Merge branch 'irq/for-block' into irq/core

Pull the irq affinity managing code which is in a seperate branch for block
developers to pull.

9 files changed, 153 insertions, 39 deletions

diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 2ee42e9..1d3ee31 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
 obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
 obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
+obj-$(CONFIG_SMP) += affinity.o
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
new file mode 100644
index 0000000..f689593
--- /dev/null
+++ b/kernel/irq/affinity.c
@@ -0,0 +1,61 @@
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+
+static int get_first_sibling(unsigned int cpu)
+{
+	unsigned int ret;
+
+	ret = cpumask_first(topology_sibling_cpumask(cpu));
+	if (ret < nr_cpu_ids)
+		return ret;
+	return cpu;
+}
+
+/*
+ * Take a map of online CPUs and the number of available interrupt vectors
+ * and generate an output cpumask suitable for spreading MSI/MSI-X vectors
+ * so that they are distributed as good as possible around the CPUs.  If
+ * more vectors than CPUs are available we'll map one to each CPU,
+ * otherwise we map one to the first sibling of each socket.
+ *
+ * If there are more vectors than CPUs we will still only have one bit
+ * set per CPU, but interrupt code will keep on assigning the vectors from
+ * the start of the bitmap until we run out of vectors.
+ */
+struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
+{
+	struct cpumask *affinity_mask;
+	unsigned int max_vecs = *nr_vecs;
+
+	if (max_vecs == 1)
+		return NULL;
+
+	affinity_mask = kzalloc(cpumask_size(), GFP_KERNEL);
+	if (!affinity_mask) {
+		*nr_vecs = 1;
+		return NULL;
+	}
+
+	if (max_vecs >= num_online_cpus()) {
+		cpumask_copy(affinity_mask, cpu_online_mask);
+		*nr_vecs = num_online_cpus();
+	} else {
+		unsigned int vecs = 0, cpu;
+
+		for_each_online_cpu(cpu) {
+			if (cpu == get_first_sibling(cpu)) {
+				cpumask_set_cpu(cpu, affinity_mask);
+				vecs++;
+			}
+
+			if (--max_vecs == 0)
+				break;
+		}
+		*nr_vecs = vecs;
+	}
+
+	return affinity_mask;
+}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 0c6f35b..bc226e7 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -107,6 +107,8 @@ static inline void unregister_handler_proc(unsigned int irq,
 					   struct irqaction *action) { }
 #endif
 
+extern bool irq_can_set_affinity_usr(unsigned int irq);
+
 extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 89b49f6..4fd2351 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -76,7 +76,7 @@ int irq_reserve_ipi(struct irq_domain *domain,
 		}
 	}
 
-	virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE);
+	virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL);
 	if (virq <= 0) {
 		pr_warn("Can't reserve IPI, failed to alloc descs\n");
 		return -ENOMEM;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 8731e1c..a623b44 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -68,9 +68,13 @@ static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
 	return 0;
 }
 
-static void desc_smp_init(struct irq_desc *desc, int node)
+static void desc_smp_init(struct irq_desc *desc, int node,
+			  const struct cpumask *affinity)
 {
-	cpumask_copy(desc->irq_common_data.affinity, irq_default_affinity);
+	if (!affinity)
+		affinity = irq_default_affinity;
+	cpumask_copy(desc->irq_common_data.affinity, affinity);
+
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_clear(desc->pending_mask);
 #endif
@@ -82,11 +86,12 @@ static void desc_smp_init(struct irq_desc *desc, int node)
 #else
 static inline int
 alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
-static inline void desc_smp_init(struct irq_desc *desc, int node) { }
+static inline void
+desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { }
 #endif
 
 static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
-		struct module *owner)
+			      const struct cpumask *affinity, struct module *owner)
 {
 	int cpu;
 
@@ -107,7 +112,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
-	desc_smp_init(desc, node);
+	desc_smp_init(desc, node, affinity);
 }
 
 int nr_irqs = NR_IRQS;
@@ -158,7 +163,9 @@ void irq_unlock_sparse(void)
 	mutex_unlock(&sparse_irq_lock);
 }
 
-static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
+static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
+				   const struct cpumask *affinity,
+				   struct module *owner)
 {
 	struct irq_desc *desc;
 	gfp_t gfp = GFP_KERNEL;
@@ -178,7 +185,8 @@ static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_rcu_head(&desc->rcu);
 
