Merge tag 'v5.12-rc3' into x86/cleanups, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 156 insertions, 71 deletions

diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index da87f3a1e351..b8f2f971c2f0 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -47,6 +47,11 @@ static unsigned evtchn_2l_max_channels(void)
 	return EVTCHN_2L_NR_CHANNELS;
 }
 
+static void evtchn_2l_remove(evtchn_port_t evtchn, unsigned int cpu)
+{
+	clear_bit(evtchn, BM(per_cpu(cpu_evtchn_mask, cpu)));
+}
+
 static void evtchn_2l_bind_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
 				  unsigned int old_cpu)
 {
@@ -72,12 +77,6 @@ static bool evtchn_2l_is_pending(evtchn_port_t port)
 	return sync_test_bit(port, BM(&s->evtchn_pending[0]));
 }
 
-static bool evtchn_2l_test_and_set_mask(evtchn_port_t port)
-{
-	struct shared_info *s = HYPERVISOR_shared_info;
-	return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0]));
-}
-
 static void evtchn_2l_mask(evtchn_port_t port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -355,18 +354,27 @@ static void evtchn_2l_resume(void)
 				EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
 }
 
+static int evtchn_2l_percpu_deinit(unsigned int cpu)
+{
+	memset(per_cpu(cpu_evtchn_mask, cpu), 0, sizeof(xen_ulong_t) *
+			EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
+
+	return 0;
+}
+
 static const struct evtchn_ops evtchn_ops_2l = {
 	.max_channels      = evtchn_2l_max_channels,
 	.nr_channels       = evtchn_2l_max_channels,
+	.remove            = evtchn_2l_remove,
 	.bind_to_cpu       = evtchn_2l_bind_to_cpu,
 	.clear_pending     = evtchn_2l_clear_pending,
 	.set_pending       = evtchn_2l_set_pending,
 	.is_pending        = evtchn_2l_is_pending,
-	.test_and_set_mask = evtchn_2l_test_and_set_mask,
 	.mask              = evtchn_2l_mask,
 	.unmask            = evtchn_2l_unmask,
 	.handle_events     = evtchn_2l_handle_events,
 	.resume	           = evtchn_2l_resume,
+	.percpu_deinit     = evtchn_2l_percpu_deinit,
 };
 
 void __init xen_evtchn_2l_init(void)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index adb7260e94b2..8236e2364eeb 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -98,13 +98,19 @@ struct irq_info {
 	short refcnt;
 	u8 spurious_cnt;
 	u8 is_accounted;
-	enum xen_irq_type type; /* type */
+	short type;		/* type: IRQT_* */
+	u8 mask_reason;		/* Why is event channel masked */
+#define EVT_MASK_REASON_EXPLICIT	0x01
+#define EVT_MASK_REASON_TEMPORARY	0x02
+#define EVT_MASK_REASON_EOI_PENDING	0x04
+	u8 is_active;		/* Is event just being handled? */
 	unsigned irq;
 	evtchn_port_t evtchn;   /* event channel */
 	unsigned short cpu;     /* cpu bound */
 	unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */
 	unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */
 	u64 eoi_time;           /* Time in jiffies when to EOI. */
+	spinlock_t lock;
 
 	union {
 		unsigned short virq;
@@ -154,6 +160,7 @@ static DEFINE_RWLOCK(evtchn_rwlock);
  *   evtchn_rwlock
  *     IRQ-desc lock
  *       percpu eoi_list_lock
+ *         irq_info->lock
  */
 
 static LIST_HEAD(xen_irq_list_head);
@@ -304,6 +311,8 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	info->irq = irq;
 	info->evtchn = evtchn;
 	info->cpu = cpu;
+	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
+	spin_lock_init(&info->lock);
 
 	ret = set_evtchn_to_irq(evtchn, irq);
 	if (ret < 0)
@@ -377,6 +386,7 @@ static int xen_irq_info_pirq_setup(unsigned irq,
 static void xen_irq_info_cleanup(struct irq_info *info)
 {
 	set_evtchn_to_irq(info->evtchn, -1);
+	xen_evtchn_port_remove(info->evtchn, info->cpu);
 	info->evtchn = 0;
 	channels_on_cpu_dec(info);
 }
@@ -458,6 +468,34 @@ unsigned int cpu_from_evtchn(evtchn_port_t evtchn)
 	return ret;
 }
 
