As there are more ALLOC_ flags that affect reserves, define what flags
affect reserves and clarify the effect of each flag.
Signed-off-by: Mel Gorman <[email protected]>
---
mm/internal.h | 3 +++
mm/page_alloc.c | 36 +++++++++++++++++++++++-------------
2 files changed, 26 insertions(+), 13 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index 9a9d9b5ee87f..370500718732 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -757,6 +757,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+/* Flags that allow allocations below the min watermark. */
+#define ALLOC_RESERVES (ALLOC_HARDER|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
+
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e2b65767dda0..85a87d0ac57a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3944,15 +3944,14 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
static inline long __zone_watermark_unusable_free(struct zone *z,
unsigned int order, unsigned int alloc_flags)
{
- const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
long unusable_free = (1 << order) - 1;
/*
- * If the caller does not have rights to ALLOC_HARDER then subtract
- * the high-atomic reserves. This will over-estimate the size of the
- * atomic reserve but it avoids a search.
+ * If the caller does not have rights to reserves below the min
+ * watermark then subtract the high-atomic reserves. This will
+ * over-estimate the size of the atomic reserve but it avoids a search.
*/
- if (likely(!alloc_harder))
+ if (likely(!(alloc_flags & ALLOC_RESERVES)))
unusable_free += z->nr_reserved_highatomic;
#ifdef CONFIG_CMA
@@ -3976,25 +3975,36 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
{
long min = mark;
int o;
- const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
- if (alloc_flags & ALLOC_MIN_RESERVE)
- min -= min / 2;
+ if (alloc_flags & ALLOC_RESERVES) {
+ /*
+ * __GFP_HIGH allows access to 50% of the min reserve as well
+ * as OOM.
+ */
+ if (alloc_flags & ALLOC_MIN_RESERVE)
+ min -= min / 2;
- if (unlikely(alloc_harder)) {
/*
- * OOM victims can try even harder than normal ALLOC_HARDER
+ * Non-blocking allocations can access some of the reserve
+ * with more access if also __GFP_HIGH. The reasoning is that
+ * a non-blocking caller may incur a more severe penalty
+ * if it cannot get memory quickly, particularly if it's
+ * also __GFP_HIGH.
+ */
+ if (alloc_flags & (ALLOC_HARDER|ALLOC_HIGHATOMIC))
+ min -= min / 4;
+
+ /*
+ * OOM victims can try even harder than the normal reserve
* users on the grounds that it's definitely going to be in
* the exit path shortly and free memory. Any allocation it
* makes during the free path will be small and short-lived.
*/
if (alloc_flags & ALLOC_OOM)
min -= min / 2;
- else
- min -= min / 4;
}
/*
@@ -5293,7 +5303,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* could deplete whole memory reserves which would just make
* the situation worse
*/
- page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_HARDER, ac);
if (page)
goto got_pg;
--
2.35.3
On 11/29/22 16:16, Mel Gorman wrote:
> As there are more ALLOC_ flags that affect reserves, define what flags
> affect reserves and clarify the effect of each flag.
Seems to me this does more than a clarification, but also some functional
tweaks, so it could be helpful if those were spelled out in the changelog.
> Signed-off-by: Mel Gorman <[email protected]>
> ---
> mm/internal.h | 3 +++
> mm/page_alloc.c | 36 +++++++++++++++++++++++-------------
> 2 files changed, 26 insertions(+), 13 deletions(-)
>
> diff --git a/mm/internal.h b/mm/internal.h
> index 9a9d9b5ee87f..370500718732 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -757,6 +757,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
> #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */
> #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
>
> +/* Flags that allow allocations below the min watermark. */
> +#define ALLOC_RESERVES (ALLOC_HARDER|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
> +
> enum ttu_flags;
> struct tlbflush_unmap_batch;
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index e2b65767dda0..85a87d0ac57a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3944,15 +3944,14 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
> static inline long __zone_watermark_unusable_free(struct zone *z,
> unsigned int order, unsigned int alloc_flags)
> {
> - const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
> long unusable_free = (1 << order) - 1;
>
> /*
> - * If the caller does not have rights to ALLOC_HARDER then subtract
> - * the high-atomic reserves. This will over-estimate the size of the
> - * atomic reserve but it avoids a search.
> + * If the caller does not have rights to reserves below the min
> + * watermark then subtract the high-atomic reserves. This will
> + * over-estimate the size of the atomic reserve but it avoids a search.
> */
> - if (likely(!alloc_harder))
> + if (likely(!(alloc_flags & ALLOC_RESERVES)))
> unusable_free += z->nr_reserved_highatomic;
>
> #ifdef CONFIG_CMA
> @@ -3976,25 +3975,36 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
> {
> long min = mark;
> int o;
> - const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
>
> /* free_pages may go negative - that's OK */
> free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
>
> - if (alloc_flags & ALLOC_MIN_RESERVE)
> - min -= min / 2;
> + if (alloc_flags & ALLOC_RESERVES) {
Do we want to keep this unlikely() as alloc_harder did before?
> + /*
> + * __GFP_HIGH allows access to 50% of the min reserve as well
> + * as OOM.
> + */
> + if (alloc_flags & ALLOC_MIN_RESERVE)
> + min -= min / 2;
>
> - if (unlikely(alloc_harder)) {
> /*
> - * OOM victims can try even harder than normal ALLOC_HARDER
> + * Non-blocking allocations can access some of the reserve
> + * with more access if also __GFP_HIGH. The reasoning is that
> + * a non-blocking caller may incur a more severe penalty
> + * if it cannot get memory quickly, particularly if it's
> + * also __GFP_HIGH.
