[PATCH] [genirq] Expose default irq affinity mask

[PATCH] [genirq] Expose default irq affinity mask

[Max Krasnyansky]

Current IRQ affinity interface does not provide a way to set affinity
for the IRQs that will be allocated/activated in the future.
This patch creates /proc/irq/default_smp_affinity that lets users set
default affinity mask for the newly allocated IRQs. Changing default
does not affect affinity masks for the currently active IRQs, they
have to be changed explicitly.

Signed-off-by: Max Krasnyansky <maxk@qualcomm.com>
---
 arch/alpha/kernel/irq.c |    5 +--
 include/linux/irq.h     |   14 ++++-------
 kernel/irq/manage.c     |   28 +++++++++++++++++++++-
 kernel/irq/proc.c       |   57 ++++++++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 89 insertions(+), 15 deletions(-)

diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index facf82a..c626a82 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -42,8 +42,7 @@ void ack_bad_irq(unsigned int irq)
 #ifdef CONFIG_SMP 
 static char irq_user_affinity[NR_IRQS];
 
-int
-select_smp_affinity(unsigned int irq)
+int irq_select_affinity(unsigned int irq)
 {
 	static int last_cpu;
 	int cpu = last_cpu + 1;
@@ -51,7 +50,7 @@ select_smp_affinity(unsigned int irq)
 	if (!irq_desc[irq].chip->set_affinity || irq_user_affinity[irq])
 		return 1;
 
-	while (!cpu_possible(cpu))
+	while (!cpu_possible(cpu) || !cpu_isset(cpu, irq_default_affinity))
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 176e5e7..8faebf8 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -228,8 +228,11 @@ static inline void set_pending_irq(unsigned int irq, cpumask_t mask)
 
 #endif /* CONFIG_GENERIC_PENDING_IRQ */
 
+extern cpumask_t irq_default_affinity;
+
 extern int irq_set_affinity(unsigned int irq, cpumask_t cpumask);
 extern int irq_can_set_affinity(unsigned int irq);
+extern int irq_select_affinity(unsigned int irq);
 
 #else /* CONFIG_SMP */
 
@@ -243,6 +246,8 @@ static inline int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 
 static inline int irq_can_set_affinity(unsigned int irq) { return 0; }
 
+static inline int irq_select_affinity(unsigned int irq)  { return 0; }
+
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_IRQBALANCE
@@ -253,15 +258,6 @@ static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
 }
 #endif
 
-#ifdef CONFIG_AUTO_IRQ_AFFINITY
-extern int select_smp_affinity(unsigned int irq);
-#else
-static inline int select_smp_affinity(unsigned int irq)
-{
-	return 1;
-}
-#endif
-
 extern int no_irq_affinity;
 
 static inline int irq_balancing_disabled(unsigned int irq)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 438a014..90f9ccc 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -16,6 +16,8 @@
 
 #ifdef CONFIG_SMP
 
+cpumask_t irq_default_affinity = CPU_MASK_ALL;
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -94,6 +96,27 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 	return 0;
 }
 
+#ifndef CONFIG_AUTO_IRQ_AFFINITY
+/**
+ * Generic version of the affinity autoselector.
+ */
+int irq_select_affinity(unsigned int irq)
+{
+	cpumask_t mask;
+
+	if (!irq_can_set_affinity(irq))
+		return 0;
+
+	cpus_and(mask, cpu_online_map, irq_default_affinity);
+
+	irq_desc[irq].affinity = mask;
+	irq_desc[irq].chip->set_affinity(irq, mask);
+
+	set_balance_irq_affinity(irq, mask);
+	return 0;
+}
+#endif
+
 #endif
 
 /**
@@ -376,6 +399,9 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 		} else
 			/* Undo nested disables: */
 			desc->depth = 1;
+
+		/* Set default affinity mask once everything is setup */
+		irq_select_affinity(irq);
 	}
 	/* Reset broken irq detection when installing new handler */
 	desc->irq_count = 0;
@@ -555,8 +581,6 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	action->next = NULL;
 	action->dev_id = dev_id;
 
