mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [RESEND PATCH v3] tracing: Allocate mask_str buffer dynamically
@ 2017-11-29  4:42 changbin.du
  2017-11-30  3:12 ` Steven Rostedt
  0 siblings, 1 reply; 3+ messages in thread
From: changbin.du @ 2017-11-29  4:42 UTC (permalink / raw)
  To: rostedt; +Cc: mingo, linux-kernel, Changbin Du

From: Changbin Du <changbin.du@intel.com>

The default NR_CPUS can be very large, but actual possible nr_cpu_ids
usually is very small. For my x86 distribution, the NR_CPUS is 8192 and
nr_cpu_ids is 4. About 2 pages are wasted.

Most machines don't have so many CPUs, so define a array with NR_CPUS
just wastes memory. So let's allocate the buffer dynamically when need.

The exact buffer size should be:
  DIV_ROUND_UP(nr_cpu_ids, 4) + nr_cpu_ids/32 + 2;

Example output:
  ff,ffffffff

With this change, the mutext tracing_cpumask_update_lock also can be
removed now, which was used to protect mask_str.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

---
v3:
  - remove tracing_cpumask_update_lock which was used to protect mask_str. (Rostedt)
v2:
  - remove 'static' declaration.
  - fix buffer size.
---
 kernel/trace/trace.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 73e67b6..6750d05 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4178,37 +4178,30 @@ static const struct file_operations show_traces_fops = {
 	.llseek		= seq_lseek,
 };
 
-/*
- * The tracer itself will not take this lock, but still we want
- * to provide a consistent cpumask to user-space:
- */
-static DEFINE_MUTEX(tracing_cpumask_update_lock);
-
-/*
- * Temporary storage for the character representation of the
- * CPU bitmask (and one more byte for the newline):
- */
-static char mask_str[NR_CPUS + 1];
-
 static ssize_t
 tracing_cpumask_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
 	struct trace_array *tr = file_inode(filp)->i_private;
+	char *mask_str;
 	int len;
 
-	mutex_lock(&tracing_cpumask_update_lock);
+	/* Bitmap, ',' and two more bytes for the newline and '\0'. */
+	len = DIV_ROUND_UP(nr_cpu_ids, 4) + nr_cpu_ids/32 + 2;
+	mask_str = kmalloc(len, GFP_KERNEL);
+	if (!mask_str)
+		return -ENOMEM;
 
-	len = snprintf(mask_str, count, "%*pb\n",
+	len = snprintf(mask_str, len, "%*pb\n",
 		       cpumask_pr_args(tr->tracing_cpumask));
 	if (len >= count) {
 		count = -EINVAL;
 		goto out_err;
 	}
-	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
 
 out_err:
-	mutex_unlock(&tracing_cpumask_update_lock);
+	kfree(mask_str);
 
 	return count;
 }
@@ -4228,8 +4221,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	if (err)
 		goto err_unlock;
 
-	mutex_lock(&tracing_cpumask_update_lock);
-
 	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	for_each_tracing_cpu(cpu) {
@@ -4252,8 +4243,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	local_irq_enable();
 
 	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
-	mutex_unlock(&tracing_cpumask_update_lock);
 	free_cpumask_var(tracing_cpumask_new);
 
 	return count;
-- 
2.7.4

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [RESEND PATCH v3] tracing: Allocate mask_str buffer dynamically
  2017-11-29  4:42 [RESEND PATCH v3] tracing: Allocate mask_str buffer dynamically changbin.du
@ 2017-11-30  3:12 ` Steven Rostedt
  2017-11-30  3:29   ` Du, Changbin
  0 siblings, 1 reply; 3+ messages in thread
From: Steven Rostedt @ 2017-11-30  3:12 UTC (permalink / raw)
  To: changbin.du; +Cc: mingo, linux-kernel

On Wed, 29 Nov 2017 12:42:45 +0800
changbin.du@intel.com wrote:

> From: Changbin Du <changbin.du@intel.com>
> 
> The default NR_CPUS can be very large, but actual possible nr_cpu_ids
> usually is very small. For my x86 distribution, the NR_CPUS is 8192 and
> nr_cpu_ids is 4. About 2 pages are wasted.
> 
> Most machines don't have so many CPUs, so define a array with NR_CPUS
> just wastes memory. So let's allocate the buffer dynamically when need.
> 
> The exact buffer size should be:
>   DIV_ROUND_UP(nr_cpu_ids, 4) + nr_cpu_ids/32 + 2;
> 
> Example output:
>   ff,ffffffff

Um, what if there's more than 64 CPUs, where I have booted several
boxes that have more. There's going to be more than 1 comma.

