Commit 49640991 authored by Balbir Singh's avatar Balbir Singh Committed by Andrew Morton
Browse files

mm/memory/fault: add THP fault handling for zone device private pages 

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.

Link: https://lkml.kernel.org/r/20251001065707.920170-9-balbirs@nvidia.com


Signed-off-by: default avatarBalbir Singh <balbirs@nvidia.com>
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: default avatarAndrew Morton <akpm@linux-foundation.org>
parent a30b48bf

include/linux/huge_mm.h

+7 −0
Original line number Diff line number Diff line
@@ -481,6 +481,8 @@ 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;
@@ -662,6 +664,11 @@ 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;

mm/huge_memory.c

+38 −0
Original line number Diff line number Diff line
@@ -1288,6 +1288,44 @@ 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;

	struct folio *folio;



	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);

	folio = page_folio(page);

	vmf->page = page;

	vmf->pte = NULL;

	if (folio_trylock(folio)) {

		folio_get(folio);

		spin_unlock(ptl);

		ret = page_pgmap(page)->ops->migrate_to_ram(vmf);

		folio_unlock(folio);

		folio_put(folio);

	} else {

		spin_unlock(ptl);

	}



	return ret;

}



/*

 * always: directly stall for all thp allocations

 * defer: wake kswapd and fail if not immediately available

mm/memory.c

+3 −2
Original line number Diff line number Diff line
@@ -6345,8 +6345,9 @@ 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_pmd_device_private_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;