* [PATCH 1/3] mm: unified hmm fault and migrate device pagewalk paths
2026-01-14 9:19 [PATCH 0/3] Migrate on fault for device pages mpenttil
@ 2026-01-14 9:19 ` mpenttil
2026-01-14 9:19 ` [PATCH 2/3] mm: add new testcase for the migrate on fault case mpenttil
2026-01-14 9:19 ` [PATCH 3/3] mm:/migrate_device.c: remove migrate_vma_collect_*() functions mpenttil
2 siblings, 0 replies; 4+ messages in thread
From: mpenttil @ 2026-01-14 9:19 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, Mika Penttilä,
David Hildenbrand, Jason Gunthorpe, Leon Romanovsky,
Alistair Popple, Balbir Singh, Zi Yan, Matthew Brost
From: Mika Penttilä <mpenttil@redhat.com>
Currently, the way device page faulting and migration works
is not optimal, if you want to do both fault handling and
migration at once.
Being able to migrate not present pages (or pages mapped with incorrect
permissions, eg. COW) to the GPU requires doing either of the
following sequences:
1. hmm_range_fault() - fault in non-present pages with correct permissions, etc.
2. migrate_vma_*() - migrate the pages
Or:
1. migrate_vma_*() - migrate present pages
2. If non-present pages detected by migrate_vma_*():
a) call hmm_range_fault() to fault pages in
b) call migrate_vma_*() again to migrate now present pages
The problem with the first sequence is that you always have to do two
page walks even when most of the time the pages are present or zero page
mappings so the common case takes a performance hit.
The second sequence is better for the common case, but far worse if
pages aren't present because now you have to walk the page tables three
times (once to find the page is not present, once so hmm_range_fault()
can find a non-present page to fault in and once again to setup the
migration). It is also tricky to code correctly.
We should be able to walk the page table once, faulting
pages in as required and replacing them with migration entries if
requested.
Add a new flag to HMM APIs, HMM_PFN_REQ_MIGRATE,
which tells to prepare for migration also during fault handling.
Also, for the migrate_vma_setup() call paths, a flags, MIGRATE_VMA_FAULT,
is added to tell to add fault handling to migrate.
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Suggested-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
---
include/linux/hmm.h | 17 +-
include/linux/migrate.h | 6 +-
mm/hmm.c | 657 +++++++++++++++++++++++++++++++++++++---
mm/migrate_device.c | 81 ++++-
4 files changed, 706 insertions(+), 55 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index db75ffc949a7..7b7294ad0f62 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -12,7 +12,7 @@
#include <linux/mm.h>
struct mmu_interval_notifier;
-
+struct migrate_vma;
/*
* On output:
* 0 - The page is faultable and a future call with
@@ -48,15 +48,25 @@ enum hmm_pfn_flags {
HMM_PFN_P2PDMA = 1UL << (BITS_PER_LONG - 5),
HMM_PFN_P2PDMA_BUS = 1UL << (BITS_PER_LONG - 6),
- HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 11),
+ /* Migrate request */
+ HMM_PFN_MIGRATE = 1UL << (BITS_PER_LONG - 7),
+ HMM_PFN_COMPOUND = 1UL << (BITS_PER_LONG - 8),
+ HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 13),
/* Input flags */
HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
+ HMM_PFN_REQ_MIGRATE = HMM_PFN_MIGRATE,
HMM_PFN_FLAGS = ~((1UL << HMM_PFN_ORDER_SHIFT) - 1),
};
+enum {
+ /* These flags are carried from input-to-output */
+ HMM_PFN_INOUT_FLAGS = HMM_PFN_DMA_MAPPED | HMM_PFN_P2PDMA |
+ HMM_PFN_P2PDMA_BUS,
+};
+
/*
* hmm_pfn_to_page() - return struct page pointed to by a device entry
*
@@ -107,6 +117,7 @@ static inline unsigned int hmm_pfn_to_map_order(unsigned long hmm_pfn)
* @default_flags: default flags for the range (write, read, ... see hmm doc)
* @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
* @dev_private_owner: owner of device private pages
+ * @migrate: structure for migrating the associated vma
*/
struct hmm_range {
struct mmu_interval_notifier *notifier;
@@ -117,12 +128,14 @@ struct hmm_range {
unsigned long default_flags;
unsigned long pfn_flags_mask;
void *dev_private_owner;
+ struct migrate_vma *migrate;
};
/*
* Please see Documentation/mm/hmm.rst for how to use the range API.
*/
int hmm_range_fault(struct hmm_range *range);
+int hmm_range_migrate_prepare(struct hmm_range *range, struct migrate_vma **pargs);
/*
* HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 26ca00c325d9..0889309a9d21 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -3,6 +3,7 @@
#define _LINUX_MIGRATE_H
#include <linux/mm.h>
+#include <linux/hmm.h>
#include <linux/mempolicy.h>
#include <linux/migrate_mode.h>
#include <linux/hugetlb.h>
@@ -140,11 +141,12 @@ static inline unsigned long migrate_pfn(unsigned long pfn)
return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
}
-enum migrate_vma_direction {
+enum migrate_vma_info {
MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2,
MIGRATE_VMA_SELECT_COMPOUND = 1 << 3,
+ MIGRATE_VMA_FAULT = 1 << 4,
};
struct migrate_vma {
@@ -192,7 +194,7 @@ void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns,
unsigned long npages);
void migrate_device_finalize(unsigned long *src_pfns,
unsigned long *dst_pfns, unsigned long npages);
-
+void migrate_hmm_range_setup(struct hmm_range *range);
#endif /* CONFIG_MIGRATION */
#endif /* _LINUX_MIGRATE_H */
diff --git a/mm/hmm.c b/mm/hmm.c
index 4ec74c18bef6..39a07d895043 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -20,6 +20,7 @@
#include <linux/pagemap.h>
#include <linux/leafops.h>
#include <linux/hugetlb.h>
+#include <linux/migrate.h>
#include <linux/memremap.h>
#include <linux/sched/mm.h>
#include <linux/jump_label.h>
@@ -31,8 +32,12 @@
#include "internal.h"
struct hmm_vma_walk {
- struct hmm_range *range;
- unsigned long last;
+ struct mmu_notifier_range mmu_range;
+ struct vm_area_struct *vma;
+ struct hmm_range *range;
+ unsigned long start;
+ unsigned long end;
+ unsigned long last;
};
enum {
@@ -41,21 +46,49 @@ enum {
HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT,
};
-enum {
- /* These flags are carried from input-to-output */
- HMM_PFN_INOUT_FLAGS = HMM_PFN_DMA_MAPPED | HMM_PFN_P2PDMA |
- HMM_PFN_P2PDMA_BUS,
-};
+static enum migrate_vma_info hmm_select_migrate(struct hmm_range *range)
+{
+ enum migrate_vma_info minfo;
+
+ minfo = range->migrate ? range->migrate->flags : 0;
+ minfo |= (range->default_flags & HMM_PFN_REQ_MIGRATE) ?
