From 7f7ace0cda64c99599c23785f8979a072e118058 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 21:58:08 -0800
Subject: cpumask: update irq_desc to use cpumask_var_t

Impact: reduce memory usage, use new cpumask API.

Replace the affinity and pending_masks with cpumask_var_t's.  This adds
to the significant size reduction done with the SPARSE_IRQS changes.

The added functions (init_alloc_desc_masks & init_copy_desc_masks) are
in the include file so they can be inlined (and optimized out for the
!CONFIG_CPUMASKS_OFFSTACK case.)  [Naming chosen to be consistent with
the other init*irq functions, as well as the backwards arg declaration
of "from, to" instead of the more common "to, from" standard.]

Includes a slight change to the declaration of struct irq_desc to embed
the pending_mask within ifdef(CONFIG_SMP) to be consistent with other
references, and some small changes to Xen.

Tested: sparse/non-sparse/cpumask_offstack/non-cpumask_offstack/nonuma/nosmp on x86_64

Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: virtualization@lists.osdl.org
Cc: xen-devel@lists.xensource.com
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
---
 kernel/irq/chip.c         |  5 ++++-
 kernel/irq/handle.c       | 26 ++++++++++++++------------
 kernel/irq/manage.c       | 12 ++++++------
 kernel/irq/migration.c    | 12 ++++++------
 kernel/irq/numa_migrate.c | 12 +++++++++++-
 kernel/irq/proc.c         |  4 ++--
 6 files changed, 43 insertions(+), 28 deletions(-)

(limited to 'kernel/irq')

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f63c706d25e..c248eba98b4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq)
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-	cpumask_setall(&desc->affinity);
+	cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
 #endif
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index c20db0be917..b8fa1354f01 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -64,9 +64,6 @@ static struct irq_desc irq_desc_init = {
 	.handle_irq = handle_bad_irq,
 	.depth      = 1,
 	.lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-	.affinity   = CPU_MASK_ALL
-#endif
 };
 
 void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
@@ -88,6 +85,8 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
 
 static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 {
+	int node = cpu_to_node(cpu);
+
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	spin_lock_init(&desc->lock);
@@ -101,6 +100,10 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
+	if (!init_alloc_desc_masks(desc, node, false)) {
+		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+		BUG_ON(1);
+	}
 	arch_init_chip_data(desc, cpu);
 }
 
@@ -119,9 +122,6 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
 		.handle_irq = handle_bad_irq,
 		.depth	    = 1,
 		.lock	    = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-		.affinity   = CPU_MASK_ALL
-#endif
 	}
 };
 
@@ -141,7 +141,7 @@ int __init early_irq_init(void)
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy[i];
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-
+		init_alloc_desc_masks(&desc[i], 0, true);
 		irq_desc_ptrs[i] = desc + i;
 	}
 
@@ -188,6 +188,10 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 		printk(KERN_ERR "can not alloc irq_desc\n");
 		BUG_ON(1);
 	}
+	if (!init_alloc_desc_masks(desc, node, false)) {
+		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+		BUG_ON(1);
+	}
 	init_one_irq_desc(irq, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
@@ -207,9 +211,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 		.handle_irq = handle_bad_irq,
 		.depth = 1,
 		.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
-#ifdef CONFIG_SMP
-		.affinity = CPU_MASK_ALL
-#endif
 	}
 };
 
@@ -222,9 +223,10 @@ int __init early_irq_init(void)
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		desc[i].irq = i;
-
+		init_alloc_desc_masks(&desc[i], 0, true);
+	}
 	return arch_early_irq_init();
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index cd0cd8dcb34..b98739af455 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -98,14 +98,14 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-		cpumask_copy(&desc->affinity, cpumask);
+		cpumask_copy(desc->affinity, cpumask);
 		desc->chip->set_affinity(irq, cpumask);
 	} else {
 		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(&desc->pending_mask, cpumask);
+		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	cpumask_copy(&desc->affinity, cpumask);
+	cpumask_copy(desc->affinity, cpumask);
 	desc->chip->set_affinity(irq, cpumask);
 #endif
 	desc->status |= IRQ_AFFINITY_SET;
@@ -127,16 +127,16 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+		if (cpumask_any_and(desc->affinity, cpu_online_mask)
 		    < nr_cpu_ids)
 			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+	cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-	desc->chip->set_affinity(irq, &desc->affinity);
+	desc->chip->set_affinity(irq, desc->affinity);
 
 	return 0;
 }
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index bd72329e630..e05ad9be43b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -18,7 +18,7 @@ void move_masked_irq(int irq)
 
 	desc->status &= ~IRQ_MOVE_PENDING;
 
