The patch titled
Subject: mm/madvise: clean up pte_offset_map_lock() scans
has been added to the -mm mm-unstable branch. Its filename is
mm-madvise-clean-up-pte_offset_map_lock-scans.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-madvise-clean-up-pte_offset_map_lock-scans.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: Hugh Dickins <hughd@xxxxxxxxxx>
Subject: mm/madvise: clean up pte_offset_map_lock() scans
Date: Thu, 8 Jun 2023 18:34:03 -0700 (PDT)
Came here to make madvise's several pte_offset_map_lock() scans advance to
next extent on failure, and remove superfluous pmd_trans_unstable() and
pmd_none_or_trans_huge_or_clear_bad() calls. But also did some nearby
cleanup.
swapin_walk_pmd_entry(): don't name an address "index"; don't drop the
lock after every pte, only when calling out to read_swap_cache_async().
madvise_cold_or_pageout_pte_range() and madvise_free_pte_range(): prefer
"start_pte" for pointer, orig_pte usually denotes a saved pte value; leave
lazy MMU mode before unlocking; merge the success and failure paths after
split_folio().
Link: https://lkml.kernel.org/r/cc4d9a88-9da6-362-50d9-6735c2b125c6@xxxxxxxxxx
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Alistair Popple <apopple@xxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: SeongJae Park <sj@xxxxxxxxxx>
Cc: Song Liu <song@xxxxxxxxxx>
Cc: Steven Price <steven.price@xxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Zack Rusin <zackr@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/madvise.c | 122 +++++++++++++++++++++++++++----------------------
1 file changed, 68 insertions(+), 54 deletions(-)
--- a/mm/madvise.c~mm-madvise-clean-up-pte_offset_map_lock-scans
+++ a/mm/madvise.c
@@ -188,37 +188,43 @@ success:
#ifdef CONFIG_SWAP
static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
- unsigned long end, struct mm_walk *walk)
+ unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->private;
- unsigned long index;
struct swap_iocb *splug = NULL;
+ pte_t *ptep = NULL;
+ spinlock_t *ptl;
+ unsigned long addr;
- if (pmd_none_or_trans_huge_or_clear_bad(pmd))
- return 0;
-
- for (index = start; index != end; index += PAGE_SIZE) {
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
pte_t pte;
swp_entry_t entry;
struct page *page;
- spinlock_t *ptl;
- pte_t *ptep;
- ptep = pte_offset_map_lock(vma->vm_mm, pmd, index, &ptl);
- pte = *ptep;
- pte_unmap_unlock(ptep, ptl);
+ if (!ptep++) {
+ ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!ptep)
+ break;
+ }
+ pte = *ptep;
if (!is_swap_pte(pte))
continue;
entry = pte_to_swp_entry(pte);
if (unlikely(non_swap_entry(entry)))
continue;
+ pte_unmap_unlock(ptep, ptl);
+ ptep = NULL;
+
page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
- vma, index, false, &splug);
+ vma, addr, false, &splug);
if (page)
put_page(page);
}
+
+ if (ptep)
+ pte_unmap_unlock(ptep, ptl);
swap_read_unplug(splug);
cond_resched();
@@ -340,7 +346,7 @@ static int madvise_cold_or_pageout_pte_r
bool pageout = private->pageout;
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
- pte_t *orig_pte, *pte, ptent;
+ pte_t *start_pte, *pte, ptent;
spinlock_t *ptl;
struct folio *folio = NULL;
LIST_HEAD(folio_list);
@@ -424,11 +430,11 @@ huge_unlock:
}
regular_folio:
- if (pmd_trans_unstable(pmd))
- return 0;
#endif
tlb_change_page_size(tlb, PAGE_SIZE);
- orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!start_pte)
+ return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
for (; addr < end; pte++, addr += PAGE_SIZE) {
@@ -449,25 +455,28 @@ regular_folio:
* are sure it's worth. Split it if we are only owner.
*/
if (folio_test_large(folio)) {
+ int err;
+
if (folio_mapcount(folio) != 1)
break;
if (pageout_anon_only_filter && !folio_test_anon(folio))
break;
- folio_get(folio);
- if (!folio_trylock(folio)) {
- folio_put(folio);
- break;
- }
- pte_unmap_unlock(orig_pte, ptl);
- if (split_folio(folio)) {
- folio_unlock(folio);
- folio_put(folio);
- orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!folio_trylock(folio))
break;
- }
+ folio_get(folio);
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ start_pte = NULL;
+ err = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
- orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (err)
+ break;
+ start_pte = pte =
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ break;
+ arch_enter_lazy_mmu_mode();
pte--;
addr -= PAGE_SIZE;
continue;
@@ -514,8 +523,10 @@ regular_folio:
folio_deactivate(folio);
}
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(orig_pte, ptl);
+ if (start_pte) {
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ }
if (pageout)
reclaim_pages(&folio_list);
cond_resched();
@@ -616,7 +627,7 @@ static int madvise_free_pte_range(pmd_t
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
- pte_t *orig_pte, *pte, ptent;
+ pte_t *start_pte, *pte, ptent;
struct folio *folio;
int nr_swap = 0;
unsigned long next;
@@ -624,13 +635,12 @@ static int madvise_free_pte_range(pmd_t
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd))
if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
- goto next;
-
- if (pmd_trans_unstable(pmd))
- return 0;
+ return 0;
tlb_change_page_size(tlb, PAGE_SIZE);
- orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -668,23 +678,26 @@ static int madvise_free_pte_range(pmd_t
* deactivate all pages.
