* + mm-hugetlb-refactor-subpage-recording.patch added to -mm tree
@ 2021-01-26 0:32 akpm
0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2021-01-26 0:32 UTC (permalink / raw)
To: joao.m.martins, mike.kravetz, mm-commits
The patch titled
Subject: mm/hugetlb: refactor subpage recording
has been added to the -mm tree. Its filename is
mm-hugetlb-refactor-subpage-recording.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-refactor-subpage-recording.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-refactor-subpage-recording.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Joao Martins <joao.m.martins@oracle.com>
Subject: mm/hugetlb: refactor subpage recording
For a given hugepage backing a VA, there's a rather ineficient
loop which is solely responsible for storing subpages in the passed
pages/vmas array. For each subpage we check whether it's within
range or size of @pages and keep incrementing @pfn_offset and a couple
other variables per subpage iteration.
Simplify this logic and minimize ops per iteration to just
store the output page/vma. Instead of incrementing number of @refs
iteratively, we do it through a precalculation of @refs and having
only a tight loop for storing pinned subpages/vmas.
pinning consequently improves considerably, bringing us close to
{pin,get}_user_pages_fast:
- 16G with 1G huge page size
gup_test -f /mnt/huge/file -m 16384 -r 10 -L -S -n 512 -w
PIN_LONGTERM_BENCHMARK: ~11k us -> ~4400 us
PIN_FAST_BENCHMARK: ~3700 us
Link: https://lkml.kernel.org/r/20210125205744.10203-3-joao.m.martins@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 49 ++++++++++++++++++++++++++++---------------------
1 file changed, 28 insertions(+), 21 deletions(-)
--- a/mm/hugetlb.c~mm-hugetlb-refactor-subpage-recording
+++ a/mm/hugetlb.c
@@ -4789,6 +4789,20 @@ out_release_nounlock:
goto out;
}
+static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma,
+ int refs, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ int nr;
+
+ for (nr = 0; nr < refs; nr++) {
+ if (likely(pages))
+ pages[nr] = page++;
+ if (vmas)
+ vmas[nr] = vma;
+ }
+}
+
long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, unsigned long *nr_pages,
@@ -4918,28 +4932,16 @@ long follow_hugetlb_page(struct mm_struc
continue;
}
- refs = 0;
+ refs = min3(pages_per_huge_page(h) - pfn_offset,
+ (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder);
-same_page:
- if (pages)
- pages[i] = mem_map_offset(page, pfn_offset);
+ if (pages || vmas)
+ record_subpages_vmas(mem_map_offset(page, pfn_offset),
+ vma, refs,
+ likely(pages) ? pages + i : NULL,
+ vmas ? vmas + i : NULL);
- if (vmas)
- vmas[i] = vma;
-
- vaddr += PAGE_SIZE;
- ++pfn_offset;
- --remainder;
- ++i;
- refs++;
- if (vaddr < vma->vm_end && remainder &&
- pfn_offset < pages_per_huge_page(h)) {
- /*
- * We use pfn_offset to avoid touching the pageframes
- * of this compound page.
- */
- goto same_page;
- } else if (pages) {
+ if (pages) {
/*
* try_grab_compound_head() should always succeed here,
* because: a) we hold the ptl lock, and b) we've just
@@ -4950,7 +4952,7 @@ same_page:
* any way. So this page must be available at this
* point, unless the page refcount overflowed:
*/
- if (WARN_ON_ONCE(!try_grab_compound_head(pages[i-1],
+ if (WARN_ON_ONCE(!try_grab_compound_head(pages[i],
refs,
flags))) {
spin_unlock(ptl);
@@ -4959,6 +4961,11 @@ same_page:
break;
}
}
+
+ vaddr += (refs << PAGE_SHIFT);
+ remainder -= refs;
+ i += refs;
+
spin_unlock(ptl);
}
*nr_pages = remainder;
_
Patches currently in -mm which might be from joao.m.martins@oracle.com are
mm-hugetlb-grab-head-page-refcount-once-per-group-of-subpages.patch
mm-hugetlb-refactor-subpage-recording.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
* + mm-hugetlb-refactor-subpage-recording.patch added to -mm tree
@ 2021-01-28 20:36 akpm
0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2021-01-28 20:36 UTC (permalink / raw)
To: joao.m.martins, mike.kravetz, mm-commits
The patch titled
Subject: mm/hugetlb: refactor subpage recording
has been added to the -mm tree. Its filename is
mm-hugetlb-refactor-subpage-recording.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-refactor-subpage-recording.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-refactor-subpage-recording.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Joao Martins <joao.m.martins@oracle.com>
Subject: mm/hugetlb: refactor subpage recording
For a given hugepage backing a VA, there's a rather ineficient loop which
is solely responsible for storing subpages in GUP @pages/@vmas array. For
each subpage we check whether it's within range or size of @pages and keep
increment @pfn_offset and a couple other variables per subpage iteration.
