diff mbox series

[v3,2/6] mm cma: rename PF_MEMALLOC_NOCMA to PF_MEMALLOC_PIN

Message ID 20201211202140.396852-3-pasha.tatashin@soleen.com (mailing list archive)
State New, archived
Headers show
Series prohibit pinning pages in ZONE_MOVABLE | expand

Commit Message

Pasha Tatashin Dec. 11, 2020, 8:21 p.m. UTC 
PF_MEMALLOC_NOCMA is used ot guarantee that the allocator will not return
pages that might belong to CMA region. This is currently used for long
term gup to make sure that such pins are not going to be done on any CMA
pages.

When PF_MEMALLOC_NOCMA has been introduced we haven't realized that it is
focusing on CMA pages too much and that there is larger class of pages that
need the same treatment. MOVABLE zone cannot contain any long term pins as
well so it makes sense to reuse and redefine this flag for that usecase as
well. Rename the flag to PF_MEMALLOC_PIN which defines an allocation
context which can only get pages suitable for long-term pins.

Also re-name:
memalloc_nocma_save()/memalloc_nocma_restore
to
memalloc_pin_save()/memalloc_pin_restore()
and make the new functions common.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
---
 include/linux/sched.h    |  2 +-
 include/linux/sched/mm.h | 21 +++++----------------
 mm/gup.c                 |  4 ++--
 mm/hugetlb.c             |  4 ++--
 mm/page_alloc.c          |  4 ++--
 5 files changed, 12 insertions(+), 23 deletions(-)

Comments

Michal Hocko Dec. 14, 2020, 2:03 p.m. UTC | #1 
On Fri 11-12-20 15:21:36, Pavel Tatashin wrote:
> PF_MEMALLOC_NOCMA is used ot guarantee that the allocator will not return
> pages that might belong to CMA region. This is currently used for long
> term gup to make sure that such pins are not going to be done on any CMA
> pages.
> 
> When PF_MEMALLOC_NOCMA has been introduced we haven't realized that it is
> focusing on CMA pages too much and that there is larger class of pages that
> need the same treatment. MOVABLE zone cannot contain any long term pins as
> well so it makes sense to reuse and redefine this flag for that usecase as
> well. Rename the flag to PF_MEMALLOC_PIN which defines an allocation
> context which can only get pages suitable for long-term pins.
> 
> Also re-name:
> memalloc_nocma_save()/memalloc_nocma_restore
> to
> memalloc_pin_save()/memalloc_pin_restore()
> and make the new functions common.
> 
> Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
> Reviewed-by: John Hubbard <jhubbard@nvidia.com>

Acked-by: Michal Hocko <mhocko@suse.com>

with one comment below
[...]
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1576,7 +1576,7 @@ extern struct pid *cad_pid;
>  #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
>  #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
>  #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
> -#define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
> +#define PF_MEMALLOC_PIN		0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */

This comment is not really helpeful. I would go with
/* Allocation context constrained to zones which allow long term
 * pinning.
 */

Something similar would be useful for memalloc_pin* functions as well.
Pasha Tatashin Dec. 15, 2020, 4:37 a.m. UTC | #2 
On Mon, Dec 14, 2020 at 9:03 AM Michal Hocko <mhocko@suse.com> wrote:
>
> On Fri 11-12-20 15:21:36, Pavel Tatashin wrote:
> > PF_MEMALLOC_NOCMA is used ot guarantee that the allocator will not return
> > pages that might belong to CMA region. This is currently used for long
> > term gup to make sure that such pins are not going to be done on any CMA
> > pages.
> >
> > When PF_MEMALLOC_NOCMA has been introduced we haven't realized that it is
> > focusing on CMA pages too much and that there is larger class of pages that
> > need the same treatment. MOVABLE zone cannot contain any long term pins as
> > well so it makes sense to reuse and redefine this flag for that usecase as
> > well. Rename the flag to PF_MEMALLOC_PIN which defines an allocation
> > context which can only get pages suitable for long-term pins.
> >
> > Also re-name:
> > memalloc_nocma_save()/memalloc_nocma_restore
> > to
> > memalloc_pin_save()/memalloc_pin_restore()
> > and make the new functions common.
> >
> > Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
> > Reviewed-by: John Hubbard <jhubbard@nvidia.com>
>
> Acked-by: Michal Hocko <mhocko@suse.com>

Thank you.