-	if (unlikely(cpumask_empty(&desc->pending_mask)))
+	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
 	if (!desc->chip->set_affinity)
@@ -38,13 +38,13 @@ void move_masked_irq(int irq)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
+	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
 		   < nr_cpu_ids)) {
-		cpumask_and(&desc->affinity,
-			    &desc->pending_mask, cpu_online_mask);
-		desc->chip->set_affinity(irq, &desc->affinity);
+		cpumask_and(desc->affinity,
+			    desc->pending_mask, cpu_online_mask);
+		desc->chip->set_affinity(irq, desc->affinity);
 	}
-	cpumask_clear(&desc->pending_mask);
+	cpumask_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index ecf765c6a77..f001a4ea641 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -46,6 +46,7 @@ static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 	desc->cpu = cpu;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+	init_copy_desc_masks(old_desc, desc);
 	arch_init_copy_chip_data(old_desc, desc, cpu);
 }
 
@@ -76,11 +77,20 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 	if (!desc) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+		printk(KERN_ERR "irq %d: can not get new irq_desc "
+				"for migration.\n", irq);
 		/* still use old one */
 		desc = old_desc;
 		goto out_unlock;
 	}
+	if (!init_alloc_desc_masks(desc, node, false)) {
+		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+				"for migration.\n", irq);
+		/* still use old one */
+		kfree(desc);
+		desc = old_desc;
+		goto out_unlock;
+	}
 	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index aae3f742bce..692363dd591 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,11 +20,11 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = &desc->affinity;
+	const struct cpumask *mask = desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
-		mask = &desc->pending_mask;
+		mask = desc->pending_mask;
 #endif
 	seq_cpumask(m, mask);
 	seq_putc(m, '\n');
-- 
cgit v1.2.3


From 802bf931f2688ad125b73db597ce63cc842fb27a Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 21:58:09 -0800
Subject: cpumask: fix bug in use cpumask_var_t in irq_desc

Impact: fix bug where new irq_desc uses old cpumask pointers which are freed.

As Yinghai pointed out, init_copy_one_irq_desc() copies the old desc to
the new desc overwriting the cpumask pointers.  Since the old_desc and
the cpumask pointers are freed, then memory corruption will occur if
these old pointers are used.

Move the allocation of these pointers to after the copy.

Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/irq.h       |  9 +++++++--
 kernel/irq/handle.c       |  8 +-------
 kernel/irq/numa_migrate.c | 13 ++++++++-----
 3 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'kernel/irq')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index fa27210f1df..27a67536511 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -426,15 +426,18 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 /**
  * init_alloc_desc_masks - allocate cpumasks for irq_desc
  * @desc:	pointer to irq_desc struct
+ * @cpu:	cpu which will be handling the cpumasks
  * @boot:	true if need bootmem
  *
  * Allocates affinity and pending_mask cpumask if required.
  * Returns true if successful (or not required).
  * Side effect: affinity has all bits set, pending_mask has all bits clear.
  */
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 								bool boot)
 {
+	int node;
+
 	if (boot) {
 		alloc_bootmem_cpumask_var(&desc->affinity);
 		cpumask_setall(desc->affinity);
@@ -446,6 +449,8 @@ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
 		return true;
 	}
 
+	node = cpu_to_node(cpu);
+
 	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
 		return false;
 	cpumask_setall(desc->affinity);
@@ -484,7 +489,7 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 
 #else /* !CONFIG_SMP */
 
