| 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: <aLC2bfpIQo/a22gr@lstrano-desk.jf.intel.com>
Date: Thu, 28 Aug 2025 13:05:01 -0700
From: Matthew Brost <matthew.brost@...el.com>
To: Balbir Singh <balbirs@...dia.com>
CC: <dri-devel@...ts.freedesktop.org>, <linux-mm@...ck.org>,
<linux-kernel@...r.kernel.org>, Andrew Morton <akpm@...ux-foundation.org>,
David Hildenbrand <david@...hat.com>, Zi Yan <ziy@...dia.com>, Joshua Hahn
<joshua.hahnjy@...il.com>, Rakie Kim <rakie.kim@...com>, Byungchul Park
<byungchul@...com>, Gregory Price <gourry@...rry.net>, Ying Huang
<ying.huang@...ux.alibaba.com>, Alistair Popple <apopple@...dia.com>, "Oscar
Salvador" <osalvador@...e.de>, Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>, "Liam R. Howlett"
<Liam.Howlett@...cle.com>, Nico Pache <npache@...hat.com>, Ryan Roberts
<ryan.roberts@....com>, Dev Jain <dev.jain@....com>, Barry Song
<baohua@...nel.org>, Lyude Paul <lyude@...hat.com>, Danilo Krummrich
<dakr@...nel.org>, David Airlie <airlied@...il.com>, Simona Vetter
<simona@...ll.ch>, Ralph Campbell <rcampbell@...dia.com>, Mika
Penttilä <mpenttil@...hat.com>, Francois Dugast
<francois.dugast@...el.com>
Subject: Re: [v3 02/11] mm/thp: zone_device awareness in THP handling code
On Tue, Aug 12, 2025 at 12:40:27PM +1000, Balbir Singh wrote:
> Make THP handling code in the mm subsystem for THP pages aware of zone
> device pages. Although the code is designed to be generic when it comes
> to handling splitting of pages, the code is designed to work for THP
> page sizes corresponding to HPAGE_PMD_NR.
>
> Modify page_vma_mapped_walk() to return true when a zone device huge
> entry is present, enabling try_to_migrate() and other code migration
> paths to appropriately process the entry. page_vma_mapped_walk() will
> return true for zone device private large folios only when
> PVMW_THP_DEVICE_PRIVATE is passed. This is to prevent locations that are
> not zone device private pages from having to add awareness. The key
> callback that needs this flag is try_to_migrate_one(). The other
> callbacks page idle, damon use it for setting young/dirty bits, which is
> not significant when it comes to pmd level bit harvesting.
>
> pmd_pfn() does not work well with zone device entries, use
> pfn_pmd_entry_to_swap() for checking and comparison as for zone device
> entries.
>
> Support partial unmapping of zone device private entries, which happens
> via munmap(). munmap() causes the device private entry pmd to be split,
> but the corresponding folio is not split. Deferred split does not work for
> zone device private folios due to the need to split during fault
> handling. Get migrate_vma_collect_pmd() to handle this case by splitting
> partially unmapped device private folios.
