| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250814072045.3637192-5-mpenttil@redhat.com>
Date: Thu, 14 Aug 2025 10:19:28 +0300
From: Mika Penttilä <mpenttil@...hat.com>
To: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org,
Mika Penttilä <mpenttil@...hat.com>,
David Hildenbrand <david@...hat.com>,
Jason Gunthorpe <jgg@...dia.com>,
Leon Romanovsky <leonro@...dia.com>,
Alistair Popple <apopple@...dia.com>,
Balbir Singh <balbirs@...dia.com>
Subject: [RFC PATCH 3/4] mm:/migrate_device.c: remove migrate_vma_collect_*() functions
With the unified fault handling and migrate path,
the migrate_vma_collect_*() functions are unused,
let's remove them.
Cc: David Hildenbrand <david@...hat.com>
Cc: Jason Gunthorpe <jgg@...dia.com>
Cc: Leon Romanovsky <leonro@...dia.com>
Cc: Alistair Popple <apopple@...dia.com>
Cc: Balbir Singh <balbirs@...dia.com>
Signed-off-by: Mika Penttilä <mpenttil@...hat.com>
---
mm/migrate_device.c | 312 +-------------------------------------------
1 file changed, 1 insertion(+), 311 deletions(-)
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 87ddc0353165..0c84dfcd5058 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -15,319 +15,9 @@
#include <linux/rmap.h>
#include <linux/swapops.h>
#include <asm/tlbflush.h>
+#include <linux/hmm.h>
#include "internal.h"
-static int migrate_vma_collect_skip(unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
-{
- struct migrate_vma *migrate = walk->private;
- unsigned long addr;
-
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->dst[migrate->npages] = 0;
- migrate->src[migrate->npages++] = 0;
- }
-
- return 0;
-}
-
-static int migrate_vma_collect_hole(unsigned long start,
- unsigned long end,
- __always_unused int depth,
- struct mm_walk *walk)
-{
- struct migrate_vma *migrate = walk->private;
- unsigned long addr;
-
- /* Only allow populating anonymous memory. */
- if (!vma_is_anonymous(walk->vma))
- return migrate_vma_collect_skip(start, end, walk);
-
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
- migrate->dst[migrate->npages] = 0;
- migrate->npages++;
- migrate->cpages++;
- }
-
- return 0;
-}
-
-static int migrate_vma_collect_pmd(pmd_t *pmdp,
- unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
-{
- struct migrate_vma *migrate = walk->private;
- struct folio *fault_folio = migrate->fault_page ?
- page_folio(migrate->fault_page) : NULL;
- struct vm_area_struct *vma = walk->vma;
- struct mm_struct *mm = vma->vm_mm;
- unsigned long addr = start, unmapped = 0;
- spinlock_t *ptl;
- pte_t *ptep;
-
-again:
- if (pmd_none(*pmdp))
- return migrate_vma_collect_hole(start, end, -1, walk);
-
- if (pmd_trans_huge(*pmdp)) {
- struct folio *folio;
-
- ptl = pmd_lock(mm, pmdp);
- if (unlikely(!pmd_trans_huge(*pmdp))) {
- spin_unlock(ptl);
- goto again;
- }
-
- folio = pmd_folio(*pmdp);
- if (is_huge_zero_folio(folio)) {
- spin_unlock(ptl);
- split_huge_pmd(vma, pmdp, addr);
- } else {
- int ret;
-
- folio_get(folio);
- spin_unlock(ptl);
- /* FIXME: we don't expect THP for fault_folio */
- if (WARN_ON_ONCE(fault_folio == folio))
- return migrate_vma_collect_skip(start, end,
- walk);
- if (unlikely(!folio_trylock(folio)))
- return migrate_vma_collect_skip(start, end,
- walk);
- ret = split_folio(folio);
- if (fault_folio != folio)
- folio_unlock(folio);
- folio_put(folio);
- if (ret)
- return migrate_vma_collect_skip(start, end,
- walk);
- }
- }
-
- ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
- if (!ptep)
- goto again;
- arch_enter_lazy_mmu_mode();
-
- for (; addr < end; addr += PAGE_SIZE, ptep++) {
- struct dev_pagemap *pgmap;
- unsigned long mpfn = 0, pfn;
- struct folio *folio;
- struct page *page;
- swp_entry_t entry;
- pte_t pte;
-
- pte = ptep_get(ptep);
-
- if (pte_none(pte)) {
- if (vma_is_anonymous(vma)) {
- mpfn = MIGRATE_PFN_MIGRATE;
- migrate->cpages++;
- }
- goto next;
- }
-
- if (!pte_present(pte)) {
- /*
- * Only care about unaddressable device page special
- * page table entry. Other special swap entries are not
- * migratable, and we ignore regular swapped page.