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 								bool boot)
 {
 	return true;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index b8fa1354f01..f01c0a30cb4 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -85,8 +85,6 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
 
 static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 {
-	int node = cpu_to_node(cpu);
-
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	spin_lock_init(&desc->lock);
@@ -100,7 +98,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
-	if (!init_alloc_desc_masks(desc, node, false)) {
+	if (!init_alloc_desc_masks(desc, cpu, false)) {
 		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
 		BUG_ON(1);
 	}
@@ -188,10 +186,6 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 		printk(KERN_ERR "can not alloc irq_desc\n");
 		BUG_ON(1);
 	}
-	if (!init_alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
-		BUG_ON(1);
-	}
 	init_one_irq_desc(irq, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index f001a4ea641..666260e4c06 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -38,16 +38,22 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
 	old_desc->kstat_irqs = NULL;
 }
 
-static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 		 struct irq_desc *desc, int cpu)
 {
 	memcpy(desc, old_desc, sizeof(struct irq_desc));
+	if (!init_alloc_desc_masks(desc, cpu, false)) {
+		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+				"for migration.\n", irq);
+		return false;
+	}
 	spin_lock_init(&desc->lock);
 	desc->cpu = cpu;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
 	init_copy_desc_masks(old_desc, desc);
 	arch_init_copy_chip_data(old_desc, desc, cpu);
+	return true;
 }
 
 static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
@@ -83,15 +89,12 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 		desc = old_desc;
 		goto out_unlock;
 	}
-	if (!init_alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
-				"for migration.\n", irq);
+	if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
 		/* still use old one */
 		kfree(desc);
 		desc = old_desc;
 		goto out_unlock;
 	}
-	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
 
-- 
cgit v1.2.3


From 9594949b060efe86ecaa1a66839232a3b9800bc9 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:06 -0800
Subject: irq: change references from NR_IRQS to nr_irqs

Impact: preparation, cleanup, add KERN_INFO printk

Modify references from NR_IRQS to nr_irqs as the later will become
variable-sized based on nr_cpu_ids when CONFIG_SPARSE_IRQS=y.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 arch/x86/kernel/io_apic.c |  2 +-
 kernel/irq/handle.c       | 14 +++++++++-----
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'kernel/irq')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1337eab60ec..ae80638012d 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3183,7 +3183,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = irq_want; new < NR_IRQS; new++) {
+	for (new = irq_want; new < nr_irqs; new++) {
 		if (platform_legacy_irq(new))
 			continue;
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f01c0a30cb4..790c5fa7ea3 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -132,6 +132,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
+
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
@@ -143,7 +145,7 @@ int __init early_irq_init(void)
 		irq_desc_ptrs[i] = desc + i;
 	}
 
-	for (i = legacy_count; i < NR_IRQS; i++)
+	for (i = legacy_count; i < nr_irqs; i++)
 		irq_desc_ptrs[i] = NULL;
 
 	return arch_early_irq_init();
@@ -151,7 +153,7 @@ int __init early_irq_init(void)
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL;
+	return (irq < nr_irqs) ? irq_desc_ptrs[irq] : NULL;
 }
 
 struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
@@ -160,9 +162,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 	unsigned long flags;
 	int node;
 
-	if (irq >= NR_IRQS) {
-		printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
-				irq, NR_IRQS);
+	if (irq >= nr_irqs) {
+		printk(KERN_WARNING "irq >= nr_irqs in irq_to_desc_alloc: %d %d\n",
+				irq, nr_irqs);
 		WARN_ON(1);
 		return NULL;
 	}
@@ -214,6 +216,8 @@ int __init early_irq_init(void)
 	int count;
 	int i;
 
+	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
-- 
cgit v1.2.3


From e2f4d06545ec1f29b0e838ee34cbf3500ea5b9a4 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:06 -0800
Subject: irq: use WARN() instead of WARN_ON().

Impact: cleanup WARN msg.

Ingo requested:
> While at it, could you please also convert this to a WARN() construct
> instead? (in a separate commit)

... and it shall be done.  ;-)

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/irq/handle.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'kernel/irq')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 790c5fa7ea3..fd1ef16252f 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -163,9 +163,8 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 	int node;
 
 	if (irq >= nr_irqs) {
-		printk(KERN_WARNING "irq >= nr_irqs in irq_to_desc_alloc: %d %d\n",
-				irq, nr_irqs);
-		WARN_ON(1);
+		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
+			irq, nr_irqs);
 		return NULL;
 	}
 
-- 
cgit v1.2.3


From 0fa0ebbf15addc1be8f73325d809c8547a9de304 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:06 -0800
Subject: irq: allocate irq_desc_ptrs array based on nr_irqs

Impact: allocate irq_desc_ptrs in preparation for making it variable-sized.

