KVM: Move all accesses to kvm::irq_routing into irqchip.c

Now that struct _irqfd does not keep a reference to storage pointed
to by the irq_routing field of struct kvm, we can move the statement
that updates it out from under the irqfds.lock and put it in
kvm_set_irq_routing() instead.  That means we then have to take a
srcu_read_lock on kvm->irq_srcu around the irqfd_update call in
kvm_irqfd_assign(), since holding the kvm->irqfds.lock no longer
ensures that that the routing can't change.

Combined with changing kvm_irq_map_gsi() and kvm_irq_map_chip_pin()
to take a struct kvm * argument instead of the pointer to the routing
table, this allows us to to move all references to kvm->irq_routing
into irqchip.c.  That in turn allows us to move the definition of the
kvm_irq_routing_table struct into irqchip.c as well.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Tested-by: Eric Auger <eric.auger@linaro.org>
Tested-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

include/linux/kvm_host.h

@@ -325,24 +325,7 @@ struct kvm_kernel_irq_routing_entry {
 	struct hlist_node link;
 };
 
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-
-struct kvm_irq_routing_table {
-	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
-	struct kvm_kernel_irq_routing_entry *rt_entries;
-	u32 nr_rt_entries;
-	/*
-	 * Array indexed by gsi. Each entry contains list of irq chips
-	 * the gsi is connected to.
-	 */
-	struct hlist_head map[0];
-};
-
-#else
-
-struct kvm_irq_routing_table {};
-
-#endif
+struct kvm_irq_routing_table;
 
 #ifndef KVM_PRIVATE_MEM_SLOTS
 #define KVM_PRIVATE_MEM_SLOTS 0
@@ -401,8 +384,7 @@ struct kvm {
 	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	/*
-	 * Update side is protected by irq_lock and,
-	 * if configured, irqfds.lock.
+	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
 	struct hlist_head mask_notifier_list;
@@ -752,10 +734,9 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask);
 
-int kvm_irq_map_gsi(struct kvm_kernel_irq_routing_entry *entries,
-		    struct kvm_irq_routing_table *irq_rt, int gsi);
-int kvm_irq_map_chip_pin(struct kvm_irq_routing_table *irq_rt,
-			 unsigned irqchip, unsigned pin);
+int kvm_irq_map_gsi(struct kvm *kvm,
+		    struct kvm_kernel_irq_routing_entry *entries, int gsi);
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
 
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 		bool line_status);
@@ -967,7 +948,7 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
-void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
+void kvm_irq_routing_update(struct kvm *);
 #else
 static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 {
@@ -989,10 +970,8 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 static inline void kvm_irqfd_release(struct kvm *kvm) {}
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm,
-					  struct kvm_irq_routing_table *irq_rt)
+static inline void kvm_irq_routing_update(struct kvm *kvm)
 {
-	rcu_assign_pointer(kvm->irq_routing, irq_rt);
 }
 #endif
 

virt/kvm/eventfd.c

@@ -278,14 +278,13 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 }
 
 /* Must be called under irqfds.lock */
-static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
-			 struct kvm_irq_routing_table *irq_rt)
+static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd)
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
 	int i, n_entries;
 
-	n_entries = kvm_irq_map_gsi(entries, irq_rt, irqfd->gsi);
+	n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi);
 
 	write_seqcount_begin(&irqfd->irq_entry_sc);
 
@@ -304,12 +303,12 @@ static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
 static int
 kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
-	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
 	struct fd f;
 	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
 	int ret;
 	unsigned int events;
+	int idx;
 
 	irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
 	if (!irqfd)
@@ -403,9 +402,9 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 		goto fail;
 	}
 
-	irq_rt = rcu_dereference_protected(kvm->irq_routing,
-					   lockdep_is_held(&kvm->irqfds.lock));
-	irqfd_update(kvm, irqfd, irq_rt);
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irqfd_update(kvm, irqfd);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
 
@@ -539,20 +538,17 @@ kvm_irqfd_release(struct kvm *kvm)
 }
 
 /*
- * Change irq_routing and irqfd.
+ * Take note of a change in irq routing.
  * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
  */
-void kvm_irq_routing_update(struct kvm *kvm,
-			    struct kvm_irq_routing_table *irq_rt)
+void kvm_irq_routing_update(struct kvm *kvm)
 {
 	struct _irqfd *irqfd;
 
 	spin_lock_irq(&kvm->irqfds.lock);
 
