Re: [PATCH v3 2/7] mm/gup: add gup trace points

[Shi, Yang]

On 12/8/2015 12:25 PM, Steven Rostedt wrote:
> On Tue,  8 Dec 2015 11:39:50 -0800
> Yang Shi <yang.shi@xxxxxxxxxx> wrote:
>
> > For slow version, just add trace point for raw __get_user_pages since all
> > slow variants call it to do the real work finally.
> >
> > Signed-off-by: Yang Shi <yang.shi@xxxxxxxxxx>
> > ---
> >   mm/gup.c | 8 ++++++++
> >   1 file changed, 8 insertions(+)
> >
> > diff --git a/mm/gup.c b/mm/gup.c
> > index deafa2c..44f05c9 100644
> > --- a/mm/gup.c
> > +++ b/mm/gup.c
> > @@ -18,6 +18,9 @@
> >
> >   #include "internal.h"
> >
> > +#define CREATE_TRACE_POINTS
> > +#include <trace/events/gup.h>
> > +
> >   static struct page *no_page_table(struct vm_area_struct *vma,
> >   		unsigned int flags)
> >   {
> > @@ -462,6 +465,8 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
> >   	if (!nr_pages)
> >   		return 0;
> >
> > +	trace_gup_get_user_pages(start, nr_pages);
> > +
> >   	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
> >
> >   	/*
> > @@ -599,6 +604,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
> >   	if (!(vm_flags & vma->vm_flags))
> >   		return -EFAULT;
> >
> > +	trace_gup_fixup_user_fault(address);
> >   	ret = handle_mm_fault(mm, vma, address, fault_flags);
> >   	if (ret & VM_FAULT_ERROR) {
> >   		if (ret & VM_FAULT_OOM)
> > @@ -1340,6 +1346,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> >   					start, len)))
> >   		return 0;
> >
> > +	trace_gup_get_user_pages_fast(start, (unsigned long) nr_pages);
>
> typecast shouldn't be needed. But I'm wondering, it would save space in
> the ring buffer if we used unsigend int instead of long. Will nr_pages
> ever be bigger than 4 billion?

The "unsigned long" comes from get_user_pages() definition, I'm not 
quite sure why "unsigned long" is used. The fast version uses int (I 
guess unsigned int sounds better since it will not go negative).

"unsigned int" could cover 0xffffffff pages (almost 16TB), it sounds 
good enough in the most use case to me. In my test, just 1 page is 
passed to nr_pages in the most cases.

Thanks,
Yang

> -- Steve
>
> > +
> >   	/*
> >   	 * Disable interrupts.  We use the nested form as we can already have
> >   	 * interrupts disabled by get_futex_key.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/