+ MIGRATE_VMA_SELECT_SYSTEM : 0;
+
+ return minfo;
+}
static int hmm_pfns_fill(unsigned long addr, unsigned long end,
- struct hmm_range *range, unsigned long cpu_flags)
+ struct hmm_vma_walk *hmm_vma_walk, unsigned long cpu_flags)
{
+ struct hmm_range *range = hmm_vma_walk->range;
unsigned long i = (addr - range->start) >> PAGE_SHIFT;
+ enum migrate_vma_info minfo;
+ bool migrate = false;
+
+ minfo = hmm_select_migrate(range);
+ if (cpu_flags != HMM_PFN_ERROR) {
+ if (minfo && (vma_is_anonymous(hmm_vma_walk->vma))) {
+ cpu_flags |= (HMM_PFN_VALID | HMM_PFN_MIGRATE);
+ migrate = true;
+ }
+ }
+
+ if (migrate && thp_migration_supported() &&
+ (minfo & MIGRATE_VMA_SELECT_COMPOUND) &&
+ IS_ALIGNED(addr, HPAGE_PMD_SIZE) &&
+ IS_ALIGNED(end, HPAGE_PMD_SIZE)) {
+ range->hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS;
+ range->hmm_pfns[i] |= cpu_flags | HMM_PFN_COMPOUND;
+ addr += PAGE_SIZE;
+ i++;
+ cpu_flags = 0;
+ }
for (; addr < end; addr += PAGE_SIZE, i++) {
range->hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS;
range->hmm_pfns[i] |= cpu_flags;
}
+
return 0;
}
@@ -171,11 +204,11 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
if (!walk->vma) {
if (required_fault)
return -EFAULT;
- return hmm_pfns_fill(addr, end, range, HMM_PFN_ERROR);
+ return hmm_pfns_fill(addr, end, hmm_vma_walk, HMM_PFN_ERROR);
}
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
- return hmm_pfns_fill(addr, end, range, 0);
+ return hmm_pfns_fill(addr, end, hmm_vma_walk, 0);
}
static inline unsigned long hmm_pfn_flags_order(unsigned long order)
@@ -289,10 +322,13 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
goto fault;
if (softleaf_is_migration(entry)) {
- pte_unmap(ptep);
- hmm_vma_walk->last = addr;
- migration_entry_wait(walk->mm, pmdp, addr);
- return -EBUSY;
+ if (!hmm_select_migrate(range)) {
+ pte_unmap(ptep);
+ hmm_vma_walk->last = addr;
+ migration_entry_wait(walk->mm, pmdp, addr);
+ return -EBUSY;
+ } else
+ goto out;
}
/* Report error for everything else */
@@ -376,7 +412,7 @@ static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start,
return -EFAULT;
}
- return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
+ return hmm_pfns_fill(start, end, hmm_vma_walk, HMM_PFN_ERROR);
}
#else
static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start,
@@ -389,10 +425,448 @@ static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start,
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
return -EFAULT;
- return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
+ return hmm_pfns_fill(start, end, hmm_vma_walk, HMM_PFN_ERROR);
}
#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+/**
+ * migrate_vma_split_folio() - Helper function to split a THP folio
+ * @folio: the folio to split
+ * @fault_page: struct page associated with the fault if any
+ *
+ * Returns 0 on success
+ */
+static int migrate_vma_split_folio(struct folio *folio,
+ struct page *fault_page)
+{
+ int ret;
+ struct folio *fault_folio = fault_page ? page_folio(fault_page) : NULL;
+ struct folio *new_fault_folio = NULL;
+
+ if (folio != fault_folio) {
+ folio_get(folio);
+ folio_lock(folio);
+ }
+
+ ret = split_folio(folio);
+ if (ret) {
+ if (folio != fault_folio) {
+ folio_unlock(folio);
+ folio_put(folio);
+ }
+ return ret;
+ }
+
+ new_fault_folio = fault_page ? page_folio(fault_page) : NULL;
+
+ /*
+ * 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) {
+ if (new_fault_folio != fault_folio) {
+ folio_get(new_fault_folio);
+ folio_lock(new_fault_folio);
+ }
+ folio_unlock(folio);
+ folio_put(folio);
+ }
+
+ return 0;
+}
+
+static int hmm_vma_handle_migrate_prepare_pmd(const struct mm_walk *walk,
+ pmd_t *pmdp,
+ unsigned long start,
+ unsigned long end,
+ unsigned long *hmm_pfn)
+{
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
+ struct migrate_vma *migrate = range->migrate;
+ struct mm_struct *mm = walk->vma->vm_mm;
+ struct folio *fault_folio = NULL;
+ struct folio *folio;
+ enum migrate_vma_info minfo;
+ spinlock_t *ptl;
+ unsigned long i;
+ int r = 0;
+
+ minfo = hmm_select_migrate(range);
+ if (!minfo)
+ return r;
+
+ fault_folio = (migrate && migrate->fault_page) ?