>
> Cc: Andrew Morton <akpm@...ux-foundation.org>
> Cc: David Hildenbrand <david@...hat.com>
> Cc: Zi Yan <ziy@...dia.com>
> Cc: Joshua Hahn <joshua.hahnjy@...il.com>
> Cc: Rakie Kim <rakie.kim@...com>
> Cc: Byungchul Park <byungchul@...com>
> Cc: Gregory Price <gourry@...rry.net>
> Cc: Ying Huang <ying.huang@...ux.alibaba.com>
> Cc: Alistair Popple <apopple@...dia.com>
> Cc: Oscar Salvador <osalvador@...e.de>
> Cc: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
> Cc: Baolin Wang <baolin.wang@...ux.alibaba.com>
> Cc: "Liam R. Howlett" <Liam.Howlett@...cle.com>
> Cc: Nico Pache <npache@...hat.com>
> Cc: Ryan Roberts <ryan.roberts@....com>
> Cc: Dev Jain <dev.jain@....com>
> Cc: Barry Song <baohua@...nel.org>
> Cc: Lyude Paul <lyude@...hat.com>
> Cc: Danilo Krummrich <dakr@...nel.org>
> Cc: David Airlie <airlied@...il.com>
> Cc: Simona Vetter <simona@...ll.ch>
> Cc: Ralph Campbell <rcampbell@...dia.com>
> Cc: Mika Penttilä <mpenttil@...hat.com>
> Cc: Matthew Brost <matthew.brost@...el.com>
> Cc: Francois Dugast <francois.dugast@...el.com>
>
> Signed-off-by: Matthew Brost <matthew.brost@...el.com>
> Signed-off-by: Balbir Singh <balbirs@...dia.com>
> ---
> include/linux/rmap.h | 2 +
> include/linux/swapops.h | 17 ++++
> lib/test_hmm.c | 2 +-
> mm/huge_memory.c | 214 +++++++++++++++++++++++++++++++---------
> mm/migrate_device.c | 47 +++++++++
> mm/page_vma_mapped.c | 13 ++-
> mm/pgtable-generic.c | 6 ++
> mm/rmap.c | 24 ++++-
> 8 files changed, 272 insertions(+), 53 deletions(-)
>
> diff --git a/include/linux/rmap.h b/include/linux/rmap.h
> index 6cd020eea37a..dfb7aae3d77b 100644
> --- a/include/linux/rmap.h
> +++ b/include/linux/rmap.h
> @@ -927,6 +927,8 @@ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
> #define PVMW_SYNC (1 << 0)
> /* Look for migration entries rather than present PTEs */
> #define PVMW_MIGRATION (1 << 1)
> +/* Look for device private THP entries */
> +#define PVMW_THP_DEVICE_PRIVATE (1 << 2)
>
> struct page_vma_mapped_walk {
> unsigned long pfn;
> diff --git a/include/linux/swapops.h b/include/linux/swapops.h
> index 64ea151a7ae3..2641c01bd5d2 100644
> --- a/include/linux/swapops.h
> +++ b/include/linux/swapops.h
> @@ -563,6 +563,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
> {
> return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
> }
> +
> #else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
> static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
> struct page *page)
> @@ -594,6 +595,22 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
> }
> #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
>
> +#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_ARCH_ENABLE_THP_MIGRATION)
> +
> +static inline int is_pmd_device_private_entry(pmd_t pmd)
> +{
> + return is_swap_pmd(pmd) && is_device_private_entry(pmd_to_swp_entry(pmd));
> +}
> +
> +#else /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
> +
> +static inline int is_pmd_device_private_entry(pmd_t pmd)
> +{
> + return 0;
> +}
> +
> +#endif /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
> +
> static inline int non_swap_entry(swp_entry_t entry)
> {
> return swp_type(entry) >= MAX_SWAPFILES;
> diff --git a/lib/test_hmm.c b/lib/test_hmm.c
> index 761725bc713c..297f1e034045 100644
> --- a/lib/test_hmm.c
> +++ b/lib/test_hmm.c
> @@ -1408,7 +1408,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
> * the mirror but here we use it to hold the page for the simulated
> * device memory and that page holds the pointer to the mirror.