> 
> With this change, the mutext tracing_cpumask_update_lock also can be
> removed now, which was used to protect mask_str.
> 
> Signed-off-by: Changbin Du <changbin.du@intel.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> 
> ---
> v3:
>   - remove tracing_cpumask_update_lock which was used to protect mask_str. (Rostedt)
> v2:
>   - remove 'static' declaration.
>   - fix buffer size.
> ---
>  kernel/trace/trace.c | 29 +++++++++--------------------
>  1 file changed, 9 insertions(+), 20 deletions(-)
> 
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index 73e67b6..6750d05 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -4178,37 +4178,30 @@ static const struct file_operations show_traces_fops = {
>  	.llseek		= seq_lseek,
>  };
>  
> -/*
> - * The tracer itself will not take this lock, but still we want
> - * to provide a consistent cpumask to user-space:
> - */
> -static DEFINE_MUTEX(tracing_cpumask_update_lock);
> -
> -/*
> - * Temporary storage for the character representation of the
> - * CPU bitmask (and one more byte for the newline):
> - */
> -static char mask_str[NR_CPUS + 1];
> -
>  static ssize_t
>  tracing_cpumask_read(struct file *filp, char __user *ubuf,
>  		     size_t count, loff_t *ppos)
>  {
>  	struct trace_array *tr = file_inode(filp)->i_private;
> +	char *mask_str;
>  	int len;
>  
> -	mutex_lock(&tracing_cpumask_update_lock);
> +	/* Bitmap, ',' and two more bytes for the newline and '\0'. */
> +	len = DIV_ROUND_UP(nr_cpu_ids, 4) + nr_cpu_ids/32 + 2;

This is broken. Instead do:

	len = snprintf(NULL, 0, "%*pb\n",
		       cpumask_pr_args(tr->tracing_cpumask)) + 1;

	mask_str = kmalloc(len, GFP_KERNEL);
	[..]
	len = snprintf(mask_str, len, "%*pb\n",
		       cpumask_pr_args(tr->tracing_cpumask));

-- Steve

> +	mask_str = kmalloc(len, GFP_KERNEL);
> +	if (!mask_str)
> +		return -ENOMEM;
>  
> -	len = snprintf(mask_str, count, "%*pb\n",
> +	len = snprintf(mask_str, len, "%*pb\n",
>  		       cpumask_pr_args(tr->tracing_cpumask));
>  	if (len >= count) {
>  		count = -EINVAL;
>  		goto out_err;
>  	}
> -	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
> +	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
>  
>  out_err:
> -	mutex_unlock(&tracing_cpumask_update_lock);
> +	kfree(mask_str);
>  
>  	return count;
>  }
> @@ -4228,8 +4221,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
>  	if (err)
>  		goto err_unlock;
>  
> -	mutex_lock(&tracing_cpumask_update_lock);
> -
>  	local_irq_disable();
>  	arch_spin_lock(&tr->max_lock);
>  	for_each_tracing_cpu(cpu) {
> @@ -4252,8 +4243,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
>  	local_irq_enable();
>  
>  	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
> -
> -	mutex_unlock(&tracing_cpumask_update_lock);
>  	free_cpumask_var(tracing_cpumask_new);
>  
>  	return count;

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [RESEND PATCH v3] tracing: Allocate mask_str buffer dynamically
  2017-11-30  3:12 ` Steven Rostedt
@ 2017-11-30  3:29   ` Du, Changbin
  0 siblings, 0 replies; 3+ messages in thread
From: Du, Changbin @ 2017-11-30  3:29 UTC (permalink / raw)
  To: Steven Rostedt; +Cc: changbin.du, mingo, linux-kernel

On Wed, Nov 29, 2017 at 10:12:09PM -0500, Steven Rostedt wrote:
> On Wed, 29 Nov 2017 12:42:45 +0800
> changbin.du@intel.com wrote:
> 
> > From: Changbin Du <changbin.du@intel.com>
> > 
> > The default NR_CPUS can be very large, but actual possible nr_cpu_ids
> > usually is very small. For my x86 distribution, the NR_CPUS is 8192 and
> > nr_cpu_ids is 4. About 2 pages are wasted.
> > 
> > Most machines don't have so many CPUs, so define a array with NR_CPUS
> > just wastes memory. So let's allocate the buffer dynamically when need.
> > 
> > The exact buffer size should be:
> >   DIV_ROUND_UP(nr_cpu_ids, 4) + nr_cpu_ids/32 + 2;
> > 
> > Example output:
> >   ff,ffffffff
> 
> Um, what if there's more than 64 CPUs, where I have booted several
> boxes that have more. There's going to be more than 1 comma.
>
The commas are calculated by formula. (DIV_ROUND_UP(nr_cpu_ids, 4))