+ page_folio(migrate->fault_page) : NULL;
+
+ ptl = pmd_lock(mm, pmdp);
+ if (pmd_none(*pmdp)) {
+ spin_unlock(ptl);
+ return hmm_pfns_fill(start, end, hmm_vma_walk, 0);
+ }
+
+ if (pmd_trans_huge(*pmdp)) {
+ if (!(minfo & MIGRATE_VMA_SELECT_SYSTEM))
+ goto out;
+
+ folio = pmd_folio(*pmdp);
+ if (is_huge_zero_folio(folio)) {
+ spin_unlock(ptl);
+ return hmm_pfns_fill(start, end, hmm_vma_walk, 0);
+ }
+
+ } else if (!pmd_present(*pmdp)) {
+ const softleaf_t entry = softleaf_from_pmd(*pmdp);
+
+ folio = softleaf_to_folio(entry);
+
+ if (!softleaf_is_device_private(entry))
+ goto out;
+
+ if (!(minfo & MIGRATE_VMA_SELECT_DEVICE_PRIVATE))
+ goto out;
+ if (folio->pgmap->owner != migrate->pgmap_owner)
+ goto out;
+
+ } else {
+ spin_unlock(ptl);
+ return -EBUSY;
+ }
+
+ folio_get(folio);
+
+ if (folio != fault_folio && unlikely(!folio_trylock(folio))) {
+ spin_unlock(ptl);
+ folio_put(folio);
+ return 0;
+ }
+
+ if (thp_migration_supported() &&
+ (migrate->flags & MIGRATE_VMA_SELECT_COMPOUND) &&
+ (IS_ALIGNED(start, HPAGE_PMD_SIZE) &&
+ IS_ALIGNED(end, HPAGE_PMD_SIZE))) {
+
+ struct page_vma_mapped_walk pvmw = {
+ .ptl = ptl,
+ .address = start,
+ .pmd = pmdp,
+ .vma = walk->vma,
+ };
+
+ hmm_pfn[0] |= HMM_PFN_MIGRATE | HMM_PFN_COMPOUND;
+
+ r = set_pmd_migration_entry(&pvmw, folio_page(folio, 0));
+ if (r) {
+ hmm_pfn[0] &= ~(HMM_PFN_MIGRATE | HMM_PFN_COMPOUND);
+ r = -ENOENT; // fallback
+ goto unlock_out;
+ }
+ for (i = 1, start += PAGE_SIZE; start < end; start += PAGE_SIZE, i++)
+ hmm_pfn[i] &= HMM_PFN_INOUT_FLAGS;
+
+ } else {
+ r = -ENOENT; // fallback
+ goto unlock_out;
+ }
+
+
+out:
+ spin_unlock(ptl);
+ return r;
+
+unlock_out:
+ if (folio != fault_folio)
+ folio_unlock(folio);
+ folio_put(folio);
+ goto out;
+
+}
+
+/*
+ * Install migration entries if migration requested, either from fault
+ * or migrate paths.
+ *
+ */
+static int hmm_vma_handle_migrate_prepare(const struct mm_walk *walk,
+ pmd_t *pmdp,
+ unsigned long addr,
+ unsigned long *hmm_pfn)
+{
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
+ struct migrate_vma *migrate = range->migrate;
+ struct mm_struct *mm = walk->vma->vm_mm;
+ struct folio *fault_folio = NULL;
+ enum migrate_vma_info minfo;
+ struct dev_pagemap *pgmap;
+ bool anon_exclusive;
+ struct folio *folio;
+ unsigned long pfn;
+ struct page *page;
+ softleaf_t entry;
+ pte_t pte, swp_pte;
+ spinlock_t *ptl;
+ bool writable = false;
+ pte_t *ptep;
+
+ // Do we want to migrate at all?
+ minfo = hmm_select_migrate(range);
+ if (!minfo)
+ return 0;
+
+ fault_folio = (migrate && migrate->fault_page) ?
+ page_folio(migrate->fault_page) : NULL;
+
+again:
+ ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+ if (!ptep)
+ return 0;
+
+ pte = ptep_get(ptep);
+
+ if (pte_none(pte)) {
+ // migrate without faulting case
+ if (vma_is_anonymous(walk->vma)) {
+ *hmm_pfn &= HMM_PFN_INOUT_FLAGS;
+ *hmm_pfn |= HMM_PFN_MIGRATE | HMM_PFN_VALID;
+ goto out;
+ }
+ }
+
+ if (!pte_present(pte)) {
+ /*
+ * Only care about unaddressable device page special
+ * page table entry. Other special swap entries are not
+ * migratable, and we ignore regular swapped page.
+ */
+ entry = softleaf_from_pte(pte);
+ if (!softleaf_is_device_private(entry))
+ goto out;
+
+ if (!(minfo & MIGRATE_VMA_SELECT_DEVICE_PRIVATE))
+ goto out;
+
+ page = softleaf_to_page(entry);
+ folio = page_folio(page);
+ if (folio->pgmap->owner != migrate->pgmap_owner)
+ goto out;
+
+ if (folio_test_large(folio)) {
+ int ret;
+
+ pte_unmap_unlock(ptep, ptl);
+ ret = migrate_vma_split_folio(folio,
+ migrate->fault_page);
+ if (ret)
+ goto out_unlocked;
+ goto again;
+ }
+
+ pfn = page_to_pfn(page);
+ if (softleaf_is_device_private_write(entry))
+ writable = true;
+ } else {
+ pfn = pte_pfn(pte);
+ if (is_zero_pfn(pfn) &&
+ (minfo & MIGRATE_VMA_SELECT_SYSTEM)) {
+ *hmm_pfn = HMM_PFN_MIGRATE|HMM_PFN_VALID;
+ goto out;
+ }
+ page = vm_normal_page(walk->vma, addr, pte);
+ if (page && !is_zone_device_page(page) &&
+ !(minfo & MIGRATE_VMA_SELECT_SYSTEM)) {
+ goto out;
+ } else if (page && is_device_coherent_page(page)) {
+ pgmap = page_pgmap(page);
+
+ if (!(minfo &
+ MIGRATE_VMA_SELECT_DEVICE_COHERENT) ||
+ pgmap->owner != migrate->pgmap_owner)
+ goto out;
+ }
+
+ folio = page_folio(page);
+ if (folio_test_large(folio)) {
+ int ret;
+
+ pte_unmap_unlock(ptep, ptl);
+ ret = migrate_vma_split_folio(folio,
+ migrate->fault_page);
+ if (ret)
+ goto out_unlocked;
+
+ goto again;
+ }
+
+ writable = pte_write(pte);
+ }
+
+ if (!page || !page->mapping)
+ goto out;
+
+ /*
+ * By getting a reference on the folio we pin it and that blocks
+ * any kind of migration. Side effect is that it "freezes" the
+ * pte.
+ *
+ * We drop this reference after isolating the folio from the lru
+ * for non device folio (device folio are not on the lru and thus
+ * can't be dropped from it).
+ */
+ folio = page_folio(page);
+ folio_get(folio);
+
+ /*
+ * We rely on folio_trylock() to avoid deadlock between
+ * concurrent migrations where each is waiting on the others
+ * folio lock. If we can't immediately lock the folio we fail this
+ * migration as it is only best effort anyway.
