diff mbox series

[5/7] mm/gup: Cleanup next_page handling

Message ID 20230613215346.1022773-6-peterx@redhat.com
State New
Headers
Series mm/gup: Unify hugetlb, speed up thp |

Commit Message

Peter Xu June 13, 2023, 9:53 p.m. UTC 
  The only path that doesn't use generic "**pages" handling is the gate vma.
Make it use the same path, meanwhile tune the next_page label upper to
cover "**pages" handling.  This prepares for THP handling for "**pages".

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/gup.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

Comments

Lorenzo Stoakes June 17, 2023, 7:48 p.m. UTC | #1 
On Tue, Jun 13, 2023 at 05:53:44PM -0400, Peter Xu wrote:
> The only path that doesn't use generic "**pages" handling is the gate vma.
> Make it use the same path, meanwhile tune the next_page label upper to
> cover "**pages" handling.  This prepares for THP handling for "**pages".
>
> Signed-off-by: Peter Xu <peterx@redhat.com>
> ---
>  mm/gup.c | 7 +++----
>  1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/mm/gup.c b/mm/gup.c
> index 8d59ae4554e7..a2d1b3c4b104 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1135,7 +1135,7 @@ static long __get_user_pages(struct mm_struct *mm,
>  			if (!vma && in_gate_area(mm, start)) {
>  				ret = get_gate_page(mm, start & PAGE_MASK,
>  						gup_flags, &vma,
> -						pages ? &pages[i] : NULL);
> +						pages ? &page : NULL);

Good spot... ugh that we handled this differently.

>  				if (ret)
>  					goto out;
>  				ctx.page_mask = 0;

We can drop this line now right? As the new next_page block will duplicate
this.

> @@ -1205,19 +1205,18 @@ static long __get_user_pages(struct mm_struct *mm,
>  				ret = PTR_ERR(page);
>  				goto out;
>  			}
> -
> -			goto next_page;

This is neat, we've already checked if pages != NULL so the if (pages)
block at the new next_page label will not be run.

>  		} else if (IS_ERR(page)) {
>  			ret = PTR_ERR(page);
>  			goto out;
>  		}
> +next_page:
>  		if (pages) {
>  			pages[i] = page;
>  			flush_anon_page(vma, page, start);
>  			flush_dcache_page(page);

I guess there's no harm that we now flush here, though it seems to me to be
superfluous, it's not a big deal I don't think.

>  			ctx.page_mask = 0;
>  		}
> -next_page:
> +
>  		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
>  		if (page_increm > nr_pages)
>  			page_increm = nr_pages;
> --
> 2.40.1
>

Other than that, LGTM,

Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>
Lorenzo Stoakes June 17, 2023, 8 p.m. UTC | #2 
On Sat, Jun 17, 2023 at 08:48:38PM +0100, Lorenzo Stoakes wrote:
> On Tue, Jun 13, 2023 at 05:53:44PM -0400, Peter Xu wrote:
> > The only path that doesn't use generic "**pages" handling is the gate vma.
> > Make it use the same path, meanwhile tune the next_page label upper to
> > cover "**pages" handling.  This prepares for THP handling for "**pages".
> >
> > Signed-off-by: Peter Xu <peterx@redhat.com>
> > ---
> >  mm/gup.c | 7 +++----
> >  1 file changed, 3 insertions(+), 4 deletions(-)
> >
> > diff --git a/mm/gup.c b/mm/gup.c
> > index 8d59ae4554e7..a2d1b3c4b104 100644
> > --- a/mm/gup.c
> > +++ b/mm/gup.c
> > @@ -1135,7 +1135,7 @@ static long __get_user_pages(struct mm_struct *mm,
> >  			if (!vma && in_gate_area(mm, start)) {
> >  				ret = get_gate_page(mm, start & PAGE_MASK,
> >  						gup_flags, &vma,
> > -						pages ? &pages[i] : NULL);
> > +						pages ? &page : NULL);
>
> Good spot... ugh that we handled this differently.
>
> >  				if (ret)
> >  					goto out;
> >  				ctx.page_mask = 0;
>
> We can drop this line now right? As the new next_page block will duplicate
> this.

OK I can see why you left this in given the last patch in the series :)
Please disregard.