> + */
> + if (alloc_flags & (ALLOC_HARDER|ALLOC_HIGHATOMIC))
> + min -= min / 4;
For example this seems to change the allowed dip to reserves for
ALLOC_HIGHATOMIC.
> +
> + /*
> + * OOM victims can try even harder than the normal reserve
> * users on the grounds that it's definitely going to be in
> * the exit path shortly and free memory. Any allocation it
> * makes during the free path will be small and short-lived.
> */
> if (alloc_flags & ALLOC_OOM)
> min -= min / 2;
> - else
> - min -= min / 4;
> }
(noted that this patch doesn't seem to change the concern I raised in
previous patch)
> /*
> @@ -5293,7 +5303,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
> * could deplete whole memory reserves which would just make
> * the situation worse
> */
> - page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
> + page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_HARDER, ac);
And this AFAICS seems to give __GFP_NOFAIL 3/4 of min reserves instead of
1/4, which seems like a significant change (but hopefully ok) so worth
noting at least.
> if (page)
> goto got_pg;
>
On Thu, Dec 08, 2022 at 06:55:00PM +0100, Vlastimil Babka wrote:
> On 11/29/22 16:16, Mel Gorman wrote:
> > As there are more ALLOC_ flags that affect reserves, define what flags
> > affect reserves and clarify the effect of each flag.
>
> Seems to me this does more than a clarification, but also some functional
> tweaks, so it could be helpful if those were spelled out in the changelog.
>
I will to take out the problematic parts that need clarification. There
are two, one I'll drop and the other will be split. More details below.
> > @@ -3976,25 +3975,36 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
> > {
> > long min = mark;
> > int o;
> > - const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
> >
> > /* free_pages may go negative - that's OK */
> > free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
> >
> > - if (alloc_flags & ALLOC_MIN_RESERVE)
> > - min -= min / 2;
> > + if (alloc_flags & ALLOC_RESERVES) {
>
> Do we want to keep this unlikely() as alloc_harder did before?
>
Added back in.
> > + /*
> > + * __GFP_HIGH allows access to 50% of the min reserve as well
> > + * as OOM.
> > + */
> > + if (alloc_flags & ALLOC_MIN_RESERVE)
> > + min -= min / 2;
> >
> > - if (unlikely(alloc_harder)) {
> > /*
> > - * OOM victims can try even harder than normal ALLOC_HARDER
> > + * Non-blocking allocations can access some of the reserve
> > + * with more access if also __GFP_HIGH. The reasoning is that
> > + * a non-blocking caller may incur a more severe penalty
> > + * if it cannot get memory quickly, particularly if it's
> > + * also __GFP_HIGH.
> > + */
> > + if (alloc_flags & (ALLOC_HARDER|ALLOC_HIGHATOMIC))
> > + min -= min / 4;
>
> For example this seems to change the allowed dip to reserves for
> ALLOC_HIGHATOMIC.
>
You're right and this could cause problems. If high-order atomic allocation
failures start appearing again, this change would help but it should be
a standalone patch in response to a bug. I'll drop it for now.
> > +
> > + /*
> > + * OOM victims can try even harder than the normal reserve
> > * users on the grounds that it's definitely going to be in
> > * the exit path shortly and free memory. Any allocation it
> > * makes during the free path will be small and short-lived.
> > */
> > if (alloc_flags & ALLOC_OOM)
> > min -= min / 2;
> > - else
> > - min -= min / 4;
> > }
>
> (noted that this patch doesn't seem to change the concern I raised in
> previous patch)
>
This might be addressed now with the chjanges to the patch that caused
you concerns about OOM handling.
> > /*
> > @@ -5293,7 +5303,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
> > * could deplete whole memory reserves which would just make
> > * the situation worse
> > */
> > - page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
> > + page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_HARDER, ac);
>
> And this AFAICS seems to give __GFP_NOFAIL 3/4 of min reserves instead of
> 1/4, which seems like a significant change (but hopefully ok) so worth
> noting at least.
>
It deserves a standalone patch. Below is the diff I intend to apply to
this patch and the standalone patch.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 58e01a31492e..6f41b84a97ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3984,7 +3984,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
/* free_pages may go negative - that's OK */
free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
- if (alloc_flags & ALLOC_RESERVES) {
+ if (unlikely(alloc_flags & ALLOC_RESERVES)) {
/*
* __GFP_HIGH allows access to 50% of the min reserve as well
* as OOM.
@@ -3999,7 +3999,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
* if it cannot get memory quickly, particularly if it's
* also __GFP_HIGH.
*/
- if (alloc_flags & (ALLOC_HARDER|ALLOC_HIGHATOMIC))
+ if (alloc_flags & ALLOC_HARDER)
min -= min / 4;
/*
@@ -5308,7 +5308,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* could deplete whole memory reserves which would just make
* the situation worse
*/
- page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_HARDER, ac);
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
if (page)
goto got_pg;
The patch to allow __GFP_NOFAIL deeper access is this
--8<--
mm/page_alloc.c: Allow __GFP_NOFAIL requests deeper access to reserves
Currently __GFP_NOFAIL allocations without any other flags can access 25%
of the reserves but these requests imply that the system cannot make forward
progress until the allocation succeeds. Allow __GFP_NOFAIL access to 75%
of the min reserve.
Signed-off-by: Mel Gorman <[email protected]>
---
mm/page_alloc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6f41b84a97ac..d2df78f5baa2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5308,7 +5308,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* could deplete whole memory reserves which would just make
* the situation worse
*/
- page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_HARDER, ac);
if (page)
goto got_pg;