+ *
+ * If we can lock the folio it's safe to set up a migration entry
+ * now. In the common case where the folio is mapped once in a
+ * single process setting up the migration entry now is an
+ * optimisation to avoid walking the rmap later with
+ * try_to_migrate().
+ */
+
+ if (fault_folio == folio || folio_trylock(folio)) {
+ anon_exclusive = folio_test_anon(folio) &&
+ PageAnonExclusive(page);
+
+ flush_cache_page(walk->vma, addr, pfn);
+
+ if (anon_exclusive) {
+ pte = ptep_clear_flush(walk->vma, addr, ptep);
+
+ if (folio_try_share_anon_rmap_pte(folio, page)) {
+ set_pte_at(mm, addr, ptep, pte);
+ folio_unlock(folio);
+ folio_put(folio);
+ goto out;
+ }
+ } else {
+ pte = ptep_get_and_clear(mm, addr, ptep);
+ }
+
+ /* Setup special migration page table entry */
+ if (writable)
+ entry = make_writable_migration_entry(pfn);
+ else if (anon_exclusive)
+ entry = make_readable_exclusive_migration_entry(pfn);
+ else
+ entry = make_readable_migration_entry(pfn);
+
+ swp_pte = swp_entry_to_pte(entry);
+ if (pte_present(pte)) {
+ if (pte_soft_dirty(pte))
+ swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_uffd_wp(pte))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
+ } else {
+ if (pte_swp_soft_dirty(pte))
+ swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_swp_uffd_wp(pte))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
+ }
+
+ set_pte_at(mm, addr, ptep, swp_pte);
+ folio_remove_rmap_pte(folio, page, walk->vma);
+ folio_put(folio);
+ *hmm_pfn |= HMM_PFN_MIGRATE;
+
+ if (pte_present(pte))
+ flush_tlb_range(walk->vma, addr, addr + PAGE_SIZE);
+ } else
+ folio_put(folio);
+out:
+ pte_unmap_unlock(ptep, ptl);
+ return 0;
+out_unlocked:
+ return -1;
+
+}
+
+static int hmm_vma_walk_split(pmd_t *pmdp,
+ unsigned long addr,
+ struct mm_walk *walk)
+{
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
+ struct migrate_vma *migrate = range->migrate;
+ struct folio *folio, *fault_folio;
+ spinlock_t *ptl;
+ int ret = 0;
+
+ fault_folio = (migrate && migrate->fault_page) ?
+ page_folio(migrate->fault_page) : NULL;
+
+ ptl = pmd_lock(walk->mm, pmdp);
+ if (unlikely(!pmd_trans_huge(*pmdp))) {
+ spin_unlock(ptl);
+ goto out;
+ }
+
+ folio = pmd_folio(*pmdp);
+ if (is_huge_zero_folio(folio)) {
+ spin_unlock(ptl);
+ split_huge_pmd(walk->vma, pmdp, addr);
+ } else {
+ folio_get(folio);
+ spin_unlock(ptl);
+
+ if (folio != fault_folio) {
+ if (unlikely(!folio_trylock(folio))) {
+ folio_put(folio);
+ ret = -EBUSY;
+ goto out;
+ }
+ } else
+ folio_put(folio);
+
+ ret = split_folio(folio);
+ if (fault_folio != folio) {
+ folio_unlock(folio);
+ folio_put(folio);
+ }
+
+ }
+out:
+ return ret;
+}
+
+static int hmm_vma_capture_migrate_range(unsigned long start,
+ unsigned long end,
+ struct mm_walk *walk)
+{
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
+
+ if (!hmm_select_migrate(range))
+ return 0;
+
+ if (hmm_vma_walk->vma && (hmm_vma_walk->vma != walk->vma))
+ return -ERANGE;
+
+ hmm_vma_walk->vma = walk->vma;
+ hmm_vma_walk->start = start;
+ hmm_vma_walk->end = end;
+
+ if (end - start > range->end - range->start)
+ return -ERANGE;
+
+ if (!hmm_vma_walk->mmu_range.owner) {
+ mmu_notifier_range_init_owner(&hmm_vma_walk->mmu_range, MMU_NOTIFY_MIGRATE, 0,
+ walk->vma->vm_mm, start, end,
+ range->dev_private_owner);
+ mmu_notifier_invalidate_range_start(&hmm_vma_walk->mmu_range);
+ }
+
+ return 0;
+}
+
static int hmm_vma_walk_pmd(pmd_t *pmdp,
unsigned long start,
unsigned long end,
@@ -404,42 +878,90 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
&range->hmm_pfns[(start - range->start) >> PAGE_SHIFT];
unsigned long npages = (end - start) >> PAGE_SHIFT;
unsigned long addr = start;
+ enum migrate_vma_info minfo;
+ unsigned long i;
+ spinlock_t *ptl;
pte_t *ptep;
pmd_t pmd;
+ int r;
+ minfo = hmm_select_migrate(range);
again:
+
pmd = pmdp_get_lockless(pmdp);
- if (pmd_none(pmd))
- return hmm_vma_walk_hole(start, end, -1, walk);
+ if (pmd_none(pmd)) {
+ r = hmm_vma_walk_hole(start, end, -1, walk);
+ if (r || !minfo)
+ return r;
+
+ ptl = pmd_lock(walk->mm, pmdp);
+ if (pmd_none(*pmdp)) {
+ // hmm_vma_walk_hole() filled migration needs
+ spin_unlock(ptl);
+ return r;
+ }
+ spin_unlock(ptl);
+ }
if (thp_migration_supported() && pmd_is_migration_entry(pmd)) {
- if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) {
- hmm_vma_walk->last = addr;
- pmd_migration_entry_wait(walk->mm, pmdp);
- return -EBUSY;
+ if (!minfo) {
+ if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) {
+ hmm_vma_walk->last = addr;
+ pmd_migration_entry_wait(walk->mm, pmdp);
+ return -EBUSY;
+ }
}
- return hmm_pfns_fill(start, end, range, 0);
+ for (i = 0; addr < end; addr += PAGE_SIZE, i++)
+ hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS;
+
+ return 0;
}
- if (!pmd_present(pmd))
- return hmm_vma_handle_absent_pmd(walk, start, end, hmm_pfns,
- pmd);
+ if (pmd_trans_huge(pmd) || !pmd_present(pmd)) {
+
+ if (!pmd_present(pmd)) {
+ r = hmm_vma_handle_absent_pmd(walk, start, end, hmm_pfns,
+ pmd);
+ if (r || !minfo)
+ return r;
+ } else {
+
+ /*
+ * No need to take pmd_lock here, even if some other thread
+ * is splitting the huge pmd we will get that event through
+ * mmu_notifier callback.