Simplify this logic and minimize the cost of each iteration to just store
the output page/vma. Instead of incrementing number of @refs iteratively,
we do it through pre-calculation of @refs and only with a tight loop for
storing pinned subpages/vmas.
Additionally, retain existing behaviour with using mem_map_offset() when
recording the subpages for configurations that don't have a contiguous
mem_map.
pinning consequently improves bringing us close to
{pin,get}_user_pages_fast:
- 16G with 1G huge page size
gup_test -f /mnt/huge/file -m 16384 -r 30 -L -S -n 512 -w
PIN_LONGTERM_BENCHMARK: ~12.8k us -> ~5.8k us
PIN_FAST_BENCHMARK: ~3.7k us
Link: https://lkml.kernel.org/r/20210128182632.24562-3-joao.m.martins@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 49 ++++++++++++++++++++++++++++---------------------
1 file changed, 28 insertions(+), 21 deletions(-)
--- a/mm/hugetlb.c~mm-hugetlb-refactor-subpage-recording
+++ a/mm/hugetlb.c
@@ -4801,6 +4801,20 @@ out_release_nounlock:
goto out;
}
+static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma,
+ int refs, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ int nr;
+
+ for (nr = 0; nr < refs; nr++) {
+ if (likely(pages))
+ pages[nr] = mem_map_offset(page, nr);
+ if (vmas)
+ vmas[nr] = vma;
+ }
+}
+
long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, unsigned long *nr_pages,
@@ -4930,28 +4944,16 @@ long follow_hugetlb_page(struct mm_struc
continue;
}
- refs = 0;
+ refs = min3(pages_per_huge_page(h) - pfn_offset,
+ (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder);
-same_page:
- if (pages)
- pages[i] = mem_map_offset(page, pfn_offset);
+ if (pages || vmas)
+ record_subpages_vmas(mem_map_offset(page, pfn_offset),
+ vma, refs,
+ likely(pages) ? pages + i : NULL,
+ vmas ? vmas + i : NULL);
- if (vmas)
- vmas[i] = vma;
-
- vaddr += PAGE_SIZE;
- ++pfn_offset;
- --remainder;
- ++i;
- ++refs;
- if (vaddr < vma->vm_end && remainder &&
- pfn_offset < pages_per_huge_page(h)) {
- /*
- * We use pfn_offset to avoid touching the pageframes
- * of this compound page.
- */
- goto same_page;
- } else if (pages) {
+ if (pages) {
/*
* try_grab_compound_head() should always succeed here,
* because: a) we hold the ptl lock, and b) we've just
@@ -4962,7 +4964,7 @@ same_page:
* any way. So this page must be available at this
* point, unless the page refcount overflowed:
*/
- if (WARN_ON_ONCE(!try_grab_compound_head(pages[i-1],
+ if (WARN_ON_ONCE(!try_grab_compound_head(pages[i],
refs,
flags))) {
spin_unlock(ptl);
@@ -4971,6 +4973,11 @@ same_page:
break;
}
}
+
+ vaddr += (refs << PAGE_SHIFT);
+ remainder -= refs;
+ i += refs;
+
spin_unlock(ptl);
}
*nr_pages = remainder;
_
Patches currently in -mm which might be from joao.m.martins@oracle.com are
mm-hugetlb-grab-head-page-refcount-once-for-group-of-subpages.patch
mm-hugetlb-refactor-subpage-recording.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-01-28 20:37 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-01-26 0:32 + mm-hugetlb-refactor-subpage-recording.patch added to -mm tree akpm
2021-01-28 20:36 akpm
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.