This addresses this memory usage bump when NR_CPUS bumped from 128 to 4096:

    34816   +229376    264192  +658%  irq_desc_ptrs(.data.read_mostly)

The patch is split into two parts, the first simply allocates the
irq_desc_ptrs array.  Then next will deal with making it variable.
This is only when CONFIG_SPARSE_IRQS=y.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/irq/handle.c    | 11 +++++++++--
 kernel/irq/internals.h |  7 +++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'kernel/irq')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index fd1ef16252f..d0b8f7e7279 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -17,6 +17,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
+#include <linux/bootmem.h>
 
 #include "internals.h"
 
@@ -110,7 +111,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
  */
 DEFINE_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+struct irq_desc **irq_desc_ptrs __read_mostly;
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS_LEGACY-1] = {
@@ -137,6 +138,9 @@ int __init early_irq_init(void)
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
+	/* allocate irq_desc_ptrs array based on nr_irqs */
+	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy[i];
@@ -153,7 +157,10 @@ int __init early_irq_init(void)
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return (irq < nr_irqs) ? irq_desc_ptrs[irq] : NULL;
+	if (irq_desc_ptrs && irq < nr_irqs)
+		return irq_desc_ptrs[irq];
+
+	return NULL;
 }
 
 struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index e6d0a43cc12..40416a81a0f 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
 extern spinlock_t sparse_irq_lock;
+
+#ifdef CONFIG_SPARSE_IRQ
+/* irq_desc_ptrs allocated at boot time */
+extern struct irq_desc **irq_desc_ptrs;
+#else
+/* irq_desc_ptrs is a fixed size array */
 extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+#endif
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
-- 
cgit v1.2.3


From 9332fccdedf8e09448f3b69b624211ae879f6c45 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:07 -0800
Subject: irq: initialize nr_irqs based on nr_cpu_ids

Impact: Reduce memory usage.

This is the second half of the changes to make the irq_desc_ptrs be
variable sized based on nr_cpu_ids.  This is done by adding a new
"max_nr_irqs" macro to irq_vectors.h (and a dummy in irqnr.h) to
return a max NR_IRQS value based on NR_CPUS or nr_cpu_ids.

This necessitated moving the define of MAX_IO_APICS to a separate
file (asm/apicnum.h) so it could be included without the baggage
of the other asm/apicdef.h declarations.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 arch/x86/include/asm/apicdef.h     |  8 ++------
 arch/x86/include/asm/apicnum.h     | 12 ++++++++++++
 arch/x86/include/asm/irq_vectors.h | 16 +++++++++++-----
 include/linux/irqnr.h              |  7 +++++++
 kernel/irq/handle.c                |  3 +++
 5 files changed, 35 insertions(+), 11 deletions(-)
 create mode 100644 arch/x86/include/asm/apicnum.h

(limited to 'kernel/irq')

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 63134e31e8b..1a6454ef7f6 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -132,12 +132,8 @@
 #define APIC_BASE_MSR	0x800
 #define X2APIC_ENABLE	(1UL << 10)
 
-#ifdef CONFIG_X86_32
-# define MAX_IO_APICS 64
-#else
-# define MAX_IO_APICS 128
-# define MAX_LOCAL_APIC 32768
-#endif
+/* get MAX_IO_APICS */
+#include <asm/apicnum.h>
 
 /*
  * All x86-64 systems are xAPIC compatible.
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 00000000000..82f613c607c
--- /dev/null
+++ b/arch/x86/include/asm/apicnum.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f7ff65032b9..602361ad0e7 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -105,6 +105,8 @@
 
