diff mbox series

[2/5] cpumask: Introduce for_each_cpu_andnot()

Message ID 20220816180727.387807-3-vschneid@redhat.com (mailing list archive)
State Not Applicable
Headers show
Series cpumask, sched/topology: NUMA-aware CPU spreading interface | expand

Commit Message

Valentin Schneider Aug. 16, 2022, 6:07 p.m. UTC
for_each_cpu_and() is very convenient as it saves having to allocate a
temporary cpumask to store the result of cpumask_and(). The same issue
applies to cpumask_andnot() which doesn't actually need temporary storage
for iteration purposes.

Following what has been done for for_each_cpu_and(), introduce
for_each_cpu_andnot().

Signed-off-by: Valentin Schneider <vschneid@redhat.com>
---
 include/linux/cpumask.h | 32 ++++++++++++++++++++++++++++++++
 lib/cpumask.c           | 19 +++++++++++++++++++
 2 files changed, 51 insertions(+)

Comments

Yury Norov Aug. 16, 2022, 10:24 p.m. UTC | #1
On Tue, Aug 16, 2022 at 07:07:24PM +0100, Valentin Schneider wrote:
> for_each_cpu_and() is very convenient as it saves having to allocate a
> temporary cpumask to store the result of cpumask_and(). The same issue
> applies to cpumask_andnot() which doesn't actually need temporary storage
> for iteration purposes.
> 
> Following what has been done for for_each_cpu_and(), introduce
> for_each_cpu_andnot().
> 
> Signed-off-by: Valentin Schneider <vschneid@redhat.com>
> ---
>  include/linux/cpumask.h | 32 ++++++++++++++++++++++++++++++++
>  lib/cpumask.c           | 19 +++++++++++++++++++
>  2 files changed, 51 insertions(+)
> 
> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
> index fe29ac7cc469..a8b2ca160e57 100644
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -157,6 +157,13 @@ static inline unsigned int cpumask_next_and(int n,
>  	return n+1;
>  }
>  
> +static inline unsigned int cpumask_next_andnot(int n,
> +					    const struct cpumask *srcp,
> +					    const struct cpumask *andp)
> +{
> +	return n+1;
> +}
> +

It looks like the patch is not based on top of 6.0, where UP cpumask
operations were fixed.  Can you please rebase?

Thanks,
Yury

>  static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask,
>  					     int start, bool wrap)
>  {
> @@ -194,6 +201,8 @@ static inline int cpumask_any_distribute(const struct cpumask *srcp)
>  	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start))
>  #define for_each_cpu_and(cpu, mask1, mask2)	\
>  	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2)
> +#define for_each_cpu_andnot(cpu, mask1, mask2)	\
> +	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2)
>  #else
>  /**
>   * cpumask_first - get the first cpu in a cpumask
> @@ -259,6 +268,9 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
>  }
>  
>  int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
> +int __pure cpumask_next_andnot(int n,
> +			       const struct cpumask *src1p,
> +			       const struct cpumask *src2p);
>  int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
>  unsigned int cpumask_local_spread(unsigned int i, int node);
>  int cpumask_any_and_distribute(const struct cpumask *src1p,
> @@ -324,6 +336,26 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool
>  	for ((cpu) = -1;						\
>  		(cpu) = cpumask_next_and((cpu), (mask1), (mask2)),	\
>  		(cpu) < nr_cpu_ids;)
> +
> +/**
> + * for_each_cpu_andnot - iterate over every cpu in one mask but not in another
> + * @cpu: the (optionally unsigned) integer iterator
> + * @mask1: the first cpumask pointer
> + * @mask2: the second cpumask pointer
> + *
> + * This saves a temporary CPU mask in many places.  It is equivalent to:
> + *	struct cpumask tmp;
> + *	cpumask_andnot(&tmp, &mask1, &mask2);
> + *	for_each_cpu(cpu, &tmp)
> + *		...
> + *
> + * After the loop, cpu is >= nr_cpu_ids.
> + */
> +#define for_each_cpu_andnot(cpu, mask1, mask2)				\
> +	for ((cpu) = -1;						\
> +		(cpu) = cpumask_next_andnot((cpu), (mask1), (mask2)),	\
> +		(cpu) < nr_cpu_ids;)
> +
>  #endif /* SMP */
>  
>  #define CPU_BITS_NONE						\
> diff --git a/lib/cpumask.c b/lib/cpumask.c
> index a971a82d2f43..6896ff4a08fd 100644
> --- a/lib/cpumask.c
> +++ b/lib/cpumask.c
> @@ -42,6 +42,25 @@ int cpumask_next_and(int n, const struct cpumask *src1p,
>  }
>  EXPORT_SYMBOL(cpumask_next_and);
>  
> +/**
> + * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p
> + * @n: the cpu prior to the place to search (ie. return will be > @n)
> + * @src1p: the first cpumask pointer
> + * @src2p: the second cpumask pointer
> + *
> + * Returns >= nr_cpu_ids if no further cpus set in *src1p & ~*src2p.
> + */
> +int cpumask_next_andnot(int n, const struct cpumask *src1p,
> +		     const struct cpumask *src2p)
> +{
> +	/* -1 is a legal arg here. */
> +	if (n != -1)
> +		cpumask_check(n);
> +	return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p),
> +		nr_cpumask_bits, n + 1);
> +}
> +EXPORT_SYMBOL(cpumask_next_andnot);
> +
>  /**
>   * cpumask_any_but - return a "random" in a cpumask, but not this one.
>   * @mask: the cpumask to search
> -- 
> 2.31.1
Valentin Schneider Aug. 17, 2022, 10:09 a.m. UTC | #2
On 16/08/22 15:24, Yury Norov wrote:
> On Tue, Aug 16, 2022 at 07:07:24PM +0100, Valentin Schneider wrote:
>> for_each_cpu_and() is very convenient as it saves having to allocate a
>> temporary cpumask to store the result of cpumask_and(). The same issue
>> applies to cpumask_andnot() which doesn't actually need temporary storage
>> for iteration purposes.
>>
>> Following what has been done for for_each_cpu_and(), introduce
>> for_each_cpu_andnot().
>>
>> Signed-off-by: Valentin Schneider <vschneid@redhat.com>
>> ---
>>  include/linux/cpumask.h | 32 ++++++++++++++++++++++++++++++++
>>  lib/cpumask.c           | 19 +++++++++++++++++++
>>  2 files changed, 51 insertions(+)
>>
>> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
>> index fe29ac7cc469..a8b2ca160e57 100644
>> --- a/include/linux/cpumask.h
>> +++ b/include/linux/cpumask.h
>> @@ -157,6 +157,13 @@ static inline unsigned int cpumask_next_and(int n,
>>      return n+1;
>>  }
>>
>> +static inline unsigned int cpumask_next_andnot(int n,
>> +					    const struct cpumask *srcp,
>> +					    const struct cpumask *andp)
>> +{
>> +	return n+1;
>> +}
>> +
>
> It looks like the patch is not based on top of 6.0, where UP cpumask
> operations were fixed.  Can you please rebase?
>