> */
> - rpage = vmf->page->zone_device_data;
> + rpage = folio_page(page_folio(vmf->page), 0)->zone_device_data;
> dmirror = rpage->zone_device_data;
>
> /* FIXME demonstrate how we can adjust migrate range */
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 9c38a95e9f09..2495e3fdbfae 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1711,8 +1711,11 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> if (unlikely(is_swap_pmd(pmd))) {
> swp_entry_t entry = pmd_to_swp_entry(pmd);
>
> - VM_BUG_ON(!is_pmd_migration_entry(pmd));
> - if (!is_readable_migration_entry(entry)) {
> + VM_WARN_ON(!is_pmd_migration_entry(pmd) &&
> + !is_pmd_device_private_entry(pmd));
> +
> + if (is_migration_entry(entry) &&
> + is_writable_migration_entry(entry)) {
> entry = make_readable_migration_entry(
> swp_offset(entry));
> pmd = swp_entry_to_pmd(entry);
> @@ -1722,6 +1725,32 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> pmd = pmd_swp_mkuffd_wp(pmd);
> set_pmd_at(src_mm, addr, src_pmd, pmd);
> }
> +
> + if (is_device_private_entry(entry)) {
> + if (is_writable_device_private_entry(entry)) {
> + entry = make_readable_device_private_entry(
> + swp_offset(entry));
> + pmd = swp_entry_to_pmd(entry);
> +
> + if (pmd_swp_soft_dirty(*src_pmd))
> + pmd = pmd_swp_mksoft_dirty(pmd);
> + if (pmd_swp_uffd_wp(*src_pmd))
> + pmd = pmd_swp_mkuffd_wp(pmd);
> + set_pmd_at(src_mm, addr, src_pmd, pmd);
> + }
> +
> + src_folio = pfn_swap_entry_folio(entry);
> + VM_WARN_ON(!folio_test_large(src_folio));
> +
> + folio_get(src_folio);
> + /*
> + * folio_try_dup_anon_rmap_pmd does not fail for
> + * device private entries.
> + */
> + VM_WARN_ON(folio_try_dup_anon_rmap_pmd(src_folio,
> + &src_folio->page, dst_vma, src_vma));
VM_WARN_ON compiles out in non-debug builds. I hit this running the
fork self I shared with a non-debug build.
Matt
[1] https://elixir.bootlin.com/linux/v6.16.3/source/include/linux/mmdebug.h#L112
> + }
> +
> add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
> mm_inc_nr_ptes(dst_mm);
> pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
> @@ -2219,15 +2248,22 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
> folio_remove_rmap_pmd(folio, page, vma);
> WARN_ON_ONCE(folio_mapcount(folio) < 0);
> VM_BUG_ON_PAGE(!PageHead(page), page);
> - } else if (thp_migration_supported()) {
> + } else if (is_pmd_migration_entry(orig_pmd) ||
> + is_pmd_device_private_entry(orig_pmd)) {
> swp_entry_t entry;
>
> - VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
> entry = pmd_to_swp_entry(orig_pmd);
> folio = pfn_swap_entry_folio(entry);
> flush_needed = 0;
> - } else
> - WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
> +
> + if (!thp_migration_supported())
> + WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
> +
> + if (is_pmd_device_private_entry(orig_pmd)) {
> + folio_remove_rmap_pmd(folio, &folio->page, vma);
> + WARN_ON_ONCE(folio_mapcount(folio) < 0);
> + }
> + }
>
> if (folio_test_anon(folio)) {
> zap_deposited_table(tlb->mm, pmd);
> @@ -2247,6 +2283,15 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
> folio_mark_accessed(folio);
> }
>
> + /*
> + * Do a folio put on zone device private pages after
> + * changes to mm_counter, because the folio_put() will
> + * clean folio->mapping and the folio_test_anon() check
> + * will not be usable.
