[RFC 05/11] mm/memory/fault: Add support for zone device THP fault handling

[Balbir Singh <balbirs@nvidia.com>]

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.

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/huge_mm.h |  7 +++++++
 mm/huge_memory.c        | 35 +++++++++++++++++++++++++++++++++++
 mm/memory.c             |  6 ++++--
 3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e893d546a49f..ad0c0ccfcbc2 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -479,6 +479,8 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 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;
 
@@ -634,6 +636,11 @@ 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 d8e018d1bdbd..995ac8be5709 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1375,6 +1375,41 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 	return __do_huge_pmd_anonymous_page(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;
+	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);
+	vmf->page = page;
+	vmf->pte = NULL;
+	get_page(page);
+	spin_unlock(ptl);
+	ret = page_pgmap(page)->ops->migrate_to_ram(vmf);
+	put_page(page);
+
+	return ret;
+}
+
 static int insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
 		pgtable_t pgtable)
diff --git a/mm/memory.c b/mm/memory.c
index a838c8c44bfd..deaa67b88708 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6149,8 +6149,10 @@ 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;
-- 
2.48.1