From: "Zach O'Keefe" <zokeefe@google.com>
To: Alex Shi <alex.shi@linux.alibaba.com>,
David Hildenbrand <david@redhat.com>,
David Rientjes <rientjes@google.com>,
Matthew Wilcox <willy@infradead.org>,
Michal Hocko <mhocko@suse.com>,
Pasha Tatashin <pasha.tatashin@soleen.com>,
Peter Xu <peterx@redhat.com>,
Rongwei Wang <rongwei.wang@linux.alibaba.com>,
SeongJae Park <sj@kernel.org>, Song Liu <songliubraving@fb.com>,
Vlastimil Babka <vbabka@suse.cz>, Yang Shi <shy828301@gmail.com>,
Zi Yan <ziy@nvidia.com>,
linux-mm@kvack.org
Cc: Andrea Arcangeli <aarcange@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Arnd Bergmann <arnd@arndb.de>,
Axel Rasmussen <axelrasmussen@google.com>,
Chris Kennelly <ckennelly@google.com>,
Chris Zankel <chris@zankel.net>, Helge Deller <deller@gmx.de>,
Hugh Dickins <hughd@google.com>,
Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>,
Jens Axboe <axboe@kernel.dk>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Matt Turner <mattst88@gmail.com>,
Max Filippov <jcmvbkbc@gmail.com>,
Miaohe Lin <linmiaohe@huawei.com>,
Minchan Kim <minchan@kernel.org>,
Patrick Xia <patrickx@google.com>,
Pavel Begunkov <asml.silence@gmail.com>,
Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
"Zach O'Keefe" <zokeefe@google.com>
Subject: [PATCH v6 04/15] mm/khugepaged: dedup and simplify hugepage alloc and charging
Date: Fri, 3 Jun 2022 17:39:53 -0700 [thread overview]
Message-ID: <20220604004004.954674-5-zokeefe@google.com> (raw)
In-Reply-To: <20220604004004.954674-1-zokeefe@google.com>
The following code is duplicated in collapse_huge_page() and
collapse_file():
gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
new_page = khugepaged_alloc_page(hpage, gfp, node);
if (!new_page) {
result = SCAN_ALLOC_HUGE_PAGE_FAIL;
goto out;
}
if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out;
}
count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
Also, "node" is passed as an argument to both collapse_huge_page() and
collapse_file() and obtained the same way, via
khugepaged_find_target_node().
Move all this into a new helper, alloc_charge_hpage(), and remove the
duplicate code from collapse_huge_page() and collapse_file(). Also,
simplify khugepaged_alloc_page() by returning a bool indicating
allocation success instead of a copy of the allocated struct page.
Suggested-by: Peter Xu <peterx@redhat.com>
---
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
---
mm/khugepaged.c | 77 ++++++++++++++++++++++---------------------------
1 file changed, 34 insertions(+), 43 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 907d0b2bd4bd..38488d114073 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -860,19 +860,18 @@ static bool alloc_fail_should_sleep(struct page **hpage, bool *wait)
return false;
}
-static struct page *
-khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
+static bool khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
{
*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
if (unlikely(!*hpage)) {
count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
*hpage = ERR_PTR(-ENOMEM);
- return NULL;
+ return false;
}
prep_transhuge_page(*hpage);
count_vm_event(THP_COLLAPSE_ALLOC);
- return *hpage;
+ return true;
}
/*
@@ -995,10 +994,23 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
return true;
}
-static void collapse_huge_page(struct mm_struct *mm,
- unsigned long address,
- struct page **hpage,
- int node, int referenced, int unmapped)
+static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
+ struct collapse_control *cc)
+{
+ gfp_t gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
+ int node = khugepaged_find_target_node(cc);
+
+ if (!khugepaged_alloc_page(hpage, gfp, node))
+ return SCAN_ALLOC_HUGE_PAGE_FAIL;
+ if (unlikely(mem_cgroup_charge(page_folio(*hpage), mm, gfp)))
+ return SCAN_CGROUP_CHARGE_FAIL;
+ count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC);
+ return SCAN_SUCCEED;
+}
+
+static void collapse_huge_page(struct mm_struct *mm, unsigned long address,
+ struct page **hpage, int referenced,
+ int unmapped, struct collapse_control *cc)
{
LIST_HEAD(compound_pagelist);
pmd_t *pmd, _pmd;
@@ -1009,13 +1021,9 @@ static void collapse_huge_page(struct mm_struct *mm,
int isolated = 0, result = 0;
struct vm_area_struct *vma;
struct mmu_notifier_range range;
- gfp_t gfp;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
- /* Only allocate from the target node */
- gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
-
/*
* Before allocating the hugepage, release the mmap_lock read lock.