> + */
> + if (folio_is_device_private(folio))
> + folio_put(folio);
> +
> spin_unlock(ptl);
> if (flush_needed)
> tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE);
> @@ -2375,7 +2420,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
> struct folio *folio = pfn_swap_entry_folio(entry);
> pmd_t newpmd;
>
> - VM_BUG_ON(!is_pmd_migration_entry(*pmd));
> + VM_WARN_ON(!is_pmd_migration_entry(*pmd) &&
> + !folio_is_device_private(folio));
> if (is_writable_migration_entry(entry)) {
> /*
> * A protection check is difficult so
> @@ -2388,6 +2434,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
> newpmd = swp_entry_to_pmd(entry);
> if (pmd_swp_soft_dirty(*pmd))
> newpmd = pmd_swp_mksoft_dirty(newpmd);
> + } else if (is_writable_device_private_entry(entry)) {
> + entry = make_readable_device_private_entry(
> + swp_offset(entry));
> + newpmd = swp_entry_to_pmd(entry);
> } else {
> newpmd = *pmd;
> }
> @@ -2842,16 +2892,19 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
> struct page *page;
> pgtable_t pgtable;
> pmd_t old_pmd, _pmd;
> - bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
> - bool anon_exclusive = false, dirty = false;
> + bool young, write, soft_dirty, uffd_wp = false;
> + bool anon_exclusive = false, dirty = false, present = false;
> unsigned long addr;
> pte_t *pte;
> int i;
> + swp_entry_t swp_entry;
>
> VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
> VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
> VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
> - VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd));
> +
> + VM_WARN_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
> + && !(is_pmd_device_private_entry(*pmd)));
>
> count_vm_event(THP_SPLIT_PMD);
>
> @@ -2899,18 +2952,45 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
> return __split_huge_zero_page_pmd(vma, haddr, pmd);
> }
>
> - pmd_migration = is_pmd_migration_entry(*pmd);
> - if (unlikely(pmd_migration)) {
> - swp_entry_t entry;
>
> + present = pmd_present(*pmd);
> + if (unlikely(!present)) {
> + swp_entry = pmd_to_swp_entry(*pmd);
> old_pmd = *pmd;
> - entry = pmd_to_swp_entry(old_pmd);
> - page = pfn_swap_entry_to_page(entry);
> - write = is_writable_migration_entry(entry);
> - if (PageAnon(page))
> - anon_exclusive = is_readable_exclusive_migration_entry(entry);
> - young = is_migration_entry_young(entry);
> - dirty = is_migration_entry_dirty(entry);
> +
> + folio = pfn_swap_entry_folio(swp_entry);
> + VM_WARN_ON(!is_migration_entry(swp_entry) &&
> + !is_device_private_entry(swp_entry));
> + page = pfn_swap_entry_to_page(swp_entry);
> +
> + if (is_pmd_migration_entry(old_pmd)) {
> + write = is_writable_migration_entry(swp_entry);
> + if (PageAnon(page))
> + anon_exclusive =
> + is_readable_exclusive_migration_entry(
> + swp_entry);
> + young = is_migration_entry_young(swp_entry);
> + dirty = is_migration_entry_dirty(swp_entry);
> + } else if (is_pmd_device_private_entry(old_pmd)) {
> + write = is_writable_device_private_entry(swp_entry);
> + anon_exclusive = PageAnonExclusive(page);
> + if (freeze && anon_exclusive &&
> + folio_try_share_anon_rmap_pmd(folio, page))
> + freeze = false;
> + if (!freeze) {
> + rmap_t rmap_flags = RMAP_NONE;
> +
> + if (anon_exclusive)
> + rmap_flags |= RMAP_EXCLUSIVE;
> +
> + folio_ref_add(folio, HPAGE_PMD_NR - 1);
> + if (anon_exclusive)
> + rmap_flags |= RMAP_EXCLUSIVE;
> + folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
> + vma, haddr, rmap_flags);
> + }
> + }
> +
> soft_dirty = pmd_swp_soft_dirty(old_pmd);
> uffd_wp = pmd_swp_uffd_wp(old_pmd);
> } else {
> @@ -2996,30 +3076,49 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
> * Note that NUMA hinting access restrictions are not transferred to
> * avoid any possibility of altering permissions across VMAs.
