The patch titled
Subject: hugetlb: do not update address in huge_pmd_unshare
has been added to the -mm mm-unstable branch. Its filename is
hugetlb-do-not-update-address-in-huge_pmd_unshare.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlb-do-not-update-address-in-huge_pmd_unshare.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: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlb: do not update address in huge_pmd_unshare
Date: Tue, 21 Jun 2022 16:56:19 -0700
As an optimization for loops sequentially processing hugetlb address
ranges, huge_pmd_unshare would update a passed address if it unshared a
pmd. Updating a loop control variable outside the loop like this is
generally a bad idea. These loops are now using hugetlb_mask_last_page to
optimize scanning when non-present ptes are discovered. The same can be
done when huge_pmd_unshare returns 1 indicating a pmd was unshared.
Remove address update from huge_pmd_unshare. Change the passed argument
type and update all callers. In loops sequentially processing addresses
use hugetlb_mask_last_page to update address if pmd is unshared.
Link: https://lkml.kernel.org/r/20220621235620.291305-4-mike.kravetz@xxxxxxxxxx
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Acked-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: James Houghton <jthoughton@xxxxxxxxxx>
Cc: kernel test robot <lkp@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Mina Almasry <almasrymina@xxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxxxx>
Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Rolf Eike Beer <eike-kernel@xxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 4 +--
mm/hugetlb.c | 46 +++++++++++++++-----------------------
mm/rmap.c | 4 +--
3 files changed, 23 insertions(+), 31 deletions(-)
--- a/include/linux/hugetlb.h~hugetlb-do-not-update-address-in-huge_pmd_unshare
+++ a/include/linux/hugetlb.h
@@ -199,7 +199,7 @@ pte_t *huge_pte_offset(struct mm_struct
unsigned long addr, unsigned long sz);
unsigned long hugetlb_mask_last_page(struct hstate *h);
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long *addr, pte_t *ptep);
+ unsigned long addr, pte_t *ptep);
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -246,7 +246,7 @@ static inline struct address_space *huge
static inline int huge_pmd_unshare(struct mm_struct *mm,
struct vm_area_struct *vma,
- unsigned long *addr, pte_t *ptep)
+ unsigned long addr, pte_t *ptep)
{
return 0;
}
--- a/mm/hugetlb.c~hugetlb-do-not-update-address-in-huge_pmd_unshare
+++ a/mm/hugetlb.c
@@ -4945,7 +4945,6 @@ int move_hugetlb_page_tables(struct vm_a
struct mm_struct *mm = vma->vm_mm;
unsigned long old_end = old_addr + len;
unsigned long last_addr_mask;
- unsigned long old_addr_copy;
pte_t *src_pte, *dst_pte;
struct mmu_notifier_range range;
bool shared_pmd = false;
@@ -4973,14 +4972,10 @@ int move_hugetlb_page_tables(struct vm_a
if (huge_pte_none(huge_ptep_get(src_pte)))
continue;
- /* old_addr arg to huge_pmd_unshare() is a pointer and so the
- * arg may be modified. Pass a copy instead to preserve the
- * value in old_addr.