+static void do_mask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+
+	if (!info->mask_reason)
+		mask_evtchn(info->evtchn);
+
+	info->mask_reason |= reason;
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+static void do_unmask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+
+	info->mask_reason &= ~reason;
+
+	if (!info->mask_reason)
+		unmask_evtchn(info->evtchn);
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
 #ifdef CONFIG_X86
 static bool pirq_check_eoi_map(unsigned irq)
 {
@@ -604,7 +642,7 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
 	}
 
 	info->eoi_time = 0;
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
 }
 
 static void xen_irq_lateeoi_worker(struct work_struct *work)
@@ -773,6 +811,12 @@ static void xen_evtchn_close(evtchn_port_t port)
 		BUG();
 }
 
+static void event_handler_exit(struct irq_info *info)
+{
+	smp_store_release(&info->is_active, 0);
+	clear_evtchn(info->evtchn);
+}
+
 static void pirq_query_unmask(int irq)
 {
 	struct physdev_irq_status_query irq_status;
@@ -791,14 +835,15 @@ static void pirq_query_unmask(int irq)
 
 static void eoi_pirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
 	int rc = 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	clear_evtchn(evtchn);
+	event_handler_exit(info);
 
 	if (pirq_needs_eoi(data->irq)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
@@ -849,7 +894,8 @@ static unsigned int __startup_pirq(unsigned int irq)
 		goto err;
 
 out:
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EXPLICIT);
+
 	eoi_pirq(irq_get_irq_data(irq));
 
 	return 0;
@@ -876,7 +922,7 @@ static void shutdown_pirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	mask_evtchn(evtchn);
+	do_mask(info, EVT_MASK_REASON_EXPLICIT);
 	xen_evtchn_close(evtchn);
 	xen_irq_info_cleanup(info);
 }
@@ -1628,6 +1674,8 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 	}
 
 	info = info_for_irq(irq);
+	if (xchg_acquire(&info->is_active, 1))
+		return;
 
 	dev = (info->type == IRQT_EVTCHN) ? info->u.interdomain : NULL;
 	if (dev)
@@ -1720,10 +1768,10 @@ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
 }
 
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
-static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
+static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
-	int masked;
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return -1;
@@ -1739,7 +1787,7 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	 * Mask the event while changing the VCPU binding to prevent
 	 * it being delivered on an unexpected VCPU.
 	 */
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
 	/*
 	 * If this fails, it usually just indicates that we're dealing with a
@@ -1749,8 +1797,7 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
 		bind_evtchn_to_cpu(evtchn, tcpu, false);
 
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 0;
 }
@@ -1789,7 +1836,7 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 	unsigned int tcpu = select_target_cpu(dest);
 	int ret;
 
-	ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
+	ret = xen_rebind_evtchn_to_cpu(info_for_irq(data->irq), tcpu);
 	if (!ret)
 		irq_data_update_effective_affinity(data, cpumask_of(tcpu));
 
@@ -1798,28 +1845,29 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 
 static void enable_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void disable_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		mask_evtchn(evtchn);
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void ack_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
-	if (!VALID_EVTCHN(evtchn))
-		return;
-
-	clear_evtchn(evtchn);
+	if (VALID_EVTCHN(evtchn))
+		event_handler_exit(info);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
@@ -1828,18 +1876,39 @@ static void mask_ack_dynirq(struct irq_data *data)
 	ack_dynirq(data);
 }
 
+static void lateeoi_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
+		event_handler_exit(info);
+	}
+}
+
+static void lateeoi_mask_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+		event_handler_exit(info);
+	}
+}
+
 static int retrigger_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
-	int masked;
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return 0;
 
