The patch titled
Subject: mm: hugetlb: kill set_huge_swap_pte_at()
has been added to the -mm mm-unstable branch. Its filename is
mm-hugetlb-kill-set_huge_swap_pte_at.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hugetlb-kill-set_huge_swap_pte_at.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: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Subject: mm: hugetlb: kill set_huge_swap_pte_at()
Date: Sun, 26 Jun 2022 22:57:17 +0800
Commit e5251fd43007 ("mm/hugetlb: introduce set_huge_swap_pte_at()
helper") add set_huge_swap_pte_at() to handle swap entries on
architectures that support hugepages consisting of contiguous ptes. And
currently the set_huge_swap_pte_at() is only overridden by arm64.
set_huge_swap_pte_at() provide a sz parameter to help determine the number
of entries to be updated. But in fact, all hugetlb swap entries contain
pfn information, so we can find the corresponding folio through the pfn
recorded in the swap entry, then the folio_size() is the number of entries
that need to be updated.
And considering that users will easily cause bugs by ignoring the
difference between set_huge_swap_pte_at() and set_huge_pte_at(). Let's
handle swap entries in set_huge_pte_at() and remove the
set_huge_swap_pte_at(), then we can call set_huge_pte_at() anywhere, which
simplifies our coding.
Link: https://lkml.kernel.org/r/20220626145717.53572-1-zhengqi.arch@xxxxxxxxxxxxx
Signed-off-by: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/arm64/include/asm/hugetlb.h | 3 --
arch/arm64/mm/hugetlbpage.c | 34 ++++++++++++++---------------
include/linux/hugetlb.h | 13 -----------
mm/hugetlb.c | 8 ++----
mm/rmap.c | 11 ++-------
5 files changed, 23 insertions(+), 46 deletions(-)
--- a/arch/arm64/include/asm/hugetlb.h~mm-hugetlb-kill-set_huge_swap_pte_at
+++ a/arch/arm64/include/asm/hugetlb.h
@@ -46,9 +46,6 @@ extern void huge_pte_clear(struct mm_str
pte_t *ptep, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_GET
extern pte_t huge_ptep_get(pte_t *ptep);
-extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz);
-#define set_huge_swap_pte_at set_huge_swap_pte_at
void __init arm64_hugetlb_cma_reserve(void);
--- a/arch/arm64/mm/hugetlbpage.c~mm-hugetlb-kill-set_huge_swap_pte_at
+++ a/arch/arm64/mm/hugetlbpage.c
@@ -238,6 +238,13 @@ static void clear_flush(struct mm_struct
flush_tlb_range(&vma, saddr, addr);
}
+static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
+{
+ VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
+
+ return page_folio(pfn_to_page(swp_offset(entry)));
+}
+
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
@@ -247,11 +254,16 @@ void set_huge_pte_at(struct mm_struct *m
unsigned long pfn, dpfn;
pgprot_t hugeprot;
- /*
- * Code needs to be expanded to handle huge swap and migration
- * entries. Needed for HUGETLB and MEMORY_FAILURE.
- */
- WARN_ON(!pte_present(pte));
+ if (!pte_present(pte)) {
+ struct folio *folio;
+
+ folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte));
+ ncontig = num_contig_ptes(folio_size(folio), &pgsize);
+
+ for (i = 0; i < ncontig; i++, ptep++)
+ set_pte_at(mm, addr, ptep, pte);
+ return;
+ }
if (!pte_cont(pte)) {
set_pte_at(mm, addr, ptep, pte);
@@ -269,18 +281,6 @@ void set_huge_pte_at(struct mm_struct *m
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
}
-void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz)
-{
- int i, ncontig;
- size_t pgsize;
-
- ncontig = num_contig_ptes(sz, &pgsize);
-
- for (i = 0; i < ncontig; i++, ptep++)
- set_pte(ptep, pte);
-}
-
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long sz)
{
--- a/include/linux/hugetlb.h~mm-hugetlb-kill-set_huge_swap_pte_at
+++ a/include/linux/hugetlb.h
@@ -928,14 +928,6 @@ static inline void hugetlb_count_sub(lon
atomic_long_sub(l, &mm->hugetlb_usage);
}
-#ifndef set_huge_swap_pte_at
-static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz)
-{
- set_huge_pte_at(mm, addr, ptep, pte);
-}
-#endif
-
#ifndef huge_ptep_modify_prot_start
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
@@ -1119,11 +1111,6 @@ static inline void hugetlb_count_sub(lon
{
}
-static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz)
-{
-}
-
static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
--- a/mm/hugetlb.c~mm-hugetlb-kill-set_huge_swap_pte_at
+++ a/mm/hugetlb.c
@@ -4813,12 +4813,11 @@ again:
entry = swp_entry_to_pte(swp_entry);
if (userfaultfd_wp(src_vma) && uffd_wp)
entry = huge_pte_mkuffd_wp(entry);
- set_huge_swap_pte_at(src, addr, src_pte,
- entry, sz);
+ set_huge_pte_at(src, addr, src_pte, entry);
}
if (!userfaultfd_wp(dst_vma) && uffd_wp)
entry = huge_pte_clear_uffd_wp(entry);
- set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
+ set_huge_pte_at(dst, addr, dst_pte, entry);
} else if (unlikely(is_pte_marker(entry))) {
/*
* We copy the pte marker only if the dst vma has
@@ -6369,8 +6368,7 @@ unsigned long hugetlb_change_protection(
newpte = pte_swp_mkuffd_wp(newpte);
else if (uffd_wp_resolve)
newpte = pte_swp_clear_uffd_wp(newpte);
- set_huge_swap_pte_at(mm, address, ptep,
- newpte, psize);
+ set_huge_pte_at(mm, address, ptep, newpte);
pages++;
}
spin_unlock(ptl);
--- a/mm/rmap.c~mm-hugetlb-kill-set_huge_swap_pte_at
+++ a/mm/rmap.c
@@ -1618,9 +1618,7 @@ static bool try_to_unmap_one(struct foli
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);
- set_huge_swap_pte_at(mm, address,
- pvmw.pte, pteval,
- vma_mmu_pagesize(vma));
+ set_huge_pte_at(mm, address, pvmw.pte, pteval);
} else {
dec_mm_counter(mm, mm_counter(&folio->page));
set_pte_at(mm, address, pvmw.pte, pteval);
@@ -2011,9 +2009,7 @@ static bool try_to_migrate_one(struct fo
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);
- set_huge_swap_pte_at(mm, address,
- pvmw.pte, pteval,
- vma_mmu_pagesize(vma));
+ set_huge_pte_at(mm, address, pvmw.pte, pteval);
} else {
dec_mm_counter(mm, mm_counter(&folio->page));
set_pte_at(mm, address, pvmw.pte, pteval);
@@ -2081,8 +2077,7 @@ static bool try_to_migrate_one(struct fo
if (pte_uffd_wp(pteval))
swp_pte = pte_swp_mkuffd_wp(swp_pte);
if (folio_test_hugetlb(folio))
- set_huge_swap_pte_at(mm, address, pvmw.pte,
- swp_pte, vma_mmu_pagesize(vma));
+ set_huge_pte_at(mm, address, pvmw.pte, swp_pte);
else
set_pte_at(mm, address, pvmw.pte, swp_pte);
trace_set_migration_pte(address, pte_val(swp_pte),
_
Patches currently in -mm which might be from zhengqi.arch@xxxxxxxxxxxxx are
mm-hugetlb-kill-set_huge_swap_pte_at.patch
