mm/khugepaged: dedup and simplify hugepage alloc and charging
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@google.com Signed-off-by: Zach O'Keefe <zokeefe@google.com> Suggested-by: Peter Xu <peterx@redhat.com> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Chris Kennelly <ckennelly@google.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Hildenbrand <david@redhat.com> Cc: Helge Deller <deller@gmx.de> Cc: Hugh Dickins <hughd@google.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Pavel Begunkov <asml.silence@gmail.com> Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <songliubraving@fb.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Zi Yan <ziy@nvidia.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: "Souptick Joarder (HPE)" <jrdr.linux@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Родитель
34d6b470ab
Коммит
9710a78ab2
|
@ -813,19 +813,18 @@ static int khugepaged_find_target_node(struct collapse_control *cc)
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
static struct page *
|
static bool khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
|
||||||
khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
|
|
||||||
{
|
{
|
||||||
*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
|
*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
|
||||||
if (unlikely(!*hpage)) {
|
if (unlikely(!*hpage)) {
|
||||||
count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
|
count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
|
||||||
*hpage = ERR_PTR(-ENOMEM);
|
*hpage = ERR_PTR(-ENOMEM);
|
||||||
return NULL;
|
return false;
|
||||||
}
|
}
|
||||||
|
|
||||||
prep_transhuge_page(*hpage);
|
prep_transhuge_page(*hpage);
|
||||||
count_vm_event(THP_COLLAPSE_ALLOC);
|
count_vm_event(THP_COLLAPSE_ALLOC);
|
||||||
return *hpage;
|
return true;
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
@ -923,10 +922,24 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
|
||||||
static void collapse_huge_page(struct mm_struct *mm,
|
static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
|
||||||
unsigned long address,
|
struct collapse_control *cc)
|
||||||
struct page **hpage,
|
{
|
||||||
int node, int referenced, int unmapped)
|
/* 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);
|
LIST_HEAD(compound_pagelist);
|
||||||
pmd_t *pmd, _pmd;
|
pmd_t *pmd, _pmd;
|
||||||
|
@ -937,13 +950,9 @@ static void collapse_huge_page(struct mm_struct *mm,
|
||||||
int isolated = 0, result = 0;
|
int isolated = 0, result = 0;
|
||||||
struct vm_area_struct *vma;
|
struct vm_area_struct *vma;
|
||||||
struct mmu_notifier_range range;
|
struct mmu_notifier_range range;
|
||||||
gfp_t gfp;
|
|
||||||
|
|
||||||
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
|
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.
|
* Before allocating the hugepage, release the mmap_lock read lock.
|
||||||
* The allocation can take potentially a long time if it involves
|
* The allocation can take potentially a long time if it involves
|
||||||
|
@ -951,17 +960,12 @@ static void collapse_huge_page(struct mm_struct *mm,
|
||||||
* that. We will recheck the vma after taking it again in write mode.
|
* that. We will recheck the vma after taking it again in write mode.
|
||||||
*/
|
*/
|
||||||
mmap_read_unlock(mm);
|
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 = alloc_charge_hpage(hpage, mm, cc);
|
||||||
result = SCAN_CGROUP_CHARGE_FAIL;
|
if (result != SCAN_SUCCEED)
|
||||||
goto out_nolock;
|
goto out_nolock;
|
||||||
}
|
|
||||||
count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
|
new_page = *hpage;
|
||||||
|
|
||||||
mmap_read_lock(mm);
|
mmap_read_lock(mm);
|
||||||
result = hugepage_vma_revalidate(mm, address, &vma);
|
result = hugepage_vma_revalidate(mm, address, &vma);
|
||||||
|
@ -1235,10 +1239,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
|
||||||
out_unmap:
|
out_unmap:
|
||||||
pte_unmap_unlock(pte, ptl);
|
pte_unmap_unlock(pte, ptl);
|
||||||
if (ret) {
|
if (ret) {
|
||||||
node = khugepaged_find_target_node(cc);
|
|
||||||
/* collapse_huge_page will return with the mmap_lock released */
|
/* collapse_huge_page will return with the mmap_lock released */
|
||||||
collapse_huge_page(mm, address, hpage, node,
|
collapse_huge_page(mm, address, hpage, referenced, unmapped,
|
||||||
referenced, unmapped);
|
cc);
|
||||||
}
|
}
|
||||||
out:
|
out:
|
||||||
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
|
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
|
||||||
|
@ -1506,7 +1509,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
|
||||||
* @file: file that collapse on
|
* @file: file that collapse on
|
||||||
* @start: collapse start address
|
* @start: collapse start address
|
||||||
* @hpage: new allocated huge page for collapse
|
* @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:
|
* Basic scheme is simple, details are more complex:
|
||||||
* - allocate and lock a new huge page;
|
* - allocate and lock a new huge page;
|
||||||
|
@ -1523,12 +1526,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
|
||||||
* + restore gaps in the page cache;
|
* + restore gaps in the page cache;
|
||||||
* + unlock and free huge page;
|
* + unlock and free huge page;
|
||||||
*/
|
*/
|
||||||
static void collapse_file(struct mm_struct *mm,
|
static void collapse_file(struct mm_struct *mm, struct file *file,
|
||||||
struct file *file, pgoff_t start,
|
pgoff_t start, struct page **hpage,
|
||||||
struct page **hpage, int node)
|
struct collapse_control *cc)
|
||||||
{
|
{
|
||||||
struct address_space *mapping = file->f_mapping;
|
struct address_space *mapping = file->f_mapping;
|
||||||
gfp_t gfp;
|
|
||||||
struct page *new_page;
|
struct page *new_page;
|
||||||
pgoff_t index, end = start + HPAGE_PMD_NR;
|
pgoff_t index, end = start + HPAGE_PMD_NR;
|
||||||
LIST_HEAD(pagelist);
|
LIST_HEAD(pagelist);
|
||||||
|
@ -1540,20 +1542,11 @@ static void collapse_file(struct mm_struct *mm,
|
||||||
VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
|
VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
|
||||||
VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
|
VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
|
||||||
|
|
||||||
/* Only allocate from the target node */
|
result = alloc_charge_hpage(hpage, mm, cc);
|
||||||
gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
|
if (result != SCAN_SUCCEED)
|
||||||
|
|
||||||
new_page = khugepaged_alloc_page(hpage, gfp, node);
|
|
||||||
if (!new_page) {
|
|
||||||
result = SCAN_ALLOC_HUGE_PAGE_FAIL;
|
|
||||||
goto out;
|
goto out;
|
||||||
}
|
|
||||||
|
|
||||||
if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
|
new_page = *hpage;
|
||||||
result = SCAN_CGROUP_CHARGE_FAIL;
|
|
||||||
goto out;
|
|
||||||
}
|
|
||||||
count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
|
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Ensure we have slots for all the pages in the range. This is
|
* Ensure we have slots for all the pages in the range. This is
|
||||||
|
@ -1965,8 +1958,7 @@ static void khugepaged_scan_file(struct mm_struct *mm, struct file *file,
|
||||||
result = SCAN_EXCEED_NONE_PTE;
|
result = SCAN_EXCEED_NONE_PTE;
|
||||||
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
|
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
|
||||||
} else {
|
} else {
|
||||||
node = khugepaged_find_target_node(cc);
|
collapse_file(mm, file, start, hpage, cc);
|
||||||
collapse_file(mm, file, start, hpage, node);
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
Загрузка…
Ссылка в новой задаче