> > 
> > With this change, the mutext tracing_cpumask_update_lock also can be
> > removed now, which was used to protect mask_str.
> > 
> > Signed-off-by: Changbin Du <changbin.du@intel.com>
> > Cc: Steven Rostedt <rostedt@goodmis.org>
> > 
> > ---
> > v3:
> >   - remove tracing_cpumask_update_lock which was used to protect mask_str. (Rostedt)
> > v2:
> >   - remove 'static' declaration.
> >   - fix buffer size.
> > ---
> >  kernel/trace/trace.c | 29 +++++++++--------------------
> >  1 file changed, 9 insertions(+), 20 deletions(-)
> > 
> > diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> > index 73e67b6..6750d05 100644
> > --- a/kernel/trace/trace.c
> > +++ b/kernel/trace/trace.c
> > @@ -4178,37 +4178,30 @@ static const struct file_operations show_traces_fops = {
> >  	.llseek		= seq_lseek,
> >  };
> >  
> > -/*
> > - * The tracer itself will not take this lock, but still we want
> > - * to provide a consistent cpumask to user-space:
> > - */
> > -static DEFINE_MUTEX(tracing_cpumask_update_lock);
> > -
> > -/*
> > - * Temporary storage for the character representation of the
> > - * CPU bitmask (and one more byte for the newline):
> > - */
> > -static char mask_str[NR_CPUS + 1];
> > -
> >  static ssize_t
> >  tracing_cpumask_read(struct file *filp, char __user *ubuf,
> >  		     size_t count, loff_t *ppos)
> >  {
> >  	struct trace_array *tr = file_inode(filp)->i_private;
> > +	char *mask_str;
> >  	int len;
> >  
> > -	mutex_lock(&tracing_cpumask_update_lock);
> > +	/* Bitmap, ',' and two more bytes for the newline and '\0'. */
> > +	len = DIV_ROUND_UP(nr_cpu_ids, 4) + nr_cpu_ids/32 + 2;
> 
> This is broken. Instead do:
> 
> 	len = snprintf(NULL, 0, "%*pb\n",
> 		       cpumask_pr_args(tr->tracing_cpumask)) + 1;
> 
> 	mask_str = kmalloc(len, GFP_KERNEL);
> 	[..]
> 	len = snprintf(mask_str, len, "%*pb\n",
> 		       cpumask_pr_args(tr->tracing_cpumask));
> 
> -- Steve
> 
hmm. I never know that snprintf has such usage. This is much better than
calculating it by a formula.

> > +	mask_str = kmalloc(len, GFP_KERNEL);
> > +	if (!mask_str)
> > +		return -ENOMEM;
> >  
> > -	len = snprintf(mask_str, count, "%*pb\n",
> > +	len = snprintf(mask_str, len, "%*pb\n",
> >  		       cpumask_pr_args(tr->tracing_cpumask));
> >  	if (len >= count) {
> >  		count = -EINVAL;
> >  		goto out_err;
> >  	}
> > -	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
> > +	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
> >  
> >  out_err:
> > -	mutex_unlock(&tracing_cpumask_update_lock);
> > +	kfree(mask_str);
> >  
> >  	return count;
> >  }
> > @@ -4228,8 +4221,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
> >  	if (err)
> >  		goto err_unlock;
> >  
> > -	mutex_lock(&tracing_cpumask_update_lock);
> > -
> >  	local_irq_disable();
> >  	arch_spin_lock(&tr->max_lock);
> >  	for_each_tracing_cpu(cpu) {
> > @@ -4252,8 +4243,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
> >  	local_irq_enable();
> >  
> >  	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
> > -
> > -	mutex_unlock(&tracing_cpumask_update_lock);
> >  	free_cpumask_var(tracing_cpumask_new);
> >  
> >  	return count;
> 

-- 
Thanks,
Changbin Du

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2017-11-30  3:36 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-11-29  4:42 [RESEND PATCH v3] tracing: Allocate mask_str buffer dynamically changbin.du
2017-11-30  3:12 ` Steven Rostedt
2017-11-30  3:29   ` Du, Changbin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®