* The allocation can take potentially a long time if it involves
@@ -1023,17 +1031,12 @@ static void collapse_huge_page(struct mm_struct *mm,
* that. We will recheck the vma after taking it again in write mode.
*/
mmap_read_unlock(mm);
- new_page = khugepaged_alloc_page(hpage, gfp, node);
- if (!new_page) {
- result = SCAN_ALLOC_HUGE_PAGE_FAIL;
- goto out_nolock;
- }
- if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
- result = SCAN_CGROUP_CHARGE_FAIL;
+ result = alloc_charge_hpage(hpage, mm, cc);
+ if (result != SCAN_SUCCEED)
goto out_nolock;
- }
- count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
+
+ new_page = *hpage;
mmap_read_lock(mm);
result = hugepage_vma_revalidate(mm, address, &vma);
@@ -1306,10 +1309,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
out_unmap:
pte_unmap_unlock(pte, ptl);
if (ret) {
- node = khugepaged_find_target_node(cc);
/* collapse_huge_page will return with the mmap_lock released */
- collapse_huge_page(mm, address, hpage, node,
- referenced, unmapped);
+ collapse_huge_page(mm, address, hpage, referenced, unmapped,
+ cc);
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
@@ -1578,7 +1580,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
* @file: file that collapse on
* @start: collapse start address
* @hpage: new allocated huge page for collapse
- * @node: appointed node the new huge page allocate from
+ * @cc: collapse context and scratchpad
*
* Basic scheme is simple, details are more complex:
* - allocate and lock a new huge page;
@@ -1595,12 +1597,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
* + restore gaps in the page cache;
* + unlock and free huge page;
*/
-static void collapse_file(struct mm_struct *mm,
- struct file *file, pgoff_t start,
- struct page **hpage, int node)
+static void collapse_file(struct mm_struct *mm, struct file *file,
+ pgoff_t start, struct page **hpage,
+ struct collapse_control *cc)
{
struct address_space *mapping = file->f_mapping;
- gfp_t gfp;
struct page *new_page;
pgoff_t index, end = start + HPAGE_PMD_NR;
LIST_HEAD(pagelist);
@@ -1612,20 +1613,11 @@ static void collapse_file(struct mm_struct *mm,
VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
- /* Only allocate from the target node */
- gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
-
- new_page = khugepaged_alloc_page(hpage, gfp, node);
- if (!new_page) {
- result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+ result = alloc_charge_hpage(hpage, mm, cc);
+ if (result != SCAN_SUCCEED)
goto out;
- }
- if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
- result = SCAN_CGROUP_CHARGE_FAIL;
- goto out;
- }
- count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
+ new_page = *hpage;
/*
* Ensure we have slots for all the pages in the range. This is
@@ -2037,8 +2029,7 @@ static void khugepaged_scan_file(struct mm_struct *mm, struct file *file,
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
} else {
- node = khugepaged_find_target_node(cc);
- collapse_file(mm, file, start, hpage, node);
+ collapse_file(mm, file, start, hpage, cc);
}
}
--
2.36.1.255.ge46751e96f-goog
next prev parent reply other threads:[~2022-06-04 0:40 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-04 0:39 [PATCH v6 00/15] mm: userspace hugepage collapse Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 01/15] mm: khugepaged: don't carry huge page to the next loop for !CONFIG_NUMA Zach O'Keefe
2022-06-06 18:25 ` Yang Shi
2022-06-29 20:49 ` Peter Xu
2022-06-30 1:15 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 02/15] mm/khugepaged: record SCAN_PMD_MAPPED when scan_pmd() finds THP Zach O'Keefe