- */
- entry = pte_to_swp_entry(pte);
- if (!is_device_private_entry(entry))
- goto next;
-
- page = pfn_swap_entry_to_page(entry);
- pgmap = page_pgmap(page);
- if (!(migrate->flags &
- MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
- pgmap->owner != migrate->pgmap_owner)
- goto next;
-
- mpfn = migrate_pfn(page_to_pfn(page)) |
- MIGRATE_PFN_MIGRATE;
- if (is_writable_device_private_entry(entry))
- mpfn |= MIGRATE_PFN_WRITE;
- } else {
- pfn = pte_pfn(pte);
- if (is_zero_pfn(pfn) &&
- (migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) {
- mpfn = MIGRATE_PFN_MIGRATE;
- migrate->cpages++;
- goto next;
- }
- page = vm_normal_page(migrate->vma, addr, pte);
- if (page && !is_zone_device_page(page) &&
- !(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) {
- goto next;
- } else if (page && is_device_coherent_page(page)) {
- pgmap = page_pgmap(page);
-
- if (!(migrate->flags &
- MIGRATE_VMA_SELECT_DEVICE_COHERENT) ||
- pgmap->owner != migrate->pgmap_owner)
- goto next;
- }
- mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
- mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
- }
-
- /* FIXME support THP */
- if (!page || !page->mapping || PageTransCompound(page)) {
- mpfn = 0;
- goto next;
- }
-
- /*
- * By getting a reference on the folio we pin it and that blocks
- * any kind of migration. Side effect is that it "freezes" the
- * pte.
- *
- * We drop this reference after isolating the folio from the lru
- * for non device folio (device folio are not on the lru and thus
- * can't be dropped from it).
- */
- folio = page_folio(page);
- folio_get(folio);
-
- /*
- * We rely on folio_trylock() to avoid deadlock between
- * concurrent migrations where each is waiting on the others
- * folio lock. If we can't immediately lock the folio we fail this
- * migration as it is only best effort anyway.
- *
- * If we can lock the folio it's safe to set up a migration entry
- * now. In the common case where the folio is mapped once in a
- * single process setting up the migration entry now is an
- * optimisation to avoid walking the rmap later with
- * try_to_migrate().
- */
- if (fault_folio == folio || folio_trylock(folio)) {
- bool anon_exclusive;
- pte_t swp_pte;
-
- flush_cache_page(vma, addr, pte_pfn(pte));
- anon_exclusive = folio_test_anon(folio) &&
- PageAnonExclusive(page);
- if (anon_exclusive) {
- pte = ptep_clear_flush(vma, addr, ptep);
-
- if (folio_try_share_anon_rmap_pte(folio, page)) {
- set_pte_at(mm, addr, ptep, pte);
- if (fault_folio != folio)
- folio_unlock(folio);
- folio_put(folio);
- mpfn = 0;
- goto next;
- }
- } else {
- pte = ptep_get_and_clear(mm, addr, ptep);
- }
-
- migrate->cpages++;
-
- /* Set the dirty flag on the folio now the pte is gone. */
- if (pte_dirty(pte))
- folio_mark_dirty(folio);
-
- /* Setup special migration page table entry */
- if (mpfn & MIGRATE_PFN_WRITE)
- entry = make_writable_migration_entry(
- page_to_pfn(page));
- else if (anon_exclusive)
- entry = make_readable_exclusive_migration_entry(
- page_to_pfn(page));
- else
- entry = make_readable_migration_entry(
- page_to_pfn(page));
- if (pte_present(pte)) {
- if (pte_young(pte))
- entry = make_migration_entry_young(entry);
- if (pte_dirty(pte))
- entry = make_migration_entry_dirty(entry);
- }
- swp_pte = swp_entry_to_pte(entry);
- if (pte_present(pte)) {
- if (pte_soft_dirty(pte))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_uffd_wp(pte))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- } else {
- if (pte_swp_soft_dirty(pte))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_swp_uffd_wp(pte))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- }
- set_pte_at(mm, addr, ptep, swp_pte);
-
- /*
- * This is like regular unmap: we remove the rmap and
- * drop the folio refcount. The folio won't be freed, as
- * we took a reference just above.
- */
- folio_remove_rmap_pte(folio, page, vma);
- folio_put(folio);
-
- if (pte_present(pte))
- unmapped++;
- } else {
- folio_put(folio);
- mpfn = 0;
- }
-
-next:
- migrate->dst[migrate->npages] = 0;
- migrate->src[migrate->npages++] = mpfn;
- }
-
- /* Only flush the TLB if we actually modified any entries */
- if (unmapped)
- flush_tlb_range(walk->vma, start, end);
-
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(ptep - 1, ptl);
-
- return 0;
-}
-
-static const struct mm_walk_ops migrate_vma_walk_ops = {
- .pmd_entry = migrate_vma_collect_pmd,
- .pte_hole = migrate_vma_collect_hole,
- .walk_lock = PGWALK_RDLOCK,
-};
-
-/*
- * migrate_vma_collect() - collect pages over a range of virtual addresses
- * @migrate: migrate struct containing all migration information
- *
- * This will walk the CPU page table. For each virtual address backed by a
- * valid page, it updates the src array and takes a reference on the page, in
- * order to pin the page until we lock it and unmap it.
- */
-static void migrate_vma_collect(struct migrate_vma *migrate)
-{
- struct mmu_notifier_range range;
-
- /*
- * Note that the pgmap_owner is passed to the mmu notifier callback so
- * that the registered device driver can skip invalidating device
- * private page mappings that won't be migrated.
- */
- mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0,
- migrate->vma->vm_mm, migrate->start, migrate->end,
- migrate->pgmap_owner);
- mmu_notifier_invalidate_range_start(&range);
-
- walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end,
- &migrate_vma_walk_ops, migrate);
-
- mmu_notifier_invalidate_range_end(&range);
- migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT);
-}
-
/*
* migrate_vma_check_page() - check if page is pinned or not
* @page: struct page to check
--
2.50.0
Powered by blists - more mailing lists