*/
if (folio_test_large(folio)) {
+ int err;
+
if (folio_mapcount(folio) != 1)
- goto out;
+ break;
+ if (!folio_trylock(folio))
+ break;
folio_get(folio);
- if (!folio_trylock(folio)) {
- folio_put(folio);
- goto out;
- }
- pte_unmap_unlock(orig_pte, ptl);
- if (split_folio(folio)) {
- folio_unlock(folio);
- folio_put(folio);
- orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
- goto out;
- }
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ start_pte = NULL;
+ err = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
- orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (err)
+ break;
+ start_pte = pte =
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ break;
+ arch_enter_lazy_mmu_mode();
pte--;
addr -= PAGE_SIZE;
continue;
@@ -729,17 +742,18 @@ static int madvise_free_pte_range(pmd_t
}
folio_mark_lazyfree(folio);
}
-out:
+
if (nr_swap) {
if (current->mm == mm)
sync_mm_rss(mm);
-
add_mm_counter(mm, MM_SWAPENTS, nr_swap);
}
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(orig_pte, ptl);
+ if (start_pte) {
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ }
cond_resched();
-next:
+
return 0;
}
_
Patches currently in -mm which might be from hughd@xxxxxxxxxx are
arm-allow-pte_offset_map-to-fail.patch
arm64-allow-pte_offset_map-to-fail.patch
arm64-hugetlb-pte_alloc_huge-pte_offset_huge.patch
ia64-hugetlb-pte_alloc_huge-pte_offset_huge.patch
m68k-allow-pte_offset_map-to-fail.patch
microblaze-allow-pte_offset_map-to-fail.patch
mips-update_mmu_cache-can-replace-__update_tlb.patch
mips-update_mmu_cache-can-replace-__update_tlb-fix.patch
parisc-add-pte_unmap-to-balance-get_ptep.patch
parisc-unmap_uncached_pte-use-pte_offset_kernel.patch
parisc-hugetlb-pte_alloc_huge-pte_offset_huge.patch
powerpc-kvmppc_unmap_free_pmd-pte_offset_kernel.patch
powerpc-allow-pte_offset_map-to-fail.patch
powerpc-hugetlb-pte_alloc_huge.patch
riscv-hugetlb-pte_alloc_huge-pte_offset_huge.patch
s390-allow-pte_offset_map_lock-to-fail.patch
s390-gmap-use-pte_unmap_unlock-not-spin_unlock.patch
sh-hugetlb-pte_alloc_huge-pte_offset_huge.patch
sparc-hugetlb-pte_alloc_huge-pte_offset_huge.patch
sparc-allow-pte_offset_map-to-fail.patch
sparc-iounit-and-iommu-use-pte_offset_kernel.patch
x86-allow-get_locked_pte-to-fail.patch
x86-sme_populate_pgd-use-pte_offset_kernel.patch
xtensa-add-pte_unmap-to-balance-pte_offset_map.patch
mm-use-pmdp_get_lockless-without-surplus-barrier.patch
mm-migrate-remove-cruft-from-migration_entry_waits.patch
mm-pgtable-kmap_local_page-instead-of-kmap_atomic.patch
mm-pgtable-allow-pte_offset_map-to-fail.patch
mm-filemap-allow-pte_offset_map_lock-to-fail.patch
mm-page_vma_mapped-delete-bogosity-in-page_vma_mapped_walk.patch
mm-page_vma_mapped-reformat-map_pte-with-less-indentation.patch
mm-page_vma_mapped-pte_offset_map_nolock-not-pte_lockptr.patch
mm-pagewalkers-action_again-if-pte_offset_map_lock-fails.patch
mm-pagewalk-walk_pte_range-allow-for-pte_offset_map.patch
mm-vmwgfx-simplify-pmd-pud-mapping-dirty-helpers.patch
mm-vmalloc-vmalloc_to_page-use-pte_offset_kernel.patch
mm-hmm-retry-if-pte_offset_map-fails.patch
mm-userfaultfd-retry-if-pte_offset_map-fails.patch
mm-userfaultfd-allow-pte_offset_map_lock-to-fail.patch
mm-debug_vm_pgtablepage_table_check-warn-pte-map-fails.patch
mm-various-give-up-if-pte_offset_map-fails.patch
mm-mprotect-delete-pmd_none_or_clear_bad_unless_trans_huge.patch
mm-mremap-retry-if-either-pte_offset_map_lock-fails.patch
mm-madvise-clean-up-pte_offset_map_lock-scans.patch
mm-madvise-clean-up-force_shm_swapin_readahead.patch
mm-swapoff-allow-pte_offset_map-to-fail.patch
mm-mglru-allow-pte_offset_map_nolock-to-fail.patch
mm-migrate_device-allow-pte_offset_map_lock-to-fail.patch
mm-gup-remove-foll_split_pmd-use-of-pmd_trans_unstable.patch
mm-huge_memory-split-huge-pmd-under-one-pte_offset_map.patch
mm-khugepaged-allow-pte_offset_map-to-fail.patch
mm-memory-allow-pte_offset_map-to-fail.patch
mm-memory-handle_pte_fault-use-pte_offset_map_nolock.patch
mm-pgtable-delete-pmd_trans_unstable-and-friends.patch
mm-swap-swap_vma_readahead-do-the-pte_offset_map.patch
perf-core-allow-pte_offset_map-to-fail.patch
