camel@...
Signed-off-by: Paul Durrant pdurrant@amazon.com Reviewed-by: David Woodhouse dwmw@amazon.co.uk --- Cc: Sean Christopherson seanjc@google.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Ingo Molnar mingo@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Dave Hansen dave.hansen@linux.intel.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: David Woodhouse dwmw2@infradead.org Cc: x86@kernel.org
v11: - Amended the commit comment.
v10: - New in this version. --- arch/x86/kvm/xen.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 5ce02699f44c..9168a6ec88fd 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1673,10 +1673,13 @@ static int set_shinfo_evtchn_pending(struct kvm_vcpu *vcpu, u32 port) unsigned long flags; int rc = -EWOULDBLOCK;
- read_lock_irqsave(&gpc->lock, flags); - if (!kvm_gpc_check(gpc, PAGE_SIZE)) + local_irq_save(flags); + if (!read_trylock(&gpc->lock)) goto out;
+ if (!kvm_gpc_check(gpc, PAGE_SIZE)) + goto out_unlock; + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { struct shared_info *shinfo = gpc->khva;
@@ -1698,8 +1701,10 @@ static int set_shinfo_evtchn_pending(struct kvm_vcpu *vcpu, u32 port) rc = 1; /* It is newly raised */ }
+ out_unlock: + read_unlock(&gpc->lock); out: - read_unlock_irqrestore(&gpc->lock, flags); + local_irq_restore(flags); return rc; }
@@ -1709,21 +1714,23 @@ static bool set_vcpu_info_evtchn_pending(struct kvm_vcpu *vcpu, u32 port) struct gfn_to_pfn_cache *gpc = &vcpu->arch.xen.vcpu_info_cache; unsigned long flags; bool kick_vcpu = false; + bool locked;
- read_lock_irqsave(&gpc->lock, flags); + local_irq_save(flags); + locked = read_trylock(&gpc->lock);
/* * Try to deliver the event directly to the vcpu_info. If successful and * the guest is using upcall_vector delivery, send the MSI. - * If the pfncache is invalid, set the shadow. In this case, or if the - * guest is using another form of event delivery, the vCPU must be - * kicked to complete the delivery. + * If the pfncache lock is contended or the cache is invalid, set the + * shadow. In this case, or if the guest is using another form of event + * delivery, the vCPU must be kicked to complete the delivery. */ if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { struct vcpu_info *vcpu_info = gpc->khva; int port_word_bit = port / 64;
- if (!kvm_gpc_check(gpc, sizeof(*vcpu_info))) { + if ((!locked || !kvm_gpc_check(gpc, sizeof(*vcpu_info)))) { if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel)) kick_vcpu = true; goto out; @@ -1737,7 +1744,7 @@ static bool set_vcpu_info_evtchn_pending(struct kvm_vcpu *vcpu, u32 port) struct compat_vcpu_info *vcpu_info = gpc->khva; int port_word_bit = port / 32;
- if (!kvm_gpc_check(gpc, sizeof(*vcpu_info))) { + if ((!locked || !kvm_gpc_check(gpc, sizeof(*vcpu_info)))) { if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel)) kick_vcpu = true; goto out; @@ -1756,7 +1763,10 @@ static bool set_vcpu_info_evtchn_pending(struct kvm_vcpu *vcpu, u32 port) }
out: - read_unlock_irqrestore(&gpc->lock, flags); + if (locked) + read_unlock(&gpc->lock); + + local_irq_restore(flags); return kick_vcpu; }