>
> > @@ -1205,19 +1205,18 @@ static long __get_user_pages(struct mm_struct *mm,
> >  				ret = PTR_ERR(page);
> >  				goto out;
> >  			}
> > -
> > -			goto next_page;
>
> This is neat, we've already checked if pages != NULL so the if (pages)
> block at the new next_page label will not be run.
>
> >  		} else if (IS_ERR(page)) {
> >  			ret = PTR_ERR(page);
> >  			goto out;
> >  		}
> > +next_page:
> >  		if (pages) {
> >  			pages[i] = page;
> >  			flush_anon_page(vma, page, start);
> >  			flush_dcache_page(page);
>
> I guess there's no harm that we now flush here, though it seems to me to be
> superfluous, it's not a big deal I don't think.
>
> >  			ctx.page_mask = 0;
> >  		}
> > -next_page:
> > +
> >  		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
> >  		if (page_increm > nr_pages)
> >  			page_increm = nr_pages;
> > --
> > 2.40.1
> >
>
> Other than that, LGTM,
>
> Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>
Peter Xu June 19, 2023, 7:18 p.m. UTC | #3 
On Sat, Jun 17, 2023 at 09:00:34PM +0100, Lorenzo Stoakes wrote:
> On Sat, Jun 17, 2023 at 08:48:38PM +0100, Lorenzo Stoakes wrote:
> > On Tue, Jun 13, 2023 at 05:53:44PM -0400, Peter Xu wrote:
> > > The only path that doesn't use generic "**pages" handling is the gate vma.
> > > Make it use the same path, meanwhile tune the next_page label upper to
> > > cover "**pages" handling.  This prepares for THP handling for "**pages".
> > >
> > > Signed-off-by: Peter Xu <peterx@redhat.com>
> > > ---
> > >  mm/gup.c | 7 +++----
> > >  1 file changed, 3 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/mm/gup.c b/mm/gup.c
> > > index 8d59ae4554e7..a2d1b3c4b104 100644
> > > --- a/mm/gup.c
> > > +++ b/mm/gup.c
> > > @@ -1135,7 +1135,7 @@ static long __get_user_pages(struct mm_struct *mm,
> > >  			if (!vma && in_gate_area(mm, start)) {
> > >  				ret = get_gate_page(mm, start & PAGE_MASK,
> > >  						gup_flags, &vma,
> > > -						pages ? &pages[i] : NULL);
> > > +						pages ? &page : NULL);
> >
> > Good spot... ugh that we handled this differently.
> >
> > >  				if (ret)
> > >  					goto out;
> > >  				ctx.page_mask = 0;
> >
> > We can drop this line now right? As the new next_page block will duplicate
> > this.
> 
> OK I can see why you left this in given the last patch in the series :)
> Please disregard.

Yes the other "page_mask=0" will be removed in the next (not last) patch.

> 
> >
> > > @@ -1205,19 +1205,18 @@ static long __get_user_pages(struct mm_struct *mm,
> > >  				ret = PTR_ERR(page);
> > >  				goto out;
> > >  			}
> > > -
> > > -			goto next_page;
> >
> > This is neat, we've already checked if pages != NULL so the if (pages)
> > block at the new next_page label will not be run.

Yes.

> >
> > >  		} else if (IS_ERR(page)) {
> > >  			ret = PTR_ERR(page);
> > >  			goto out;
> > >  		}
> > > +next_page:
> > >  		if (pages) {
> > >  			pages[i] = page;
> > >  			flush_anon_page(vma, page, start);
> > >  			flush_dcache_page(page);
> >
> > I guess there's no harm that we now flush here, though it seems to me to be
> > superfluous, it's not a big deal I don't think.

I'd say GUP on gate vma page should be so rare so yeah I think it shouldn't
be a big deal.  Even iiuc vsyscall=xonly should be the default, so gup may
have already failed on a gate vma page even trying to read-only..

> >
> > >  			ctx.page_mask = 0;
> > >  		}
> > > -next_page:
> > > +
> > >  		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
> > >  		if (page_increm > nr_pages)
> > >  			page_increm = nr_pages;
> > > --
> > > 2.40.1
> > >
> >
> > Other than that, LGTM,
> >
> > Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>

Thanks for looking!
diff mbox series

Patch

diff --git a/mm/gup.c b/mm/gup.c
index 8d59ae4554e7..a2d1b3c4b104 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1135,7 +1135,7 @@  static long __get_user_pages(struct mm_struct *mm,
 			if (!vma && in_gate_area(mm, start)) {
 				ret = get_gate_page(mm, start & PAGE_MASK,
 						gup_flags, &vma,
-						pages ? &pages[i] : NULL);
+						pages ? &page : NULL);
 				if (ret)
 					goto out;
 				ctx.page_mask = 0;
@@ -1205,19 +1205,18 @@  static long __get_user_pages(struct mm_struct *mm,
 				ret = PTR_ERR(page);
 				goto out;
 			}
-
-			goto next_page;
 		} else if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
 			goto out;
 		}
+next_page:
 		if (pages) {
 			pages[i] = page;
 			flush_anon_page(vma, page, start);
 			flush_dcache_page(page);
 			ctx.page_mask = 0;
 		}
-next_page:
+
 		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
 		if (page_increm > nr_pages)
 			page_increm = nr_pages;