+ *
+ * So just read pmd value and check again it's a transparent
+ * huge or device mapping one and compute corresponding pfn
+ * values.
+ */
+
+ pmd = pmdp_get_lockless(pmdp);
+ if (!pmd_trans_huge(pmd))
+ goto again;
+
+ r = hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
+
+ if (r || !minfo)
+ return r;
+ }
- if (pmd_trans_huge(pmd)) {
- /*
- * No need to take pmd_lock here, even if some other thread
- * is splitting the huge pmd we will get that event through
- * mmu_notifier callback.
- *
- * So just read pmd value and check again it's a transparent
- * huge or device mapping one and compute corresponding pfn
- * values.
- */
- pmd = pmdp_get_lockless(pmdp);
- if (!pmd_trans_huge(pmd))
- goto again;
+ r = hmm_vma_handle_migrate_prepare_pmd(walk, pmdp, start, end, hmm_pfns);
+
+ if (r == -ENOENT) {
+ r = hmm_vma_walk_split(pmdp, addr, walk);
+ if (r) {
+ /* Split not successful, skip */
+ return hmm_pfns_fill(start, end, hmm_vma_walk, HMM_PFN_ERROR);
+ }
+
+ /* Split successful or "again", reloop */
+ hmm_vma_walk->last = addr;
+ return -EBUSY;
+ }
+
+ return r;
- return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
}
/*
@@ -451,22 +973,26 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
if (pmd_bad(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
return -EFAULT;
- return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
+ return hmm_pfns_fill(start, end, hmm_vma_walk, HMM_PFN_ERROR);
}
ptep = pte_offset_map(pmdp, addr);
if (!ptep)
goto again;
for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) {
- int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns);
if (r) {
/* hmm_vma_handle_pte() did pte_unmap() */
return r;
}
+
+ r = hmm_vma_handle_migrate_prepare(walk, pmdp, addr, hmm_pfns);
+ if (r)
+ break;
}
pte_unmap(ptep - 1);
+
return 0;
}
@@ -600,6 +1126,11 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
+ int r;
+
+ r = hmm_vma_capture_migrate_range(start, end, walk);
+ if (r)
+ return r;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)) &&
vma->vm_flags & VM_READ)
@@ -622,7 +1153,7 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
(end - start) >> PAGE_SHIFT, 0))
return -EFAULT;
- hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
+ hmm_pfns_fill(start, end, hmm_vma_walk, HMM_PFN_ERROR);
/* Skip this vma and continue processing the next vma. */
return 1;
@@ -652,9 +1183,17 @@ static const struct mm_walk_ops hmm_walk_ops = {
* the invalidation to finish.
* -EFAULT: A page was requested to be valid and could not be made valid
* ie it has no backing VMA or it is illegal to access
+ * -ERANGE: The range crosses multiple VMAs, or space for hmm_pfns array
+ * is too low.
*
* This is similar to get_user_pages(), except that it can read the page tables
* without mutating them (ie causing faults).
+ *
+ * If want to do migrate after faultin, call hmm_rangem_fault() with
+ * HMM_PFN_REQ_MIGRATE and initialize range.migrate field.
+ * After hmm_range_fault() call migrate_hmm_range_setup() instead of
+ * migrate_vma_setup() and after that follow normal migrate calls path.
+ *
*/
int hmm_range_fault(struct hmm_range *range)
{
@@ -662,16 +1201,28 @@ int hmm_range_fault(struct hmm_range *range)
.range = range,
.last = range->start,
};
- struct mm_struct *mm = range->notifier->mm;
+ bool is_fault_path = !!range->notifier;
+ struct mm_struct *mm;
int ret;
+ /*
+ *
+ * Could be serving a device fault or come from migrate
+ * entry point. For the former we have not resolved the vma
+ * yet, and the latter we don't have a notifier (but have a vma).
+ *
+ */
+ mm = is_fault_path ? range->notifier->mm : range->migrate->vma->vm_mm;
mmap_assert_locked(mm);
do {
/* If range is no longer valid force retry. */
- if (mmu_interval_check_retry(range->notifier,
- range->notifier_seq))
- return -EBUSY;
+ if (is_fault_path && mmu_interval_check_retry(range->notifier,
+ range->notifier_seq)) {
+ ret = -EBUSY;
+ break;
+ }
+
ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
&hmm_walk_ops, &hmm_vma_walk);
/*
@@ -681,6 +1232,18 @@ int hmm_range_fault(struct hmm_range *range)
* output, and all >= are still at their input values.
*/
} while (ret == -EBUSY);
+
+ if (hmm_select_migrate(range) && range->migrate &&
+ hmm_vma_walk.mmu_range.owner) {
+ // The migrate_vma path has the following initialized
+ if (is_fault_path) {
+ range->migrate->vma = hmm_vma_walk.vma;
+ range->migrate->start = range->start;
+ range->migrate->end = hmm_vma_walk.end;
+ }
+ mmu_notifier_invalidate_range_end(&hmm_vma_walk.mmu_range);
+ }
+
return ret;
}
EXPORT_SYMBOL(hmm_range_fault);
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 23379663b1e1..d89efdfca8f6 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -734,7 +734,17 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
*/
int migrate_vma_setup(struct migrate_vma *args)
{
+ int ret;
long nr_pages = (args->end - args->start) >> PAGE_SHIFT;
+ struct hmm_range range = {
+ .notifier = NULL,
+ .start = args->start,
+ .end = args->end,
+ .migrate = args,
+ .hmm_pfns = args->src,
+ .dev_private_owner = args->pgmap_owner,
+ .migrate = args
+ };
args->start &= PAGE_MASK;
args->end &= PAGE_MASK;
@@ -759,17 +769,19 @@ int migrate_vma_setup(struct migrate_vma *args)
args->cpages = 0;
args->npages = 0;
- migrate_vma_collect(args);
+ if (args->flags & MIGRATE_VMA_FAULT)
+ range.default_flags |= HMM_PFN_REQ_FAULT;
+
+ ret = hmm_range_fault(&range);
- if (args->cpages)
- migrate_vma_unmap(args);
+ migrate_hmm_range_setup(&range);
/*
* At this point pages are locked and unmapped, and thus they have
* stable content and can safely be copied to destination memory that
* is allocated by the drivers.