-	desc_set_defaults(irq, desc, node, owner);
+	desc_set_defaults(irq, desc, node, affinity, owner);
+	irqd_set(&desc->irq_data, flags);
 
 	return desc;
 
@@ -223,13 +231,32 @@ static void free_desc(unsigned int irq)
 }
 
 static int alloc_descs(unsigned int start, unsigned int cnt, int node,
-		       struct module *owner)
+		       const struct cpumask *affinity, struct module *owner)
 {
+	const struct cpumask *mask = NULL;
 	struct irq_desc *desc;
-	int i;
+	unsigned int flags;
+	int i, cpu = -1;
+
+	if (affinity && cpumask_empty(affinity))
+		return -EINVAL;
+
+	flags = affinity ? IRQD_AFFINITY_MANAGED : 0;
 
 	for (i = 0; i < cnt; i++) {
-		desc = alloc_desc(start + i, node, owner);
+		if (affinity) {
+			cpu = cpumask_next(cpu, affinity);
+			if (cpu >= nr_cpu_ids)
+				cpu = cpumask_first(affinity);
+			node = cpu_to_node(cpu);
+
+			/*
+			 * For single allocations we use the caller provided
+			 * mask otherwise we use the mask of the target cpu
+			 */
+			mask = cnt == 1 ? affinity : cpumask_of(cpu);
+		}
+		desc = alloc_desc(start + i, node, flags, mask, owner);
 		if (!desc)
 			goto err;
 		mutex_lock(&sparse_irq_lock);
@@ -277,7 +304,7 @@ int __init early_irq_init(void)
 		nr_irqs = initcnt;
 
 	for (i = 0; i < initcnt; i++) {
-		desc = alloc_desc(i, node, NULL);
+		desc = alloc_desc(i, node, 0, NULL, NULL);
 		set_bit(i, allocated_irqs);
 		irq_insert_desc(i, desc);
 	}
@@ -311,7 +338,7 @@ int __init early_irq_init(void)
 		alloc_masks(&desc[i], GFP_KERNEL, node);
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		desc_set_defaults(i, &desc[i], node, NULL);
+		desc_set_defaults(i, &desc[i], node, NULL, NULL);
 	}
 	return arch_early_irq_init();
 }
@@ -328,11 +355,12 @@ static void free_desc(unsigned int irq)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL);
+	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
+			      const struct cpumask *affinity,
 			      struct module *owner)
 {
 	u32 i;
@@ -453,12 +481,15 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
  * @cnt:	Number of consecutive irqs to allocate.
  * @node:	Preferred node on which the irq descriptor should be allocated
  * @owner:	Owning module (can be NULL)
+ * @affinity:	Optional pointer to an affinity mask which hints where the
+ *		irq descriptors should be allocated and which default
+ *		affinities to use
  *
  * Returns the first irq number or error code
  */
 int __ref
 __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
-		  struct module *owner)
+		  struct module *owner, const struct cpumask *affinity)
 {
 	int start, ret;
 
@@ -494,7 +525,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 
 	bitmap_set(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
-	return alloc_descs(start, cnt, node, owner);
+	return alloc_descs(start, cnt, node, affinity, owner);
 
 err:
 	mutex_unlock(&sparse_irq_lock);
@@ -512,7 +543,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs);
  */
 unsigned int irq_alloc_hwirqs(int cnt, int node)
 {
-	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL);
+	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL);
 
 	if (irq < 0)
 		return 0;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5d89d72..a828537 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -481,7 +481,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 	}
 
 	/* Allocate a virtual interrupt number */
-	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node));
+	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL);
 	if (virq <= 0) {
 		pr_debug("-> virq allocation failed\n");
 		return 0;
@@ -879,19 +879,23 @@ const struct irq_domain_ops irq_domain_simple_ops = {
 EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
 
 int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
-			   int node)
+			   int node, const struct cpumask *affinity)
 {
 	unsigned int hint;
 
