On Fri, Jul 04, 2025 at 09:35:04AM +1000, Balbir Singh wrote:
> When the CPU touches a zone device THP entry, the data needs to
> be migrated back to the CPU, call migrate_to_ram() on these pages
> via do_huge_pmd_device_private() fault handling helper.
>
> Cc: Karol Herbst <kherbst@redhat.com>
> Cc: Lyude Paul <lyude@redhat.com>
> Cc: Danilo Krummrich <dakr@kernel.org>
> Cc: David Airlie <airlied@gmail.com>
> Cc: Simona Vetter <simona@ffwll.ch>
> Cc: "Jérôme Glisse" <jglisse@redhat.com>
> Cc: Shuah Khan <shuah@kernel.org>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Barry Song <baohua@kernel.org>
> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
> Cc: Ryan Roberts <ryan.roberts@arm.com>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Peter Xu <peterx@redhat.com>
> Cc: Zi Yan <ziy@nvidia.com>
> Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
> Cc: Jane Chu <jane.chu@oracle.com>
> Cc: Alistair Popple <apopple@nvidia.com>
> Cc: Donet Tom <donettom@linux.ibm.com>
>
> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
> ---
> include/linux/huge_mm.h | 7 +++++++
> mm/huge_memory.c | 40 ++++++++++++++++++++++++++++++++++++++++
> mm/memory.c | 6 ++++--
> 3 files changed, 51 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 4d5bb67dc4ec..65a1bdf29bb9 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -474,6 +474,8 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
>
> vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf);
>
> +vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf);
> +
> extern struct folio *huge_zero_folio;
> extern unsigned long huge_zero_pfn;
>
> @@ -627,6 +629,11 @@ static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
> return 0;
> }
>
> +static inline vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf)
> +{
> + return 0;
> +}
> +
> static inline bool is_huge_zero_folio(const struct folio *folio)
> {
> return false;
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index e6e390d0308f..f29add796931 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1267,6 +1267,46 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf)
>
> }
>
> +vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf)
> +{
> + struct vm_area_struct *vma = vmf->vma;
> + unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> + vm_fault_t ret = 0;
> + spinlock_t *ptl;
> + swp_entry_t swp_entry;
> + struct page *page;
> +
> + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
> + return VM_FAULT_FALLBACK;
> +
> + if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
> + vma_end_read(vma);
> + return VM_FAULT_RETRY;
> + }
> +
> + ptl = pmd_lock(vma->vm_mm, vmf->pmd);
> + if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) {
> + spin_unlock(ptl);
> + return 0;
> + }
> +
> + swp_entry = pmd_to_swp_entry(vmf->orig_pmd);
> + page = pfn_swap_entry_to_page(swp_entry);
Would it make more sense here to use folio lock, unlock, put, get
functions?
Matt
> + vmf->page = page;
> + vmf->pte = NULL;
> + if (trylock_page(vmf->page)) {
> + get_page(page);
> + spin_unlock(ptl);
> + ret = page_pgmap(page)->ops->migrate_to_ram(vmf);
> + unlock_page(vmf->page);
> + put_page(page);
> + } else {
> + spin_unlock(ptl);
> + }
> +
> + return ret;
> +}
> +
> /*
> * always: directly stall for all thp allocations
> * defer: wake kswapd and fail if not immediately available
> diff --git a/mm/memory.c b/mm/memory.c
> index 0f9b32a20e5b..c26c421b8325 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -6165,8 +6165,10 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
> vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
>
> if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
> - VM_BUG_ON(thp_migration_supported() &&
> - !is_pmd_migration_entry(vmf.orig_pmd));
> + if (is_device_private_entry(
> + pmd_to_swp_entry(vmf.orig_pmd)))
> + return do_huge_pmd_device_private(&vmf);
> +
> if (is_pmd_migration_entry(vmf.orig_pmd))
> pmd_migration_entry_wait(mm, vmf.pmd);
> return 0;
> --
> 2.49.0
>