- */
- old_addr_copy = old_addr;
-
- if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) {
+ if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) {
shared_pmd = true;
+ old_addr |= last_addr_mask;
+ new_addr |= last_addr_mask;
continue;
}
@@ -5045,10 +5040,11 @@ static void __unmap_hugepage_range(struc
}
ptl = huge_pte_lock(h, mm, ptep);
- if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+ if (huge_pmd_unshare(mm, vma, address, ptep)) {
spin_unlock(ptl);
tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
force_flush = true;
+ address |= last_addr_mask;
continue;
}
@@ -6337,7 +6333,7 @@ unsigned long hugetlb_change_protection(
continue;
}
ptl = huge_pte_lock(h, mm, ptep);
- if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+ if (huge_pmd_unshare(mm, vma, address, ptep)) {
/*
* When uffd-wp is enabled on the vma, unshare
* shouldn't happen at all. Warn about it if it
@@ -6347,6 +6343,7 @@ unsigned long hugetlb_change_protection(
pages++;
spin_unlock(ptl);
shared_pmd = true;
+ address |= last_addr_mask;
continue;
}
pte = huge_ptep_get(ptep);
@@ -6770,11 +6767,11 @@ out:
* 0 the underlying pte page is not shared, or it is the last user
*/
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long *addr, pte_t *ptep)
+ unsigned long addr, pte_t *ptep)
{
- pgd_t *pgd = pgd_offset(mm, *addr);
- p4d_t *p4d = p4d_offset(pgd, *addr);
- pud_t *pud = pud_offset(p4d, *addr);
+ pgd_t *pgd = pgd_offset(mm, addr);
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
i_mmap_assert_write_locked(vma->vm_file->f_mapping);
BUG_ON(page_count(virt_to_page(ptep)) == 0);
@@ -6784,14 +6781,6 @@ int huge_pmd_unshare(struct mm_struct *m
pud_clear(pud);
put_page(virt_to_page(ptep));
mm_dec_nr_pmds(mm);
- /*
- * This update of passed address optimizes loops sequentially
- * processing addresses in increments of huge page size (PMD_SIZE
- * in this case). By clearing the pud, a PUD_SIZE area is unmapped.
- * Update address to the 'last page' in the cleared area so that
- * calling loop can move to first page past this area.
- */
- *addr |= PUD_SIZE - PMD_SIZE;
return 1;
}
@@ -6803,7 +6792,7 @@ pte_t *huge_pmd_share(struct mm_struct *
}
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long *addr, pte_t *ptep)
+ unsigned long addr, pte_t *ptep)
{
return 0;
}
@@ -6910,6 +6899,12 @@ unsigned long hugetlb_mask_last_page(str
/* See description above. Architectures can provide their own version. */
__weak unsigned long hugetlb_mask_last_page(struct hstate *h)
{
+ unsigned long hp_size = huge_page_size(h);
+
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+ if (hp_size == PMD_SIZE)
+ return PUD_SIZE - PMD_SIZE;
+#endif
return 0UL;
}
@@ -7136,14 +7131,11 @@ void hugetlb_unshare_all_pmds(struct vm_
mmu_notifier_invalidate_range_start(&range);
i_mmap_lock_write(vma->vm_file->f_mapping);
for (address = start; address < end; address += PUD_SIZE) {
- unsigned long tmp = address;
-
ptep = huge_pte_offset(mm, address, sz);
if (!ptep)
continue;
ptl = huge_pte_lock(h, mm, ptep);
- /* We don't want 'address' to be changed */
- huge_pmd_unshare(mm, vma, &tmp, ptep);
+ huge_pmd_unshare(mm, vma, address, ptep);
spin_unlock(ptl);
}
flush_hugetlb_tlb_range(vma, start, end);
--- a/mm/rmap.c~hugetlb-do-not-update-address-in-huge_pmd_unshare
+++ a/mm/rmap.c
@@ -1559,7 +1559,7 @@ static bool try_to_unmap_one(struct foli
* do this outside rmap routines.
*/
VM_BUG_ON(!anon && !(flags & TTU_RMAP_LOCKED));
- if (!anon && huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
+ if (!anon && huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
flush_tlb_range(vma, range.start, range.end);
mmu_notifier_invalidate_range(mm, range.start,
range.end);
@@ -1922,7 +1922,7 @@ static bool try_to_migrate_one(struct fo
* do this outside rmap routines.
*/
VM_BUG_ON(!anon && !(flags & TTU_RMAP_LOCKED));
- if (!anon && huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
+ if (!anon && huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
flush_tlb_range(vma, range.start, range.end);
mmu_notifier_invalidate_range(mm, range.start,
range.end);
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlb-skip-to-end-of-pt-page-mapping-when-pte-not-present.patch
hugetlb-do-not-update-address-in-huge_pmd_unshare.patch
hugetlb-lazy-page-table-copies-in-fork.patch