*/
- return 0;
+ return ret;
}
EXPORT_SYMBOL(migrate_vma_setup);
@@ -1489,3 +1501,64 @@ int migrate_device_coherent_folio(struct folio *folio)
return 0;
return -EBUSY;
}
+
+void migrate_hmm_range_setup(struct hmm_range *range)
+{
+
+ struct migrate_vma *migrate = range->migrate;
+
+ if (!migrate)
+ return;
+
+ migrate->npages = (migrate->end - migrate->start) >> PAGE_SHIFT;
+ migrate->cpages = 0;
+
+ for (unsigned long i = 0; i < migrate->npages; i++) {
+
+ unsigned long pfn = range->hmm_pfns[i];
+
+ pfn &= ~HMM_PFN_INOUT_FLAGS;
+
+ /*
+ *
+ * Don't do migration if valid and migrate flags are not both set.
+ *
+ */
+ if ((pfn & (HMM_PFN_VALID | HMM_PFN_MIGRATE)) !=
+ (HMM_PFN_VALID | HMM_PFN_MIGRATE)) {
+ migrate->src[i] = 0;
+ migrate->dst[i] = 0;
+ continue;
+ }
+
+ migrate->cpages++;
+
+ /*
+ *
+ * The zero page is encoded in a special way, valid and migrate is
+ * set, and pfn part is zero. Encode specially for migrate also.
+ *
+ */
+ if (pfn == (HMM_PFN_VALID|HMM_PFN_MIGRATE)) {
+ migrate->src[i] = MIGRATE_PFN_MIGRATE;
+ migrate->dst[i] = 0;
+ continue;
+ }
+ if (pfn == (HMM_PFN_VALID|HMM_PFN_MIGRATE|HMM_PFN_COMPOUND)) {
+ migrate->src[i] = MIGRATE_PFN_MIGRATE|MIGRATE_PFN_COMPOUND;
+ migrate->dst[i] = 0;
+ continue;
+ }
+
+ migrate->src[i] = migrate_pfn(page_to_pfn(hmm_pfn_to_page(pfn)))
+ | MIGRATE_PFN_MIGRATE;
+ migrate->src[i] |= (pfn & HMM_PFN_WRITE) ? MIGRATE_PFN_WRITE : 0;
+ migrate->src[i] |= (pfn & HMM_PFN_COMPOUND) ? MIGRATE_PFN_COMPOUND : 0;
+ migrate->dst[i] = 0;
+ }
+
+ if (migrate->cpages)
+ migrate_vma_unmap(migrate);
+
+}
+EXPORT_SYMBOL(migrate_hmm_range_setup);
--
2.50.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH 2/3] mm: add new testcase for the migrate on fault case
2026-01-14 9:19 [PATCH 0/3] Migrate on fault for device pages mpenttil
2026-01-14 9:19 ` [PATCH 1/3] mm: unified hmm fault and migrate device pagewalk paths mpenttil
@ 2026-01-14 9:19 ` mpenttil
2026-01-14 9:19 ` [PATCH 3/3] mm:/migrate_device.c: remove migrate_vma_collect_*() functions mpenttil
2 siblings, 0 replies; 4+ messages in thread
From: mpenttil @ 2026-01-14 9:19 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, Mika Penttilä,
David Hildenbrand, Jason Gunthorpe, Leon Romanovsky,
Alistair Popple, Balbir Singh, Zi Yan, Matthew Brost,
Marco Pagani
From: Mika Penttilä <mpenttil@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Marco Pagani <marpagan@redhat.com>
Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
---
lib/test_hmm.c | 100 ++++++++++++++++++++++++-
lib/test_hmm_uapi.h | 19 ++---
tools/testing/selftests/mm/hmm-tests.c | 54 +++++++++++++
3 files changed, 163 insertions(+), 10 deletions(-)
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 8af169d3873a..b82517cfd616 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -36,6 +36,7 @@
#define DMIRROR_RANGE_FAULT_TIMEOUT 1000
#define DEVMEM_CHUNK_SIZE (256 * 1024 * 1024U)
#define DEVMEM_CHUNKS_RESERVE 16
+#define PFNS_ARRAY_SIZE 64
/*
* For device_private pages, dpage is just a dummy struct page
@@ -145,7 +146,7 @@ static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
HMM_DMIRROR_MEMORY_DEVICE_PRIVATE);
}
-static enum migrate_vma_direction
+static enum migrate_vma_info
dmirror_select_device(struct dmirror *dmirror)
{
return (dmirror->mdevice->zone_device_type ==
@@ -1194,6 +1195,99 @@ static int dmirror_migrate_to_device(struct dmirror *dmirror,
return ret;
}
+static int do_fault_and_migrate(struct dmirror *dmirror, struct hmm_range *range)
+{
+ struct migrate_vma *migrate = range->migrate;
+ int ret;
+
+ mmap_read_lock(dmirror->notifier.mm);
+
+ /* Fault-in pages for migration and update device page table */
+ ret = dmirror_range_fault(dmirror, range);
+
+ pr_debug("Migrating from sys mem to device mem\n");
+ migrate_hmm_range_setup(range);
+
+ dmirror_migrate_alloc_and_copy(migrate, dmirror);
+ migrate_vma_pages(migrate);
+ dmirror_migrate_finalize_and_map(migrate, dmirror);
+ migrate_vma_finalize(migrate);
+
+ mmap_read_unlock(dmirror->notifier.mm);
+ return ret;
+}
+
+static int dmirror_fault_and_migrate_to_device(struct dmirror *dmirror,
+ struct hmm_dmirror_cmd *cmd)
+{
+ unsigned long start, size, end, next;
+ unsigned long src_pfns[PFNS_ARRAY_SIZE] = { 0 };
+ unsigned long dst_pfns[PFNS_ARRAY_SIZE] = { 0 };
+ struct migrate_vma migrate = { 0 };
+ struct hmm_range range = { 0 };
+ struct dmirror_bounce bounce;
+ int ret = 0;
+
+ /* Whole range */
+ start = cmd->addr;
+ size = cmd->npages << PAGE_SHIFT;
+ end = start + size;
+
+ if (!mmget_not_zero(dmirror->notifier.mm)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ migrate.pgmap_owner = dmirror->mdevice;
+ migrate.src = src_pfns;
+ migrate.dst = dst_pfns;
+
+ range.migrate = &migrate;
+ range.hmm_pfns = src_pfns;
+ range.pfn_flags_mask = 0;
+ range.default_flags = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_MIGRATE;
+ range.dev_private_owner = dmirror->mdevice;
+ range.notifier = &dmirror->notifier;
+
+ for (next = start; next < end; next = range.end) {
+ range.start = next;
+ range.end = min(end, next + (PFNS_ARRAY_SIZE << PAGE_SHIFT));
+
+ pr_debug("Fault and migrate range start:%#lx end:%#lx\n",
+ range.start, range.end);
+
+ ret = do_fault_and_migrate(dmirror, &range);
+ if (ret)
+ goto out_mmput;
+ }
+
+ /*
+ * Return the migrated data for verification.