>
> with one comment below
> [...]
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -1576,7 +1576,7 @@ extern struct pid *cad_pid;
> >  #define PF_SWAPWRITE         0x00800000      /* Allowed to write to swap */
> >  #define PF_NO_SETAFFINITY    0x04000000      /* Userland is not allowed to meddle with cpus_mask */
> >  #define PF_MCE_EARLY         0x08000000      /* Early kill for mce process policy */
> > -#define PF_MEMALLOC_NOCMA    0x10000000      /* All allocation request will have _GFP_MOVABLE cleared */
> > +#define PF_MEMALLOC_PIN              0x10000000      /* All allocation request will have _GFP_MOVABLE cleared */
>
> This comment is not really helpeful. I would go with
> /* Allocation context constrained to zones which allow long term
>  * pinning.
>  */
>
> Something similar would be useful for memalloc_pin* functions as well.

I will add it.

> --
> Michal Hocko
> SUSE Labs
diff mbox series

Patch

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e5ad6d354b7b..f3226ef7134f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1576,7 +1576,7 @@  extern struct pid *cad_pid;
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
-#define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
+#define PF_MEMALLOC_PIN		0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
 #define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1ae08b8462a4..5f4dd3274734 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -270,29 +270,18 @@  static inline void memalloc_noreclaim_restore(unsigned int flags)
 	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
 }
 
-#ifdef CONFIG_CMA
-static inline unsigned int memalloc_nocma_save(void)
+static inline unsigned int memalloc_pin_save(void)
 {
-	unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
+	unsigned int flags = current->flags & PF_MEMALLOC_PIN;
 
-	current->flags |= PF_MEMALLOC_NOCMA;
+	current->flags |= PF_MEMALLOC_PIN;
 	return flags;
 }
 
-static inline void memalloc_nocma_restore(unsigned int flags)
+static inline void memalloc_pin_restore(unsigned int flags)
 {
-	current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
+	current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags;
 }
-#else
-static inline unsigned int memalloc_nocma_save(void)
-{
-	return 0;
-}
-
-static inline void memalloc_nocma_restore(unsigned int flags)
-{
-}
-#endif
 
 #ifdef CONFIG_MEMCG
 DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
diff --git a/mm/gup.c b/mm/gup.c
index 87452fcad048..007060e66a48 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1671,7 +1671,7 @@  static long __gup_longterm_locked(struct mm_struct *mm,
 	long rc;
 
 	if (gup_flags & FOLL_LONGTERM)
-		flags = memalloc_nocma_save();
+		flags = memalloc_pin_save();
 
 	rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL,
 				     gup_flags);
@@ -1680,7 +1680,7 @@  static long __gup_longterm_locked(struct mm_struct *mm,
 		if (rc > 0)
 			rc = check_and_migrate_cma_pages(mm, start, rc, pages,
 							 vmas, gup_flags);
-		memalloc_nocma_restore(flags);
+		memalloc_pin_restore(flags);
 	}
 	return rc;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3bcc0bc7e02a..012246234eb5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1033,10 +1033,10 @@  static void enqueue_huge_page(struct hstate *h, struct page *page)
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 {
 	struct page *page;
-	bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA);
+	bool pin = !!(current->flags & PF_MEMALLOC_PIN);
 
 	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
-		if (nocma && is_migrate_cma_page(page))
+		if (pin && is_migrate_cma_page(page))
 			continue;
 
 		if (PageHWPoison(page))
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 774542e1483e..ec05396a597b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3808,8 +3808,8 @@  static inline unsigned int current_alloc_flags(gfp_t gfp_mask,
 #ifdef CONFIG_CMA
 	unsigned int pflags = current->flags;
 
-	if (!(pflags & PF_MEMALLOC_NOCMA) &&
-			gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+	if (!(pflags & PF_MEMALLOC_PIN) &&
+	    gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 
 #endif