 	if (virq >= 0) {
-		virq = irq_alloc_descs(virq, virq, cnt, node);
+		virq = __irq_alloc_descs(virq, virq, cnt, node, THIS_MODULE,
+					 affinity);
 	} else {
 		hint = hwirq % nr_irqs;
 		if (hint == 0)
 			hint++;
-		virq = irq_alloc_descs_from(hint, cnt, node);
-		if (virq <= 0 && hint > 1)
-			virq = irq_alloc_descs_from(1, cnt, node);
+		virq = __irq_alloc_descs(-1, hint, cnt, node, THIS_MODULE,
+					 affinity);
+		if (virq <= 0 && hint > 1) {
+			virq = __irq_alloc_descs(-1, 1, cnt, node, THIS_MODULE,
+						 affinity);
+		}
 	}
 
 	return virq;
@@ -1204,6 +1208,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
  * @node:	NUMA node id for memory allocation
  * @arg:	domain specific argument
  * @realloc:	IRQ descriptors have already been allocated if true
+ * @affinity:	Optional irq affinity mask for multiqueue devices
  *
  * Allocate IRQ numbers and initialized all data structures to support
  * hierarchy IRQ domains.
@@ -1219,7 +1224,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
  */
 int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 			    unsigned int nr_irqs, int node, void *arg,
-			    bool realloc)
+			    bool realloc, const struct cpumask *affinity)
 {
 	int i, ret, virq;
 
@@ -1237,7 +1242,8 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 	if (realloc && irq_base >= 0) {
 		virq = irq_base;
 	} else {
-		virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node);
+		virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node,
+					      affinity);
 		if (virq < 0) {
 			pr_debug("cannot allocate IRQ(base %d, count %d)\n",
 				 irq_base, nr_irqs);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 00cfc85..73a2b78 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -115,12 +115,12 @@ EXPORT_SYMBOL(synchronize_irq);
 #ifdef CONFIG_SMP
 cpumask_var_t irq_default_affinity;
 
-static int __irq_can_set_affinity(struct irq_desc *desc)
+static bool __irq_can_set_affinity(struct irq_desc *desc)
 {
 	if (!desc || !irqd_can_balance(&desc->irq_data) ||
 	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
-		return 0;
-	return 1;
+		return false;
+	return true;
 }
 
 /**
@@ -134,6 +134,21 @@ int irq_can_set_affinity(unsigned int irq)
 }
 
 /**
+ * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space
+ * @irq:	Interrupt to check
+ *
+ * Like irq_can_set_affinity() above, but additionally checks for the
+ * AFFINITY_MANAGED flag.
+ */
+bool irq_can_set_affinity_usr(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return __irq_can_set_affinity(desc) &&
+		!irqd_affinity_is_managed(&desc->irq_data);
+}
+
+/**
  *	irq_set_thread_affinity - Notify irq threads to adjust affinity
  *	@desc:		irq descriptor which has affitnity changed
  *
@@ -338,10 +353,11 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask)
 		return 0;
 
 	/*
-	 * Preserve an userspace affinity setup, but make sure that
-	 * one of the targets is online.
+	 * Preserve the managed affinity setting and an userspace affinity
+	 * setup, but make sure that one of the targets is online.
 	 */
-	if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
+	if (irqd_affinity_is_managed(&desc->irq_data) ||
+	    irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
 		if (cpumask_intersects(desc->irq_common_data.affinity,
 				       cpu_online_mask))
 			set = desc->irq_common_data.affinity;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 38e89ce..0e2a736 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -324,7 +324,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 	struct msi_domain_ops *ops = info->ops;
 	msi_alloc_info_t arg;
 	struct msi_desc *desc;
-	int i, ret, virq = -1;
+	int i, ret, virq;
 
 	ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
 	if (ret)
@@ -332,13 +332,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 
 	for_each_msi_entry(desc, dev) {
 		ops->set_desc(&arg, desc);
-		if (info->flags & MSI_FLAG_IDENTITY_MAP)
-			virq = (int)ops->get_hwirq(info, &arg);
-		else
-			virq = -1;
 
-		virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
-					       dev_to_node(dev), &arg, false);
+		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
+					       dev_to_node(dev), &arg, false,
+					       desc->affinity);
 		if (virq < 0) {
 			ret = -ENOSPC;
 			if (ops->handle_error)
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index f30425d..feaa813 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -96,7 +96,7 @@ static ssize_t write_irq_affinity(int type, struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_can_set_affinity(irq) || no_irq_affinity)
+	if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
 		return -EIO;
 
 	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))