+ * Only for pages in device zone
+ */
+ ret = dmirror_bounce_init(&bounce, start, size);
+ if (ret)
+ goto out_mmput;
+
+ mutex_lock(&dmirror->mutex);
+ ret = dmirror_do_read(dmirror, start, end, &bounce);
+ mutex_unlock(&dmirror->mutex);
+ if (ret == 0) {
+ ret = copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr, bounce.size);
+ if (ret)
+ ret = -EFAULT;
+ }
+
+ cmd->cpages = bounce.cpages;
+ dmirror_bounce_fini(&bounce);
+
+
+out_mmput:
+ mmput(dmirror->notifier.mm);
+out:
+ return ret;
+}
+
static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
unsigned char *perm, unsigned long entry)
{
@@ -1510,6 +1604,10 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
ret = dmirror_migrate_to_device(dmirror, &cmd);
break;
+ case HMM_DMIRROR_MIGRATE_ON_FAULT_TO_DEV:
+ ret = dmirror_fault_and_migrate_to_device(dmirror, &cmd);
+ break;
+
case HMM_DMIRROR_MIGRATE_TO_SYS:
ret = dmirror_migrate_to_system(dmirror, &cmd);
break;
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
index f94c6d457338..0b6e7a419e36 100644
--- a/lib/test_hmm_uapi.h
+++ b/lib/test_hmm_uapi.h
@@ -29,15 +29,16 @@ struct hmm_dmirror_cmd {
};
/* Expose the address space of the calling process through hmm device file */
-#define HMM_DMIRROR_READ _IOWR('H', 0x00, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_WRITE _IOWR('H', 0x01, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_MIGRATE_TO_DEV _IOWR('H', 0x02, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_MIGRATE_TO_SYS _IOWR('H', 0x03, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x04, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_RELEASE _IOWR('H', 0x07, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_FLAGS _IOWR('H', 0x08, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_READ _IOWR('H', 0x00, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_WRITE _IOWR('H', 0x01, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_TO_DEV _IOWR('H', 0x02, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_ON_FAULT_TO_DEV _IOWR('H', 0x03, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_TO_SYS _IOWR('H', 0x04, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x05, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x07, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_RELEASE _IOWR('H', 0x08, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_FLAGS _IOWR('H', 0x09, struct hmm_dmirror_cmd)
#define HMM_DMIRROR_FLAG_FAIL_ALLOC (1ULL << 0)
diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c
index e8328c89d855..c75616875c9e 100644
--- a/tools/testing/selftests/mm/hmm-tests.c
+++ b/tools/testing/selftests/mm/hmm-tests.c
@@ -277,6 +277,13 @@ static int hmm_migrate_sys_to_dev(int fd,
return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_DEV, buffer, npages);
}
+static int hmm_migrate_on_fault_sys_to_dev(int fd,
+ struct hmm_buffer *buffer,
+ unsigned long npages)
+{
+ return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_ON_FAULT_TO_DEV, buffer, npages);
+}
+
static int hmm_migrate_dev_to_sys(int fd,
struct hmm_buffer *buffer,
unsigned long npages)
@@ -1034,6 +1041,53 @@ TEST_F(hmm, migrate)
hmm_buffer_free(buffer);
}
+
+/*
+ * Fault and migrate anonymous memory to device private memory.
+ */
+TEST_F(hmm, migrate_on_fault)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned long i;
+ int *ptr;
+ int ret;
+
+ npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+ ASSERT_NE(npages, 0);
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(size);
+ ASSERT_NE(buffer->mirror, NULL);
+
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ buffer->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Initialize buffer in system memory. */
+ for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+ ptr[i] = i;
+
+ /* Fault and migrate memory to device. */
+ ret = hmm_migrate_on_fault_sys_to_dev(self->fd, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device read. */
+ for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+ ASSERT_EQ(ptr[i], i);
+
+ hmm_buffer_free(buffer);
+}
+
/*
* Migrate anonymous memory to device private memory and fault some of it back
* to system memory, then try migrating the resulting mix of system and device
--
2.50.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH 3/3] mm:/migrate_device.c: remove migrate_vma_collect_*() functions
2026-01-14 9:19 [PATCH 0/3] Migrate on fault for device pages mpenttil
2026-01-14 9:19 ` [PATCH 1/3] mm: unified hmm fault and migrate device pagewalk paths mpenttil
2026-01-14 9:19 ` [PATCH 2/3] mm: add new testcase for the migrate on fault case mpenttil
@ 2026-01-14 9:19 ` mpenttil
2 siblings, 0 replies; 4+ messages in thread
From: mpenttil @ 2026-01-14 9:19 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, Mika Penttilä,
David Hildenbrand, Jason Gunthorpe, Leon Romanovsky,
Alistair Popple, Balbir Singh, Zi Yan, Matthew Brost
From: Mika Penttilä <mpenttil@redhat.com>
With the unified fault handling and migrate path,
the migrate_vma_collect_*() functions are unused,
let's remove them.