2022-06-06 20:45 ` Yang Shi
2022-06-07 16:01 ` Zach O'Keefe
2022-06-07 19:32 ` Zach O'Keefe
2022-06-07 21:27 ` Yang Shi
2022-06-08 0:27 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 03/15] mm/khugepaged: add struct collapse_control Zach O'Keefe
2022-06-06 2:41 ` kernel test robot
2022-06-06 16:40 ` Zach O'Keefe
2022-06-06 20:20 ` Yang Shi
2022-06-06 21:22 ` Yang Shi
2022-06-06 22:23 ` Andrew Morton
2022-06-06 23:53 ` Yang Shi
2022-06-08 0:42 ` Zach O'Keefe
2022-06-08 1:00 ` Yang Shi
2022-06-08 1:06 ` Zach O'Keefe
2022-06-04 0:39 ` Zach O'Keefe [this message]
2022-06-06 20:50 ` [PATCH v6 04/15] mm/khugepaged: dedup and simplify hugepage alloc and charging Yang Shi
2022-06-29 21:58 ` Peter Xu
2022-06-30 20:14 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 05/15] mm/khugepaged: make allocation semantics context-specific Zach O'Keefe
2022-06-06 20:58 ` Yang Shi
2022-06-07 19:56 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 06/15] mm/khugepaged: pipe enum scan_result codes back to callers Zach O'Keefe
2022-06-06 22:39 ` Yang Shi
2022-06-07 0:17 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 07/15] mm/khugepaged: add flag to ignore khugepaged heuristics Zach O'Keefe
2022-06-06 22:51 ` Yang Shi
2022-06-04 0:39 ` [PATCH v6 08/15] mm/khugepaged: add flag to ignore THP sysfs enabled Zach O'Keefe
2022-06-06 23:02 ` Yang Shi
[not found] ` <YrzehlUoo2iMMLC2@xz-m1.local>
[not found] ` <CAAa6QmRXD5KboM8=ZZRPThOmcLEPtxzf0XyjkCeY_vgR7VOPqg@mail.gmail.com>
2022-06-30 2:32 ` Peter Xu
2022-06-30 14:17 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 09/15] mm/madvise: introduce MADV_COLLAPSE sync hugepage collapse Zach O'Keefe
2022-06-06 23:53 ` Yang Shi
2022-06-07 22:48 ` Zach O'Keefe
2022-06-08 0:39 ` Yang Shi
2022-06-09 17:35 ` Zach O'Keefe
2022-06-09 18:51 ` Yang Shi
2022-06-10 14:51 ` Zach O'Keefe
2022-06-04 0:39 ` [PATCH v6 10/15] mm/khugepaged: rename prefix of shared collapse functions Zach O'Keefe
2022-06-06 23:56 ` Yang Shi
2022-06-07 0:31 ` Zach O'Keefe
2022-06-04 0:40 ` [PATCH v6 11/15] mm/madvise: add MADV_COLLAPSE to process_madvise() Zach O'Keefe
2022-06-07 19:14 ` Yang Shi
2022-06-04 0:40 ` [PATCH v6 12/15] selftests/vm: modularize collapse selftests Zach O'Keefe
2022-06-04 0:40 ` [PATCH v6 13/15] selftests/vm: add MADV_COLLAPSE collapse context to selftests Zach O'Keefe
2022-06-04 0:40 ` [PATCH v6 14/15] selftests/vm: add selftest to verify recollapse of THPs Zach O'Keefe
2022-06-04 0:40 ` [PATCH v6 15/15] tools headers uapi: add MADV_COLLAPSE madvise mode to tools Zach O'Keefe
2022-06-06 23:58 ` Yang Shi
2022-06-07 0:24 ` Zach O'Keefe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220604004004.954674-5-zokeefe@google.com \
--to=zokeefe@google.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@linux.alibaba.com \
--cc=arnd@arndb.de \
--cc=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=axelrasmussen@google.com \
--cc=chris@zankel.net \
--cc=ckennelly@google.com \
--cc=david@redhat.com \
--cc=deller@gmx.de \
--cc=hughd@google.com \
--cc=ink@jurassic.park.msu.ru \
--cc=jcmvbkbc@gmail.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linmiaohe@huawei.com \
--cc=linux-mm@kvack.org \
--cc=mattst88@gmail.com \
--cc=mhocko@suse.com \
--cc=minchan@kernel.org \
--cc=pasha.tatashin@soleen.com \
--cc=patrickx@google.com \
--cc=peterx@redhat.com \
--cc=rientjes@google.com \
--cc=rongwei.wang@linux.alibaba.com \
--cc=shy828301@gmail.com \
--cc=sj@kernel.org \
--cc=songliubraving@fb.com \
--cc=tsbogend@alpha.franken.de \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
--cc=ziy@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).