The quilt patch titled
Subject: mm: handle some PMD faults under the VMA lock
has been removed from the -mm tree. Its filename was
mm-handle-some-pmd-faults-under-the-vma-lock.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Subject: mm: handle some PMD faults under the VMA lock
Date: Mon, 24 Jul 2023 19:54:05 +0100
Push the VMA_LOCK check down from __handle_mm_fault() to
handle_pte_fault(). Once again, we refuse to call ->huge_fault() with the
VMA lock held, but we will wait for a PMD migration entry with the VMA
lock held, handle NUMA migration and set the accessed bit. We were
already doing this for anonymous VMAs, so it should be safe.
Link: https://lkml.kernel.org/r/20230724185410.1124082-6-willy@xxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Arjun Roy <arjunroy@xxxxxxxxxx>
Cc: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Punit Agrawal <punit.agrawal@xxxxxxxxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory.c | 39 +++++++++++++++++++++++++--------------
1 file changed, 25 insertions(+), 14 deletions(-)
--- a/mm/memory.c~mm-handle-some-pmd-faults-under-the-vma-lock
+++ a/mm/memory.c
@@ -4821,36 +4821,47 @@ out_map:
static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
{
- if (vma_is_anonymous(vmf->vma))
+ struct vm_area_struct *vma = vmf->vma;
+ if (vma_is_anonymous(vma))
return do_huge_pmd_anonymous_page(vmf);
- if (vmf->vma->vm_ops->huge_fault)
- return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+ if (vma->vm_ops->huge_fault) {
+ if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
+ vma_end_read(vma);
+ return VM_FAULT_RETRY;
+ }
+ return vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+ }
return VM_FAULT_FALLBACK;
}
/* `inline' is required to avoid gcc 4.1.2 build error */
static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
vm_fault_t ret;
- if (vma_is_anonymous(vmf->vma)) {
+ if (vma_is_anonymous(vma)) {
if (likely(!unshare) &&
- userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
+ userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd))
return handle_userfault(vmf, VM_UFFD_WP);
return do_huge_pmd_wp_page(vmf);
}
- if (vmf->vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
- if (vmf->vma->vm_ops->huge_fault) {
- ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+ if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
+ if (vma->vm_ops->huge_fault) {
+ if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
+ vma_end_read(vma);
+ return VM_FAULT_RETRY;
+ }
+ ret = vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
}
}
/* COW or write-notify handled on pte level: split pmd. */
- __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
+ __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);
return VM_FAULT_FALLBACK;
}
@@ -4921,6 +4932,11 @@ static vm_fault_t handle_pte_fault(struc
{
pte_t entry;
+ if ((vmf->flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vmf->vma)) {
+ vma_end_read(vmf->vma);
+ return VM_FAULT_RETRY;
+ }
+
if (unlikely(pmd_none(*vmf->pmd))) {
/*
* Leave __pte_alloc() until later: because vm_ops->fault may
@@ -5060,11 +5076,6 @@ retry_pud:
if (pud_trans_unstable(vmf.pud))
goto retry_pud;
- if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma)) {
- vma_end_read(vma);
- return VM_FAULT_RETRY;
- }
-
if (pmd_none(*vmf.pmd) &&
hugepage_vma_check(vma, vm_flags, false, true, true)) {
ret = create_huge_pmd(&vmf);
_
Patches currently in -mm which might be from willy@xxxxxxxxxxxxx are
mm-drop-per-vma-lock-when-returning-vm_fault_retry-or-vm_fault_completed-fix.patch
zswap-make-zswap_store-take-a-folio.patch
memcg-convert-get_obj_cgroup_from_page-to-get_obj_cgroup_from_folio.patch
swap-remove-some-calls-to-compound_head-in-swap_readpage.patch
zswap-make-zswap_load-take-a-folio.patch
mm-improve-the-comment-in-isolate_migratepages_block.patch
minmax-add-in_range-macro.patch
mm-convert-page_table_check_pte_set-to-page_table_check_ptes_set.patch
mm-add-generic-flush_icache_pages-and-documentation.patch
mm-add-folio_flush_mapping.patch
mm-remove-arch_implements_flush_dcache_folio.patch
mm-add-default-definition-of-set_ptes.patch
alpha-implement-the-new-page-table-range-api.patch
arc-implement-the-new-page-table-range-api.patch
arm-implement-the-new-page-table-range-api.patch
arm64-implement-the-new-page-table-range-api.patch
csky-implement-the-new-page-table-range-api.patch
hexagon-implement-the-new-page-table-range-api.patch
ia64-implement-the-new-page-table-range-api.patch
ia64-implement-the-new-page-table-range-api-fix.patch
loongarch-implement-the-new-page-table-range-api.patch
m68k-implement-the-new-page-table-range-api.patch
microblaze-implement-the-new-page-table-range-api.patch
mips-implement-the-new-page-table-range-api.patch
nios2-implement-the-new-page-table-range-api.patch
openrisc-implement-the-new-page-table-range-api.patch
parisc-implement-the-new-page-table-range-api.patch
powerpc-implement-the-new-page-table-range-api.patch
powerpc-implement-the-new-page-table-range-api-fix.patch
riscv-implement-the-new-page-table-range-api.patch
s390-implement-the-new-page-table-range-api.patch
sh-implement-the-new-page-table-range-api.patch
sparc32-implement-the-new-page-table-range-api.patch
sparc64-implement-the-new-page-table-range-api.patch
um-implement-the-new-page-table-range-api.patch
x86-implement-the-new-page-table-range-api.patch
xtensa-implement-the-new-page-table-range-api.patch
mm-remove-page_mapping_file.patch
mm-rationalise-flush_icache_pages-and-flush_icache_page.patch
mm-tidy-up-set_ptes-definition.patch
mm-use-flush_icache_pages-in-do_set_pmd.patch
mm-call-update_mmu_cache_range-in-more-page-fault-handling-paths.patch
