[v4 07/15] mm/memory/fault: add THP fault handling for zone device private pages

[Balbir Singh <balbirs@nvidia.com>]

Implement CPU fault handling for zone device THP entries through
do_huge_pmd_device_private(), enabling transparent migration of
device-private large pages back to system memory on CPU access.

When the CPU accesses a zone device THP entry, the fault handler
calls the device driver's migrate_to_ram() callback to migrate
the entire large page back to system memory.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
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: Ralph Campbell <rcampbell@nvidia.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/huge_mm.h |  7 +++++++
 mm/huge_memory.c        | 36 ++++++++++++++++++++++++++++++++++++
 mm/memory.c             |  6 ++++--
 3 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7748489fde1b..a4880fe98e46 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;
 
@@ -632,6 +634,11 @@ 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 47fe07b9fee4..9adffe343de4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1267,6 +1267,42 @@ 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;
+	vm_fault_t ret = 0;
+	spinlock_t *ptl;
+	swp_entry_t swp_entry;
+	struct page *page;
+
+	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;
+	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 0ba4f6b71847..ad05a38bb232 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6170,8 +6170,10 @@ 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;
-- 
2.50.1