 #if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
 
+#include <asm/apicnum.h>	/* need MAX_IO_APICS */
+
 #ifndef CONFIG_SPARSE_IRQ
 # if NR_CPUS < MAX_IO_APICS
 #  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
@@ -112,11 +114,15 @@
 #  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
 # endif
 #else
-# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
-#  define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
+
+/* defined as a macro so nr_irqs = max_nr_irqs(nr_cpu_ids) can be used */
+# define max_nr_irqs(nr_cpus)				\
+	((8 * nr_cpus) > (32 * MAX_IO_APICS) ?		\
+		(NR_VECTORS + (8 * NR_CPUS)) :		\
+		(NR_VECTORS + (32 * MAX_IO_APICS)))	\
+
+# define NR_IRQS max_nr_irqs(NR_CPUS)
+
 #endif
 
 #elif defined(CONFIG_X86_VOYAGER)
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 86af92e9e84..de66e4e1040 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -20,11 +20,18 @@
 
 # define for_each_irq_desc_reverse(irq, desc)                          \
 	for (irq = nr_irqs - 1; irq >= 0; irq--)
+
 #else /* CONFIG_GENERIC_HARDIRQS */
 
+#include <asm/irq_vectors.h>	/* need possible max_nr_irqs() */
+
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
 
+# ifndef max_nr_irqs
+#  define max_nr_irqs(nr_cpus)	NR_IRQS
+# endif
+
 # define for_each_irq_desc(irq, desc)					\
 	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
 	     irq++, desc = irq_to_desc(irq))				\
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d0b8f7e7279..ebba7a116f1 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -133,6 +133,9 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	/* initialize nr_irqs based on nr_cpu_ids */
+	nr_irqs = max_nr_irqs(nr_cpu_ids);
+
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
 
 	desc = irq_desc_legacy;
-- 
cgit v1.2.3


From 542d865bbed4ce1f050f586e53cf1cfadda93766 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:07 -0800
Subject: kstat: modify kstat_irqs_legacy to be variable sized

Impact: reduce memory usage.

Allocate kstat_irqs_legacy based on nr_cpu_ids to deal with this
memory usage bump when NR_CPUS bumped from 128 to 4096:

     8192   +253952    262144 +3100%  kstat_irqs_legacy(.bss)

This is only when CONFIG_SPARSE_IRQS=y.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/irq/handle.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'kernel/irq')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index ebba7a116f1..b39f32ac8f8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -124,8 +124,7 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
 	}
 };
 
-/* FIXME: use bootmem alloc ...*/
-static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
+static unsigned int *kstat_irqs_legacy;
 
 int __init early_irq_init(void)
 {
@@ -144,9 +143,14 @@ int __init early_irq_init(void)
 	/* allocate irq_desc_ptrs array based on nr_irqs */
 	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
 
+	/* allocate based on nr_cpu_ids */
+	/* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
+	kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
+					  sizeof(int));
+
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
-		desc[i].kstat_irqs = kstat_irqs_legacy[i];
+		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		init_alloc_desc_masks(&desc[i], 0, true);
 		irq_desc_ptrs[i] = desc + i;
-- 
cgit v1.2.3


From 92296c6d6e908c35fca287a21af27be814af9c75 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sun, 11 Jan 2009 09:22:58 -0800
Subject: cpumask, irq: non-x86 build failures

Ingo Molnar wrote:

> All non-x86 architectures fail to build:
>
> In file included from /home/mingo/tip/include/linux/random.h:11,
>                  from /home/mingo/tip/include/linux/stackprotector.h:6,
>                  from /home/mingo/tip/init/main.c:17:
> /home/mingo/tip/include/linux/irqnr.h:26:63: error: asm/irq_vectors.h: No such file or directory

Do not include asm/irq_vectors.h in generic code - it's not available
on all architectures.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/apicdef.h | 8 ++++++--
 include/linux/irqnr.h          | 6 ------
 kernel/irq/handle.c            | 5 +++++
 3 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'kernel/irq')

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 1a6454ef7f6..63134e31e8b 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -132,8 +132,12 @@
 #define APIC_BASE_MSR	0x800
 #define X2APIC_ENABLE	(1UL << 10)
 
-/* get MAX_IO_APICS */
-#include <asm/apicnum.h>
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
 