> */
> - if (freeze || pmd_migration) {
> + if (freeze || !present) {
> for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
> pte_t entry;
> - swp_entry_t swp_entry;
> -
> - if (write)
> - swp_entry = make_writable_migration_entry(
> - page_to_pfn(page + i));
> - else if (anon_exclusive)
> - swp_entry = make_readable_exclusive_migration_entry(
> - page_to_pfn(page + i));
> - else
> - swp_entry = make_readable_migration_entry(
> - page_to_pfn(page + i));
> - if (young)
> - swp_entry = make_migration_entry_young(swp_entry);
> - if (dirty)
> - swp_entry = make_migration_entry_dirty(swp_entry);
> - entry = swp_entry_to_pte(swp_entry);
> - if (soft_dirty)
> - entry = pte_swp_mksoft_dirty(entry);
> - if (uffd_wp)
> - entry = pte_swp_mkuffd_wp(entry);
> -
> + if (freeze || is_migration_entry(swp_entry)) {
> + if (write)
> + swp_entry = make_writable_migration_entry(
> + page_to_pfn(page + i));
> + else if (anon_exclusive)
> + swp_entry = make_readable_exclusive_migration_entry(
> + page_to_pfn(page + i));
> + else
> + swp_entry = make_readable_migration_entry(
> + page_to_pfn(page + i));
> + if (young)
> + swp_entry = make_migration_entry_young(swp_entry);
> + if (dirty)
> + swp_entry = make_migration_entry_dirty(swp_entry);
> + entry = swp_entry_to_pte(swp_entry);
> + if (soft_dirty)
> + entry = pte_swp_mksoft_dirty(entry);
> + if (uffd_wp)
> + entry = pte_swp_mkuffd_wp(entry);
> + } else {
> + /*
> + * anon_exclusive was already propagated to the relevant
> + * pages corresponding to the pte entries when freeze
> + * is false.
> + */
> + if (write)
> + swp_entry = make_writable_device_private_entry(
> + page_to_pfn(page + i));
> + else
> + swp_entry = make_readable_device_private_entry(
> + page_to_pfn(page + i));
> + /*
> + * Young and dirty bits are not progated via swp_entry
> + */
> + entry = swp_entry_to_pte(swp_entry);
> + if (soft_dirty)
> + entry = pte_swp_mksoft_dirty(entry);
> + if (uffd_wp)
> + entry = pte_swp_mkuffd_wp(entry);
> + }
> VM_WARN_ON(!pte_none(ptep_get(pte + i)));
> set_pte_at(mm, addr, pte + i, entry);
> }
> @@ -3046,7 +3145,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
> }
> pte_unmap(pte);
>
> - if (!pmd_migration)
> + if (present)
> folio_remove_rmap_pmd(folio, page, vma);
> if (freeze)
> put_page(page);
> @@ -3058,8 +3157,10 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
> void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
> pmd_t *pmd, bool freeze)
> {
> +
> VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
> - if (pmd_trans_huge(*pmd) || is_pmd_migration_entry(*pmd))
> + if (pmd_trans_huge(*pmd) || is_pmd_migration_entry(*pmd) ||
> + (is_pmd_device_private_entry(*pmd)))
> __split_huge_pmd_locked(vma, pmd, address, freeze);
> }
>
> @@ -3238,6 +3339,9 @@ static void lru_add_split_folio(struct folio *folio, struct folio *new_folio,
> VM_BUG_ON_FOLIO(folio_test_lru(new_folio), folio);
> lockdep_assert_held(&lruvec->lru_lock);
>
> + if (folio_is_device_private(folio))
> + return;
> +
> if (list) {
> /* page reclaim is reclaiming a huge page */
> VM_WARN_ON(folio_test_lru(folio));
> @@ -3252,6 +3356,7 @@ static void lru_add_split_folio(struct folio *folio, struct folio *new_folio,
> list_add_tail(&new_folio->lru, &folio->lru);
> folio_set_lru(new_folio);
> }
> +
> }
>
> /* Racy check whether the huge page can be split */
> @@ -3727,7 +3832,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
>
> /* Prevent deferred_split_scan() touching ->_refcount */
> spin_lock(&ds_queue->split_queue_lock);
> - if (folio_ref_freeze(folio, 1 + extra_pins)) {
> + if (folio_ref_freeze(folio, 1 + folio_expected_ref_count(folio))) {
> struct address_space *swap_cache = NULL;
> struct lruvec *lruvec;
> int expected_refs;
> @@ -3858,8 +3963,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
> if (nr_shmem_dropped)
> shmem_uncharge(mapping->host, nr_shmem_dropped);
>
> - if (!ret && is_anon)