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 	set_evtchn(evtchn);
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 1;
 }
@@ -1938,10 +2007,11 @@ static void restore_cpu_ipis(unsigned int cpu)
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = info_for_irq(irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 }
 EXPORT_SYMBOL(xen_clear_irq_pending);
 void xen_set_irq_pending(int irq)
@@ -2053,8 +2123,8 @@ static struct irq_chip xen_lateeoi_chip __read_mostly = {
 	.irq_mask		= disable_dynirq,
 	.irq_unmask		= enable_dynirq,
 
-	.irq_ack		= mask_ack_dynirq,
-	.irq_mask_ack		= mask_ack_dynirq,
+	.irq_ack		= lateeoi_ack_dynirq,
+	.irq_mask_ack		= lateeoi_mask_ack_dynirq,
 
 	.irq_set_affinity	= set_affinity_irq,
 	.irq_retrigger		= retrigger_dynirq,
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index b234f1766810..ad9fe51d3fb3 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -209,12 +209,6 @@ static bool evtchn_fifo_is_pending(evtchn_port_t port)
 	return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
-static bool evtchn_fifo_test_and_set_mask(evtchn_port_t port)
-{
-	event_word_t *word = event_word_from_port(port);
-	return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
-}
-
 static void evtchn_fifo_mask(evtchn_port_t port)
 {
 	event_word_t *word = event_word_from_port(port);
@@ -423,7 +417,6 @@ static const struct evtchn_ops evtchn_ops_fifo = {
 	.clear_pending     = evtchn_fifo_clear_pending,
 	.set_pending       = evtchn_fifo_set_pending,
 	.is_pending        = evtchn_fifo_is_pending,
-	.test_and_set_mask = evtchn_fifo_test_and_set_mask,
 	.mask              = evtchn_fifo_mask,
 	.unmask            = evtchn_fifo_unmask,
 	.handle_events     = evtchn_fifo_handle_events,
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index 0a97c0549db7..4d3398eff9cd 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -14,13 +14,13 @@ struct evtchn_ops {
 	unsigned (*nr_channels)(void);
 
 	int (*setup)(evtchn_port_t port);
+	void (*remove)(evtchn_port_t port, unsigned int cpu);
 	void (*bind_to_cpu)(evtchn_port_t evtchn, unsigned int cpu,
 			    unsigned int old_cpu);
 
 	void (*clear_pending)(evtchn_port_t port);
 	void (*set_pending)(evtchn_port_t port);
 	bool (*is_pending)(evtchn_port_t port);
-	bool (*test_and_set_mask)(evtchn_port_t port);
 	void (*mask)(evtchn_port_t port);
 	void (*unmask)(evtchn_port_t port);
 
@@ -54,6 +54,13 @@ static inline int xen_evtchn_port_setup(evtchn_port_t evtchn)
 	return 0;
 }
 
+static inline void xen_evtchn_port_remove(evtchn_port_t evtchn,
+					  unsigned int cpu)
+{
+	if (evtchn_ops->remove)
+		evtchn_ops->remove(evtchn, cpu);
+}
+
 static inline void xen_evtchn_port_bind_to_cpu(evtchn_port_t evtchn,
 					       unsigned int cpu,
 					       unsigned int old_cpu)
@@ -76,11 +83,6 @@ static inline bool test_evtchn(evtchn_port_t port)
 	return evtchn_ops->is_pending(port);
 }
 
-static inline bool test_and_set_mask(evtchn_port_t port)
-{
-	return evtchn_ops->test_and_set_mask(port);
-}
-
 static inline void mask_evtchn(evtchn_port_t port)
 {
 	return evtchn_ops->mask(port);
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 5447c5156b2e..f01d58c7a042 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -133,20 +133,26 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	if (NULL == add)
 		return NULL;
 