 /*
  * All x86-64 systems are xAPIC compatible.
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index de66e4e1040..887477bc2ab 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -23,15 +23,9 @@
 
 #else /* CONFIG_GENERIC_HARDIRQS */
 
-#include <asm/irq_vectors.h>	/* need possible max_nr_irqs() */
-
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
 
-# ifndef max_nr_irqs
-#  define max_nr_irqs(nr_cpus)	NR_IRQS
-# endif
-
 # define for_each_irq_desc(irq, desc)					\
 	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
 	     irq++, desc = irq_to_desc(irq))				\
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index b39f32ac8f8..04d3e46031e 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -58,6 +58,11 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
+
+#ifndef max_nr_irqs
+#define max_nr_irqs(nr_cpus)	NR_IRQS
+#endif
+
 static struct irq_desc irq_desc_init = {
 	.irq	    = -1,
 	.status	    = IRQ_DISABLED,
-- 
cgit v1.2.3


From 4a046d1754ee6ebb6f399696805ed61ea0444d4c Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Mon, 12 Jan 2009 17:39:24 -0800
Subject: x86: arch_probe_nr_irqs

Impact: save RAM with large NR_CPUS, get smaller nr_irqs

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Mike Travis <travis@sgi.com>
---
 arch/x86/include/asm/irq_vectors.h |  7 ++-----
 arch/x86/kernel/io_apic.c          | 16 ++++++++++++++++
 include/linux/interrupt.h          |  1 +
 kernel/irq/handle.c                |  9 ++-------
 kernel/softirq.c                   |  5 +++++
 5 files changed, 26 insertions(+), 12 deletions(-)

(limited to 'kernel/irq')

diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 602361ad0e7..a16a2ab2b42 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -115,14 +115,11 @@
 # endif
 #else
 
-/* defined as a macro so nr_irqs = max_nr_irqs(nr_cpu_ids) can be used */
-# define max_nr_irqs(nr_cpus)				\
-	((8 * nr_cpus) > (32 * MAX_IO_APICS) ?		\
+# define NR_IRQS					\
+	((8 * NR_CPUS) > (32 * MAX_IO_APICS) ?		\
 		(NR_VECTORS + (8 * NR_CPUS)) :		\
 		(NR_VECTORS + (32 * MAX_IO_APICS)))	\
 
-# define NR_IRQS max_nr_irqs(NR_CPUS)
-
 #endif
 
 #elif defined(CONFIG_X86_VOYAGER)
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index ae80638012d..157986916cd 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3850,6 +3850,22 @@ void __init probe_nr_irqs_gsi(void)
 		nr_irqs_gsi = nr;
 }
 
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+	int nr;
+
+	nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ?
+		(NR_VECTORS + (8 * nr_cpu_ids)) :
+		(NR_VECTORS + (32 * nr_ioapics)));
+
+	if (nr < nr_irqs && nr > nr_irqs_gsi)
+		nr_irqs = nr;
+
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 9127f6b51a3..472f11765f6 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -467,6 +467,7 @@ int show_interrupts(struct seq_file *p, void *v);
 struct irq_desc;
 
 extern int early_irq_init(void);
+extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
 extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 04d3e46031e..375d68cd5bf 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -59,10 +59,6 @@ EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
 
-#ifndef max_nr_irqs
-#define max_nr_irqs(nr_cpus)	NR_IRQS
-#endif
-
 static struct irq_desc irq_desc_init = {
 	.irq	    = -1,
 	.status	    = IRQ_DISABLED,
@@ -137,9 +133,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
-	/* initialize nr_irqs based on nr_cpu_ids */
-	nr_irqs = max_nr_irqs(nr_cpu_ids);
-
+	 /* initialize nr_irqs based on nr_cpu_ids */
+	arch_probe_nr_irqs();
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
 
 	desc = irq_desc_legacy;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8..0365b4899a3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -795,6 +795,11 @@ int __init __weak early_irq_init(void)
 	return 0;
 }
 
+int __init __weak arch_probe_nr_irqs(void)
+{
+	return 0;
+}
+
 int __init __weak arch_early_irq_init(void)
 {
 	return 0;
-- 
cgit v1.2.3