> + if (!ret && is_anon && !folio_is_device_private(folio))
> remap_flags = RMP_USE_SHARED_ZEROPAGE;
> +
> remap_page(folio, 1 << order, remap_flags);
>
> /*
> @@ -4603,7 +4709,10 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
> return 0;
>
> flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
> - pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
> + if (unlikely(is_pmd_device_private_entry(*pvmw->pmd)))
> + pmdval = pmdp_huge_clear_flush(vma, address, pvmw->pmd);
> + else
> + pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
>
> /* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */
> anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page);
> @@ -4653,6 +4762,17 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
> entry = pmd_to_swp_entry(*pvmw->pmd);
> folio_get(folio);
> pmde = folio_mk_pmd(folio, READ_ONCE(vma->vm_page_prot));
> +
> + if (folio_is_device_private(folio)) {
> + if (pmd_write(pmde))
> + entry = make_writable_device_private_entry(
> + page_to_pfn(new));
> + else
> + entry = make_readable_device_private_entry(
> + page_to_pfn(new));
> + pmde = swp_entry_to_pmd(entry);
> + }
> +
> if (pmd_swp_soft_dirty(*pvmw->pmd))
> pmde = pmd_mksoft_dirty(pmde);
> if (is_writable_migration_entry(entry))
> diff --git a/mm/migrate_device.c b/mm/migrate_device.c
> index e05e14d6eacd..0ed337f94fcd 100644
> --- a/mm/migrate_device.c
> +++ b/mm/migrate_device.c
> @@ -136,6 +136,8 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
> * page table entry. Other special swap entries are not
> * migratable, and we ignore regular swapped page.
> */
> + struct folio *folio;
> +
> entry = pte_to_swp_entry(pte);
> if (!is_device_private_entry(entry))
> goto next;
> @@ -147,6 +149,51 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
> pgmap->owner != migrate->pgmap_owner)
> goto next;
>
> + folio = page_folio(page);
> + if (folio_test_large(folio)) {
> + struct folio *new_folio;
> + struct folio *new_fault_folio = NULL;
> +
> + /*
> + * The reason for finding pmd present with a
> + * device private pte and a large folio for the
> + * pte is partial unmaps. Split the folio now
> + * for the migration to be handled correctly
> + */
> + pte_unmap_unlock(ptep, ptl);
> +
> + folio_get(folio);
> + if (folio != fault_folio)
> + folio_lock(folio);
> + if (split_folio(folio)) {
> + if (folio != fault_folio)
> + folio_unlock(folio);
> + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
> + goto next;
> + }
> +
> + new_folio = page_folio(page);
> + if (fault_folio)
> + new_fault_folio = page_folio(migrate->fault_page);
> +
> + /*
> + * Ensure the lock is held on the correct
> + * folio after the split
> + */
> + if (!new_fault_folio) {
> + folio_unlock(folio);
> + folio_put(folio);
> + } else if (folio != new_fault_folio) {
> + folio_get(new_fault_folio);
> + folio_lock(new_fault_folio);
> + folio_unlock(folio);
> + folio_put(folio);
> + }
> +
> + addr = start;
> + goto again;
> + }
> +
> mpfn = migrate_pfn(page_to_pfn(page)) |
> MIGRATE_PFN_MIGRATE;
> if (is_writable_device_private_entry(entry))
> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
> index e981a1a292d2..246e6c211f34 100644
> --- a/mm/page_vma_mapped.c
> +++ b/mm/page_vma_mapped.c
> @@ -250,12 +250,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
> pvmw->ptl = pmd_lock(mm, pvmw->pmd);
> pmde = *pvmw->pmd;
> if (!pmd_present(pmde)) {
> - swp_entry_t entry;
> + swp_entry_t entry = pmd_to_swp_entry(pmde);
>
> if (!thp_migration_supported() ||
> !(pvmw->flags & PVMW_MIGRATION))
> return not_found(pvmw);
> - entry = pmd_to_swp_entry(pmde);
> if (!is_migration_entry(entry) ||
> !check_pmd(swp_offset_pfn(entry), pvmw))
> return not_found(pvmw);
> @@ -277,6 +276,16 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
> * cannot return prematurely, while zap_huge_pmd() has
> * cleared *pmd but not decremented compound_mapcount().