-	add->grants    = kvcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
-	add->map_ops   = kvcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
-	add->unmap_ops = kvcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
-	add->kmap_ops  = kvcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
-	add->kunmap_ops = kvcalloc(count,
-				   sizeof(add->kunmap_ops[0]), GFP_KERNEL);
+	add->grants    = kvmalloc_array(count, sizeof(add->grants[0]),
+					GFP_KERNEL);
+	add->map_ops   = kvmalloc_array(count, sizeof(add->map_ops[0]),
+					GFP_KERNEL);
+	add->unmap_ops = kvmalloc_array(count, sizeof(add->unmap_ops[0]),
+					GFP_KERNEL);
 	add->pages     = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
-	    NULL == add->kmap_ops  ||
-	    NULL == add->kunmap_ops ||
 	    NULL == add->pages)
 		goto err;
+	if (use_ptemod) {
+		add->kmap_ops   = kvmalloc_array(count, sizeof(add->kmap_ops[0]),
+						 GFP_KERNEL);
+		add->kunmap_ops = kvmalloc_array(count, sizeof(add->kunmap_ops[0]),
+						 GFP_KERNEL);
+		if (NULL == add->kmap_ops || NULL == add->kunmap_ops)
+			goto err;
+	}
 
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 	add->dma_flags = dma_flags;
@@ -183,10 +189,14 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 		goto err;
 
 	for (i = 0; i < count; i++) {
-		add->map_ops[i].handle = -1;
-		add->unmap_ops[i].handle = -1;
-		add->kmap_ops[i].handle = -1;
-		add->kunmap_ops[i].handle = -1;
+		add->grants[i].domid = DOMID_INVALID;
+		add->grants[i].ref = INVALID_GRANT_REF;
+		add->map_ops[i].handle = INVALID_GRANT_HANDLE;
+		add->unmap_ops[i].handle = INVALID_GRANT_HANDLE;
+		if (use_ptemod) {
+			add->kmap_ops[i].handle = INVALID_GRANT_HANDLE;
+			add->kunmap_ops[i].handle = INVALID_GRANT_HANDLE;
+		}
 	}
 
 	add->index = 0;
@@ -274,7 +284,7 @@ static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data)
 			  map->grants[pgnr].ref,
 			  map->grants[pgnr].domid);
 	gnttab_set_unmap_op(&map->unmap_ops[pgnr], pte_maddr, flags,
-			    -1 /* handle */);
+			    INVALID_GRANT_HANDLE);
 	return 0;
 }
 
@@ -292,7 +302,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 
 	if (!use_ptemod) {
 		/* Note: it could already be mapped */
-		if (map->map_ops[0].handle != -1)
+		if (map->map_ops[0].handle != INVALID_GRANT_HANDLE)
 			return 0;
 		for (i = 0; i < map->count; i++) {
 			unsigned long addr = (unsigned long)
@@ -301,7 +311,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 				map->grants[i].ref,
 				map->grants[i].domid);
 			gnttab_set_unmap_op(&map->unmap_ops[i], addr,
-				map->flags, -1 /* handle */);
+				map->flags, INVALID_GRANT_HANDLE);
 		}
 	} else {
 		/*
@@ -327,13 +337,13 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 				map->grants[i].ref,
 				map->grants[i].domid);
 			gnttab_set_unmap_op(&map->kunmap_ops[i], address,
-				flags, -1);
+				flags, INVALID_GRANT_HANDLE);
 		}
 	}
 
 	pr_debug("map %d+%d\n", map->index, map->count);
-	err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
-			map->pages, map->count);
+	err = gnttab_map_refs(map->map_ops, map->kmap_ops, map->pages,
+			map->count);
 
 	for (i = 0; i < map->count; i++) {
 		if (map->map_ops[i].status == GNTST_okay)
@@ -385,7 +395,7 @@ static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
 		pr_debug("unmap handle=%d st=%d\n",
 			map->unmap_ops[offset+i].handle,
 			map->unmap_ops[offset+i].status);
-		map->unmap_ops[offset+i].handle = -1;
+		map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
 	}
 	return err;
 }
@@ -401,13 +411,15 @@ static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
 	 * already unmapped some of the grants. Only unmap valid ranges.
 	 */
 	while (pages && !err) {
-		while (pages && map->unmap_ops[offset].handle == -1) {
+		while (pages &&
+		       map->unmap_ops[offset].handle == INVALID_GRANT_HANDLE) {
 			offset++;
 			pages--;
 		}
 		range = 0;
 		while (range < pages) {
-			if (map->unmap_ops[offset+range].handle == -1)
+			if (map->unmap_ops[offset + range].handle ==
+			    INVALID_GRANT_HANDLE)
 				break;
 			range++;
 		}