From 26a82feb3017642b77c22aaa11b4dce8c8bbae9c Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Wed, 6 Sep 2017 16:25:04 -0700
Subject: [PATCH] mm: hugetlb: clear target sub-page last when clearing huge
page
References: bnc#971975 VM performance -- thp
Patch-mainline: v4.14-rc1
Git-commit: c79b57e462b5d2f47afa5f175cf1828f16e18612
Huge page helps to reduce TLB miss rate, but it has higher cache
footprint, sometimes this may cause some issue. For example, when
clearing huge page on x86_64 platform, the cache footprint is 2M. But
on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M
LLC (last level cache). That is, in average, there are 2.5M LLC for
each core and 1.25M LLC for each thread.
If the cache pressure is heavy when clearing the huge page, and we clear
the huge page from the begin to the end, it is possible that the begin
of huge page is evicted from the cache after we finishing clearing the
end of the huge page. And it is possible for the application to access
the begin of the huge page after clearing the huge page.
To help the above situation, in this patch, when we clear a huge page,
the order to clear sub-pages is changed. In quite some situation, we
can get the address that the application will access after we clear the
huge page, for example, in a page fault handler. Instead of clearing
the huge page from begin to end, we will clear the sub-pages farthest
from the the sub-page to access firstly, and clear the sub-page to
access last. This will make the sub-page to access most cache-hot and
sub-pages around it more cache-hot too. If we cannot know the address
the application will access, the begin of the huge page is assumed to be
the the address the application will access.
With this patch, the throughput increases ~28.3% in vm-scalability
anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699
system (36 cores, 72 threads). The test case creates 72 processes, each
process mmap a big anonymous memory area and writes to it from the begin
to the end. For each process, other processes could be seen as other
workload which generates heavy cache pressure. At the same time, the
cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per
cycle) increased from 0.56 to 0.74, and the time spent in user space is
reduced ~7.9%
Christopher Lameter suggests to clear bytes inside a sub-page from end
to begin too. But tests show no visible performance difference in the
tests. May because the size of page is small compared with the cache
size.
Thanks Andi Kleen to propose to use address to access to determine the
order of sub-pages to clear.
The hugetlbfs access address could be improved, will do that in another
patch.
[ying.huang@intel.com: improve readability of clear_huge_page()]
Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com
Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com
Suggested-by: Andi Kleen <andi.kleen@intel.com>
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Jan Kara <jack@suse.cz>
Reviewed-by: Michal Hocko <mhocko@suse.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Nadia Yvette Chambers <nyc@holomorphy.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shaohua Li <shli@fb.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/mm.h | 2 +-
mm/huge_memory.c | 4 ++--
mm/memory.c | 42 ++++++++++++++++++++++++++++++++++++++----
3 files changed, 41 insertions(+), 7 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 48ff19c10bc0..54b266a51946 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2505,7 +2505,7 @@ enum mf_action_page_type {
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
extern void clear_huge_page(struct page *page,
- unsigned long addr,
+ unsigned long addr_hint,
unsigned int pages_per_huge_page);
extern void copy_user_huge_page(struct page *dst, struct page *src,
unsigned long addr, struct vm_area_struct *vma,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 315e3fcbc718..5071d5a7f8b8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -567,7 +567,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
goto release;
}
- clear_huge_page(page, haddr, HPAGE_PMD_NR);
+ clear_huge_page(page, vmf->address, HPAGE_PMD_NR);
/*
* The memory barrier inside __SetPageUptodate makes sure that
* clear_huge_page writes become visible before the set_pmd_at()
@@ -1291,7 +1291,7 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
count_vm_event(THP_FAULT_ALLOC);
if (!page)
- clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
+ clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR);
else
copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
__SetPageUptodate(new_page);
diff --git a/mm/memory.c b/mm/memory.c
index 78cc9cf5cf6b..b1b6c4dee488 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4342,19 +4342,53 @@ static void clear_gigantic_page(struct page *page,
}
}
void clear_huge_page(struct page *page,
- unsigned long addr, unsigned int pages_per_huge_page)
+ unsigned long addr_hint, unsigned int pages_per_huge_page)
{
- int i;
+ int i, n, base, l;
+ unsigned long addr = addr_hint &
+ ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
clear_gigantic_page(page, addr, pages_per_huge_page);
return;
}
+ /* Clear sub-page to access last to keep its cache lines hot */
might_sleep();
- for (i = 0; i < pages_per_huge_page; i++) {
+ n = (addr_hint - addr) / PAGE_SIZE;
+ if (2 * n <= pages_per_huge_page) {
+ /* If sub-page to access in first half of huge page */
+ base = 0;
+ l = n;
+ /* Clear sub-pages at the end of huge page */
+ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) {
+ cond_resched();
+ clear_user_highpage(page + i, addr + i * PAGE_SIZE);
+ }
+ } else {
+ /* If sub-page to access in second half of huge page */
+ base = pages_per_huge_page - 2 * (pages_per_huge_page - n);
+ l = pages_per_huge_page - n;
+ /* Clear sub-pages at the begin of huge page */
+ for (i = 0; i < base; i++) {
+ cond_resched();
+ clear_user_highpage(page + i, addr + i * PAGE_SIZE);
+ }
+ }
+ /*
+ * Clear remaining sub-pages in left-right-left-right pattern
+ * towards the sub-page to access
+ */
+ for (i = 0; i < l; i++) {
+ int left_idx = base + i;
+ int right_idx = base + 2 * l - 1 - i;
+
+ cond_resched();
+ clear_user_highpage(page + left_idx,
+ addr + left_idx * PAGE_SIZE);
cond_resched();
- clear_user_highpage(page + i, addr + i * PAGE_SIZE);
+ clear_user_highpage(page + right_idx,
+ addr + right_idx * PAGE_SIZE);
}
}