> */
> + swp_entry_t entry;
> +
> + entry = pmd_to_swp_entry(pmde);
> +
> + if (is_device_private_entry(entry) &&
> + (pvmw->flags & PVMW_THP_DEVICE_PRIVATE)) {
> + pvmw->ptl = pmd_lock(mm, pvmw->pmd);
> + return true;
> + }
> +
> if ((pvmw->flags & PVMW_SYNC) &&
> thp_vma_suitable_order(vma, pvmw->address,
> PMD_ORDER) &&
> diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
> index 567e2d084071..604e8206a2ec 100644
> --- a/mm/pgtable-generic.c
> +++ b/mm/pgtable-generic.c
> @@ -292,6 +292,12 @@ pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
> *pmdvalp = pmdval;
> if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
> goto nomap;
> + if (is_swap_pmd(pmdval)) {
> + swp_entry_t entry = pmd_to_swp_entry(pmdval);
> +
> + if (is_device_private_entry(entry))
> + goto nomap;
> + }
> if (unlikely(pmd_trans_huge(pmdval)))
> goto nomap;
> if (unlikely(pmd_bad(pmdval))) {
> diff --git a/mm/rmap.c b/mm/rmap.c
> index b5837075b6e0..f40e45564295 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -2285,7 +2285,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
> unsigned long address, void *arg)
> {
> struct mm_struct *mm = vma->vm_mm;
> - DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
> + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address,
> + PVMW_THP_DEVICE_PRIVATE);
> bool anon_exclusive, writable, ret = true;
> pte_t pteval;
> struct page *subpage;
> @@ -2330,6 +2331,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
> while (page_vma_mapped_walk(&pvmw)) {
> /* PMD-mapped THP migration entry */
> if (!pvmw.pte) {
> +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
> + unsigned long pfn;
> +#endif
> +
> if (flags & TTU_SPLIT_HUGE_PMD) {
> split_huge_pmd_locked(vma, pvmw.address,
> pvmw.pmd, true);
> @@ -2338,8 +2343,21 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
> break;
> }
> #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
> - subpage = folio_page(folio,
> - pmd_pfn(*pvmw.pmd) - folio_pfn(folio));
> + /*
> + * Zone device private folios do not work well with
> + * pmd_pfn() on some architectures due to pte
> + * inversion.
> + */
> + if (is_pmd_device_private_entry(*pvmw.pmd)) {
> + swp_entry_t entry = pmd_to_swp_entry(*pvmw.pmd);
> +
> + pfn = swp_offset_pfn(entry);
> + } else {
> + pfn = pmd_pfn(*pvmw.pmd);
> + }
> +
> + subpage = folio_page(folio, pfn - folio_pfn(folio));
> +
> VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
> !folio_test_pmd_mappable(folio), folio);
>
> --
> 2.50.1
>
Powered by blists - more mailing lists