-	select_smp_affinity(irq);
-
 #ifdef CONFIG_DEBUG_SHIRQ
 	if (irqflags & IRQF_SHARED) {
 		/*
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index c2f2ccb..c20eb52 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -66,13 +66,51 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
 	if (cpus_empty(tmp))
 		/* Special case for empty set - allow the architecture
 		   code to set default SMP affinity. */
-		return select_smp_affinity(irq) ? -EINVAL : full_count;
+		return irq_select_affinity(irq) ? -EINVAL : full_count;
 
 	irq_set_affinity(irq, new_value);
 
 	return full_count;
 }
 
+extern cpumask_t irq_default_affinity;
+
+static int default_affinity_read(char *page, char **start, off_t off,
+				  int count, int *eof, void *data)
+{
+	int len = cpumask_scnprintf(page, count, irq_default_affinity);
+	if (count - len < 2)
+		return -EINVAL;
+	len += sprintf(page + len, "\n");
+	return len;
+}
+
+static int default_affinity_write(struct file *file, const char __user *buffer,
+				   unsigned long count, void *data)
+{
+	unsigned int full_count = count, err;
+	cpumask_t new_value, tmp;
+
+	err = cpumask_parse_user(buffer, count, new_value);
+	if (err)
+		return err;
+
+	if (!is_affinity_mask_valid(new_value))
+		return -EINVAL;
+
+	/*
+	 * Do not allow disabling IRQs completely - it's a too easy
+	 * way to make the system unusable accidentally :-) At least
+	 * one online CPU still has to be targeted.
+	 */
+	cpus_and(tmp, new_value, cpu_online_map);
+	if (cpus_empty(tmp))
+		return -EINVAL;
+
+	irq_default_affinity = new_value;
+
+	return full_count;
+}
 #endif
 
 static int irq_spurious_read(char *page, char **start, off_t off,
@@ -171,6 +209,21 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 		remove_proc_entry(action->dir->name, irq_desc[irq].dir);
 }
 
+void register_default_affinity_proc(void)
+{
+#ifdef CONFIG_SMP
+	struct proc_dir_entry *entry;
+
+	/* create /proc/irq/default_smp_affinity */
+	entry = create_proc_entry("default_smp_affinity", 0600, root_irq_dir);
+	if (entry) {
+		entry->data = NULL;
+		entry->read_proc  = default_affinity_read;
+		entry->write_proc = default_affinity_write;
+	}
+#endif
+}
+
 void init_irq_proc(void)
 {
 	int i;
@@ -180,6 +233,8 @@ void init_irq_proc(void)
 	if (!root_irq_dir)
 		return;
 
+	register_default_affinity_proc();
+
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-- 
1.5.4.5

Re: [PATCH] [genirq] Expose default irq affinity mask

[Randy Dunlap]

On Fri, 23 May 2008 12:46:35 -0700 Max Krasnyansky wrote:

> Current IRQ affinity interface does not provide a way to set affinity
> for the IRQs that will be allocated/activated in the future.
> This patch creates /proc/irq/default_smp_affinity that lets users set
> default affinity mask for the newly allocated IRQs. Changing default
> does not affect affinity masks for the currently active IRQs, they
> have to be changed explicitly.

Documentation, perhaps an update to Documentation/filesystems/proc.txt ?

> Signed-off-by: Max Krasnyansky <maxk@qualcomm.com>
> ---
>  arch/alpha/kernel/irq.c |    5 +--
>  include/linux/irq.h     |   14 ++++-------
>  kernel/irq/manage.c     |   28 +++++++++++++++++++++-
>  kernel/irq/proc.c       |   57 ++++++++++++++++++++++++++++++++++++++++++++++-
>  4 files changed, 89 insertions(+), 15 deletions(-)
> 
> diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
> index 438a014..90f9ccc 100644
> --- a/kernel/irq/manage.c
> +++ b/kernel/irq/manage.c
> @@ -16,6 +16,8 @@
>  
>  #ifdef CONFIG_SMP
>  
> +cpumask_t irq_default_affinity = CPU_MASK_ALL;
> +
>  /**
>   *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
>   *	@irq: interrupt number to wait for
> @@ -94,6 +96,27 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
>  	return 0;
>  }
>  
> +#ifndef CONFIG_AUTO_IRQ_AFFINITY
> +/**
> + * Generic version of the affinity autoselector.
> + */

Please don't use /** as the beginning of a comment block unless that
comment block is in kernel-doc format (this one is not).

