The patch titled
Subject: mm/khugepaged: dedup and simplify hugepage alloc and charging
has been added to the -mm mm-unstable branch. Its filename is
mm-khugepaged-dedup-and-simplify-hugepage-alloc-and-charging.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-khugepaged-dedup-and-simplify-hugepage-alloc-and-charging.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Zach O'Keefe" <zokeefe@xxxxxxxxxx>
Subject: mm/khugepaged: dedup and simplify hugepage alloc and charging
Date: Wed, 6 Jul 2022 16:59:22 -0700
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 *.
Link: https://lkml.kernel.org/r/20220706235936.2197195-5-zokeefe@xxxxxxxxxx
Signed-off-by: Zach O'Keefe <zokeefe@xxxxxxxxxx>
Suggested-by: Peter Xu <peterx@xxxxxxxxxx>
Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
Cc: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: Chris Kennelly <ckennelly@xxxxxxxxxx>
Cc: Chris Zankel <chris@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Helge Deller <deller@xxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx>
Cc: James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Matt Turner <mattst88@xxxxxxxxx>
Cc: Max Filippov <jcmvbkbc@xxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Pasha Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Pavel Begunkov <asml.silence@xxxxxxxxx>
Cc: Rongwei Wang <rongwei.wang@xxxxxxxxxxxxxxxxx>
Cc: SeongJae Park <sj@xxxxxxxxxx>
Cc: Song Liu <songliubraving@xxxxxx>
Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/khugepaged.c | 78 ++++++++++++++++++++--------------------------
1 file changed, 35 insertions(+), 43 deletions(-)
--- a/mm/khugepaged.c~mm-khugepaged-dedup-and-simplify-hugepage-alloc-and-charging
+++ a/mm/khugepaged.c
@@ -813,19 +813,18 @@ static int khugepaged_find_target_node(s
}
#endif
-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;
}
/*
@@ -921,10 +920,24 @@ static bool __collapse_huge_page_swapin(
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)
+{
+ /* Only allocate from the target node */
+ 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;
@@ -935,13 +948,9 @@ static void collapse_huge_page(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
@@ -949,17 +958,12 @@ static void collapse_huge_page(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);
@@ -1233,10 +1237,9 @@ static int khugepaged_scan_pmd(struct mm
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,
@@ -1504,7 +1507,7 @@ static void retract_page_tables(struct a
* @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;
@@ -1521,12 +1524,11 @@ static void retract_page_tables(struct a
* + 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);
@@ -1538,20 +1540,11 @@ static void collapse_file(struct mm_stru
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
@@ -1963,8 +1956,7 @@ static void khugepaged_scan_file(struct
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);
}
}
_
Patches currently in -mm which might be from zokeefe@xxxxxxxxxx are
mm-khugepaged-remove-redundant-transhuge_vma_suitable-check.patch
mm-khugepaged-add-struct-collapse_control.patch
mm-khugepaged-dedup-and-simplify-hugepage-alloc-and-charging.patch
mm-khugepaged-pipe-enum-scan_result-codes-back-to-callers.patch
mm-khugepaged-add-flag-to-predicate-khugepaged-only-behavior.patch
mm-thp-add-flag-to-enforce-sysfs-thp-in-hugepage_vma_check.patch
mm-khugepaged-record-scan_pmd_mapped-when-scan_pmd-finds-hugepage.patch
mm-madvise-introduce-madv_collapse-sync-hugepage-collapse.patch
mm-khugepaged-rename-prefix-of-shared-collapse-functions.patch
mm-madvise-add-huge_memory-mm_madvise_collapse-tracepoint.patch
mm-madvise-add-madv_collapse-to-process_madvise.patch
proc-smaps-add-pmdmappable-field-to-smaps.patch
selftests-vm-modularize-collapse-selftests.patch
selftests-vm-dedup-hugepage-allocation-logic.patch
selftests-vm-add-madv_collapse-collapse-context-to-selftests.patch
selftests-vm-add-selftest-to-verify-recollapse-of-thps.patch
selftests-vm-add-selftest-to-verify-multi-thp-collapse.patch
