diff mbox series

[v10,17/19] KVM: xen: don't block on pfncache locks in kvm_xen_set_evtchn_fast()

Message ID 20231204144334.910-18-paul@xen.org
State New
Headers show
Series KVM: xen: update shared_info and vcpu_info handling | expand

Commit Message

Paul Durrant Dec. 4, 2023, 2:43 p.m. UTC 
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.
Instead, use read_trylock() and treat failure to lock the same as an
invalid cache.

[1] https://lore.kernel.org/lkml/99771ef3a4966a01fefd3adbb2ba9c3a75f97cf2.camel@infradead.org/T/#mbd06e5a04534ce9c0ee94bd8f1e8d942b2d45bd6

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
---
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

v10:
 - New in this version.
---
 arch/x86/kvm/xen.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

Comments

David Woodhouse Dec. 14, 2023, 2:03 p.m. UTC | #1 
On Mon, 2023-12-04 at 14:43 +0000, Paul Durrant wrote:
> 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.
> Instead, use read_trylock() and treat failure to lock the same as an
> invalid cache.
> 
> [1] https://lore.kernel.org/lkml/99771ef3a4966a01fefd3adbb2ba9c3a75f97cf2.camel@infradead.org/T/#mbd06e5a04534ce9c0ee94bd8f1e8d942b2d45bd6
> 
> Signed-off-by: Paul Durrant <pdurrant@amazon.com>

Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>

Although I would prefer the commit comment to note that this is only
wrong for PREEMPT_RT, as all those locks were irq-safe. This is because
PREEMPT_RT is going to turn them into mutexes — and mostly trick things
into working by making all IRQ handlers threaded... except this one
isn't just in an IRQ handler; its in an HRTIMER_MODE_ABS_HARD callback
which still *will* be in real interrupt context.

And there's no 'raw' version of the rwlock for us to use.
diff mbox series

Patch

diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 88ceaefaa121..7109d20a4608 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1665,10 +1665,13 @@  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;
 
@@ -1690,8 +1693,10 @@  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;
 }
 
@@ -1701,21 +1706,23 @@  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;
 		u32 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;
@@ -1729,7 +1736,7 @@  static bool set_vcpu_info_evtchn_pending(struct kvm_vcpu *vcpu, u32 port)
 		struct compat_vcpu_info *vcpu_info = gpc->khva;
 		u32 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;
@@ -1747,8 +1754,12 @@  static bool set_vcpu_info_evtchn_pending(struct kvm_vcpu *vcpu, u32 port)
 		kick_vcpu = false;
 	}
 
+
  out:
-	read_unlock_irqrestore(&gpc->lock, flags);
+	if (locked)
+		read_unlock(&gpc->lock);
+
+	local_irq_restore(flags);
 	return kick_vcpu;
 }