Right, this is based on tip/sched/core, I'll rebase it. Sorry about that!
diff mbox series

Patch

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index fe29ac7cc469..a8b2ca160e57 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -157,6 +157,13 @@  static inline unsigned int cpumask_next_and(int n,
 	return n+1;
 }
 
+static inline unsigned int cpumask_next_andnot(int n,
+					    const struct cpumask *srcp,
+					    const struct cpumask *andp)
+{
+	return n+1;
+}
+
 static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask,
 					     int start, bool wrap)
 {
@@ -194,6 +201,8 @@  static inline int cpumask_any_distribute(const struct cpumask *srcp)
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start))
 #define for_each_cpu_and(cpu, mask1, mask2)	\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2)
+#define for_each_cpu_andnot(cpu, mask1, mask2)	\
+	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2)
 #else
 /**
  * cpumask_first - get the first cpu in a cpumask
@@ -259,6 +268,9 @@  static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 }
 
 int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
+int __pure cpumask_next_andnot(int n,
+			       const struct cpumask *src1p,
+			       const struct cpumask *src2p);
 int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
 unsigned int cpumask_local_spread(unsigned int i, int node);
 int cpumask_any_and_distribute(const struct cpumask *src1p,
@@ -324,6 +336,26 @@  extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool
 	for ((cpu) = -1;						\
 		(cpu) = cpumask_next_and((cpu), (mask1), (mask2)),	\
 		(cpu) < nr_cpu_ids;)
+
+/**
+ * for_each_cpu_andnot - iterate over every cpu in one mask but not in another
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask1: the first cpumask pointer
+ * @mask2: the second cpumask pointer
+ *
+ * This saves a temporary CPU mask in many places.  It is equivalent to:
+ *	struct cpumask tmp;
+ *	cpumask_andnot(&tmp, &mask1, &mask2);
+ *	for_each_cpu(cpu, &tmp)
+ *		...
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_andnot(cpu, mask1, mask2)				\
+	for ((cpu) = -1;						\
+		(cpu) = cpumask_next_andnot((cpu), (mask1), (mask2)),	\
+		(cpu) < nr_cpu_ids;)
+
 #endif /* SMP */
 
 #define CPU_BITS_NONE						\
diff --git a/lib/cpumask.c b/lib/cpumask.c
index a971a82d2f43..6896ff4a08fd 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -42,6 +42,25 @@  int cpumask_next_and(int n, const struct cpumask *src1p,
 }
 EXPORT_SYMBOL(cpumask_next_and);
 
+/**
+ * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set in *src1p & ~*src2p.
+ */
+int cpumask_next_andnot(int n, const struct cpumask *src1p,
+		     const struct cpumask *src2p)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p),
+		nr_cpumask_bits, n + 1);
+}
+EXPORT_SYMBOL(cpumask_next_andnot);
+
 /**
  * cpumask_any_but - return a "random" in a cpumask, but not this one.
  * @mask: the cpumask to search