-	rcu_assign_pointer(kvm->irq_routing, irq_rt);
-
 	list_for_each_entry(irqfd, &kvm->irqfds.items, list)
-		irqfd_update(kvm, irqfd, irq_rt);
+		irqfd_update(kvm, irqfd);
 
 	spin_unlock_irq(&kvm->irqfds.lock);
 }

virt/kvm/irq_comm.c

@@ -163,7 +163,6 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
 	struct kvm_kernel_irq_routing_entry *e;
 	int ret = -EINVAL;
-	struct kvm_irq_routing_table *irq_rt;
 	int idx;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
@@ -177,8 +176,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	 * which is limited to 1:1 GSI mapping.
 	 */
 	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	if (kvm_irq_map_gsi(entries, irq_rt, irq) > 0) {
+	if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
 		e = &entries[0];
 		if (likely(e->type == KVM_IRQ_ROUTING_MSI))
 			ret = kvm_set_msi_inatomic(e, kvm);
@@ -264,7 +262,7 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	int idx, gsi;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
-	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
 			if (kimn->irq == gsi)

virt/kvm/irqchip.c

@@ -31,12 +31,26 @@
 #include <trace/events/kvm.h>
 #include "irq.h"
 
-int kvm_irq_map_gsi(struct kvm_kernel_irq_routing_entry *entries,
-		    struct kvm_irq_routing_table *irq_rt, int gsi)
+struct kvm_irq_routing_table {
+	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
+	struct kvm_kernel_irq_routing_entry *rt_entries;
+	u32 nr_rt_entries;
+	/*
+	 * Array indexed by gsi. Each entry contains list of irq chips
+	 * the gsi is connected to.
+	 */
+	struct hlist_head map[0];
+};
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+		    struct kvm_kernel_irq_routing_entry *entries, int gsi)
 {
+	struct kvm_irq_routing_table *irq_rt;
 	struct kvm_kernel_irq_routing_entry *e;
 	int n = 0;
 
+	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
+					lockdep_is_held(&kvm->irq_lock));
 	if (gsi < irq_rt->nr_rt_entries) {
 		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
 			entries[n] = *e;
@@ -47,21 +61,21 @@ int kvm_irq_map_gsi(struct kvm_kernel_irq_routing_entry *entries,
 	return n;
 }
 
-int kvm_irq_map_chip_pin(struct kvm_irq_routing_table *irq_rt,
-			 unsigned irqchip, unsigned pin)
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
+	struct kvm_irq_routing_table *irq_rt;
+
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
 	return irq_rt->chip[irqchip][pin];
 }
 
 bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
-	struct kvm_irq_routing_table *irq_rt;
 	struct kvm_irq_ack_notifier *kian;
 	int gsi, idx;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	gsi = kvm_irq_map_chip_pin(irq_rt, irqchip, pin);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
 					 link)
@@ -78,15 +92,13 @@ EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
 
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
-	struct kvm_irq_routing_table *irq_rt;
 	struct kvm_irq_ack_notifier *kian;
 	int gsi, idx;
 
 	trace_kvm_ack_irq(irqchip, pin);
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	gsi = kvm_irq_map_chip_pin(irq_rt, irqchip, pin);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
 					 link)
@@ -143,7 +155,6 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 {
 	struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS];
 	int ret = -1, i, idx;
-	struct kvm_irq_routing_table *irq_rt;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
@@ -152,8 +163,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 	 * writes to the unused one.
 	 */
 	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	i = kvm_irq_map_gsi(irq_set, irq_rt, irq);
+	i = kvm_irq_map_gsi(kvm, irq_set, irq);
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	while(i--) {
@@ -250,7 +260,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
 
 	mutex_lock(&kvm->irq_lock);
 	old = kvm->irq_routing;
-	kvm_irq_routing_update(kvm, new);
+	rcu_assign_pointer(kvm->irq_routing, new);
+	kvm_irq_routing_update(kvm);
 	mutex_unlock(&kvm->irq_lock);
 
 	synchronize_srcu_expedited(&kvm->irq_srcu);