> +int irq_select_affinity(unsigned int irq)
> +{
> +	cpumask_t mask;
> +
> +	if (!irq_can_set_affinity(irq))
> +		return 0;
> +
> +	cpus_and(mask, cpu_online_map, irq_default_affinity);
> +
> +	irq_desc[irq].affinity = mask;
> +	irq_desc[irq].chip->set_affinity(irq, mask);
> +
> +	set_balance_irq_affinity(irq, mask);
> +	return 0;
> +}
> +#endif


---
~Randy

Re: [PATCH] [genirq] Expose default irq affinity mask

[Max Krasnyanskiy]

Randy Dunlap wrote:
> On Fri, 23 May 2008 12:46:35 -0700 Max Krasnyansky wrote:
> 
>> Current IRQ affinity interface does not provide a way to set affinity
>> for the IRQs that will be allocated/activated in the future.
>> This patch creates /proc/irq/default_smp_affinity that lets users set
>> default affinity mask for the newly allocated IRQs. Changing default
>> does not affect affinity masks for the currently active IRQs, they
>> have to be changed explicitly.
> 
> Documentation, perhaps an update to Documentation/filesystems/proc.txt ?
Absolutely. I wanted to see if it gets accepted first.

> 
>> Signed-off-by: Max Krasnyansky <maxk@qualcomm.com>
>> ---
>>  arch/alpha/kernel/irq.c |    5 +--
>>  include/linux/irq.h     |   14 ++++-------
>>  kernel/irq/manage.c     |   28 +++++++++++++++++++++-
>>  kernel/irq/proc.c       |   57 ++++++++++++++++++++++++++++++++++++++++++++++-
>>  4 files changed, 89 insertions(+), 15 deletions(-)
>>
>> diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
>> index 438a014..90f9ccc 100644
>> --- a/kernel/irq/manage.c
>> +++ b/kernel/irq/manage.c
>> @@ -16,6 +16,8 @@
>>  
>>  #ifdef CONFIG_SMP
>>  
>> +cpumask_t irq_default_affinity = CPU_MASK_ALL;
>> +
>>  /**
>>   *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
>>   *	@irq: interrupt number to wait for
>> @@ -94,6 +96,27 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
>>  	return 0;
>>  }
>>  
>> +#ifndef CONFIG_AUTO_IRQ_AFFINITY
>> +/**
>> + * Generic version of the affinity autoselector.
>> + */
> 
> Please don't use /** as the beginning of a comment block unless that
> comment block is in kernel-doc format (this one is not).

Oops, my bad. Did it again. Will fix.

Max

Re: [PATCH] [genirq] Expose default irq affinity mask

[Paul Jackson]

Max, replying to Randy:
> > Documentation, perhaps an update to Documentation/filesystems/proc.txt ?
> Absolutely. I wanted to see if it gets accepted first.

For new features such as this, documentation is helpful in reviewing.

(For me at least, documentation is even helpful in -writing- the code,
as I find that if I can't explain something in words clearly and
accurately, then my code is probably confused as well.  However, I'm
obviously weird, and not just in this regard.)

>From what I can tell, it's ok.  I look forward to seeing the Documentation,
and will review it again at that time.

-- 
                  I won't rest till it's the best ...
                  Programmer, Linux Scalability
                  Paul Jackson <pj@sgi.com> 1.940.382.4214

Re: [PATCH] [genirq] Expose default irq affinity mask

[Max Krasnyanskiy]

Paul Jackson wrote:
> Max, replying to Randy:
>>> Documentation, perhaps an update to Documentation/filesystems/proc.txt ?
>> Absolutely. I wanted to see if it gets accepted first.
> 
> For new features such as this, documentation is helpful in reviewing.
> 
> (For me at least, documentation is even helpful in -writing- the code,
> as I find that if I can't explain something in words clearly and
> accurately, then my code is probably confused as well.  However, I'm
> obviously weird, and not just in this regard.)
> 
>>From what I can tell, it's ok.  I look forward to seeing the Documentation,
> and will review it again at that time.
> 

There is not going to be whole a lot of documentation for this. Basically the 
commit comment is what will be in the documentation.
In other words I do not think it'll help you with the review.

Max

Re: [PATCH] [genirq] Expose default irq affinity mask

[Paul Jackson]

> In other words I do not think it'll help you with the review.

I really do prefer to encourage people to include the Doc changes
in their submitted patches.  It does make it easier to review,
and the Doc changes are part of what needs to be reviewed.

I will do my best to complete my review, and I will most likely
ack this patch, once it is complete.

-- 
                  I won't rest till it's the best ...
                  Programmer, Linux Scalability
                  Paul Jackson <pj@sgi.com> 1.940.382.4214