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
---
mm/migrate_device.c | 508 --------------------------------------------
1 file changed, 508 deletions(-)
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index d89efdfca8f6..c8f5a0615a5e 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -18,514 +18,6 @@
#include <asm/tlbflush.h>
#include "internal.h"
-static int migrate_vma_collect_skip(unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
-{
- struct migrate_vma *migrate = walk->private;
- unsigned long addr;
-
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->dst[migrate->npages] = 0;
- migrate->src[migrate->npages++] = 0;
- }
-
- return 0;
-}
-
-static int migrate_vma_collect_hole(unsigned long start,
- unsigned long end,
- __always_unused int depth,
- struct mm_walk *walk)
-{
- struct migrate_vma *migrate = walk->private;
- unsigned long addr;
-
- /* Only allow populating anonymous memory. */
- if (!vma_is_anonymous(walk->vma))
- return migrate_vma_collect_skip(start, end, walk);
-
- if (thp_migration_supported() &&
- (migrate->flags & MIGRATE_VMA_SELECT_COMPOUND) &&
- (IS_ALIGNED(start, HPAGE_PMD_SIZE) &&
- IS_ALIGNED(end, HPAGE_PMD_SIZE))) {
- migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE |
- MIGRATE_PFN_COMPOUND;
- migrate->dst[migrate->npages] = 0;
- migrate->npages++;
- migrate->cpages++;
-
- /*
- * Collect the remaining entries as holes, in case we
- * need to split later
- */
- return migrate_vma_collect_skip(start + PAGE_SIZE, end, walk);
- }
-
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
- migrate->dst[migrate->npages] = 0;
- migrate->npages++;
- migrate->cpages++;
- }
-
- return 0;
-}
-
-/**
- * migrate_vma_split_folio() - Helper function to split a THP folio
- * @folio: the folio to split
- * @fault_page: struct page associated with the fault if any
- *
- * Returns 0 on success
- */
-static int migrate_vma_split_folio(struct folio *folio,
- struct page *fault_page)
-{
- int ret;
- struct folio *fault_folio = fault_page ? page_folio(fault_page) : NULL;
- struct folio *new_fault_folio = NULL;
-
- if (folio != fault_folio) {
- folio_get(folio);
- folio_lock(folio);
- }
-
- ret = split_folio(folio);
- if (ret) {
- if (folio != fault_folio) {
- folio_unlock(folio);
- folio_put(folio);
- }
- return ret;
- }
-
- new_fault_folio = fault_page ? page_folio(fault_page) : NULL;
-
- /*
- * 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) {
- if (new_fault_folio != fault_folio) {
- folio_get(new_fault_folio);
- folio_lock(new_fault_folio);
- }
- folio_unlock(folio);
- folio_put(folio);
- }
-
- return 0;
-}
-
-/** migrate_vma_collect_huge_pmd - collect THP pages without splitting the
- * folio for device private pages.
- * @pmdp: pointer to pmd entry
- * @start: start address of the range for migration
- * @end: end address of the range for migration
- * @walk: mm_walk callback structure
- * @fault_folio: folio associated with the fault if any
- *
- * Collect the huge pmd entry at @pmdp for migration and set the
- * MIGRATE_PFN_COMPOUND flag in the migrate src entry to indicate that
- * migration will occur at HPAGE_PMD granularity
- */
-static int migrate_vma_collect_huge_pmd(pmd_t *pmdp, unsigned long start,
- unsigned long end, struct mm_walk *walk,
- struct folio *fault_folio)
-{
- struct mm_struct *mm = walk->mm;
- struct folio *folio;
- struct migrate_vma *migrate = walk->private;
- spinlock_t *ptl;
- int ret;
- unsigned long write = 0;
-
- ptl = pmd_lock(mm, pmdp);
- if (pmd_none(*pmdp)) {
- spin_unlock(ptl);
- return migrate_vma_collect_hole(start, end, -1, walk);
- }
-
- if (pmd_trans_huge(*pmdp)) {
- if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) {
- spin_unlock(ptl);
- return migrate_vma_collect_skip(start, end, walk);
- }
-
- folio = pmd_folio(*pmdp);
- if (is_huge_zero_folio(folio)) {
- spin_unlock(ptl);
- return migrate_vma_collect_hole(start, end, -1, walk);
- }
- if (pmd_write(*pmdp))
- write = MIGRATE_PFN_WRITE;
- } else if (!pmd_present(*pmdp)) {
- const softleaf_t entry = softleaf_from_pmd(*pmdp);
-
- folio = softleaf_to_folio(entry);
-
- if (!softleaf_is_device_private(entry) ||
- !(migrate->flags & MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
- (folio->pgmap->owner != migrate->pgmap_owner)) {
- spin_unlock(ptl);
- return migrate_vma_collect_skip(start, end, walk);
- }
-
- if (softleaf_is_migration(entry)) {
- migration_entry_wait_on_locked(entry, ptl);
- spin_unlock(ptl);
- return -EAGAIN;
- }
-
- if (softleaf_is_device_private_write(entry))
- write = MIGRATE_PFN_WRITE;
- } else {
- spin_unlock(ptl);
- return -EAGAIN;
- }
-
- folio_get(folio);
- if (folio != fault_folio && unlikely(!folio_trylock(folio))) {
- spin_unlock(ptl);
- folio_put(folio);
- return migrate_vma_collect_skip(start, end, walk);
- }
-
- if (thp_migration_supported() &&
- (migrate->flags & MIGRATE_VMA_SELECT_COMPOUND) &&
- (IS_ALIGNED(start, HPAGE_PMD_SIZE) &&
- IS_ALIGNED(end, HPAGE_PMD_SIZE))) {
-
- struct page_vma_mapped_walk pvmw = {
- .ptl = ptl,
- .address = start,
- .pmd = pmdp,
- .vma = walk->vma,
- };
-
- unsigned long pfn = page_to_pfn(folio_page(folio, 0));
-
- migrate->src[migrate->npages] = migrate_pfn(pfn) | write
- | MIGRATE_PFN_MIGRATE
- | MIGRATE_PFN_COMPOUND;
- migrate->dst[migrate->npages++] = 0;
- migrate->cpages++;
- ret = set_pmd_migration_entry(&pvmw, folio_page(folio, 0));
- if (ret) {
- migrate->npages--;
- migrate->cpages--;
- migrate->src[migrate->npages] = 0;
- migrate->dst[migrate->npages] = 0;
- goto fallback;
- }
- migrate_vma_collect_skip(start + PAGE_SIZE, end, walk);
- spin_unlock(ptl);
- return 0;
- }
-
-fallback:
- spin_unlock(ptl);
- if (!folio_test_large(folio))
- goto done;
- ret = split_folio(folio);
- if (fault_folio != folio)
- folio_unlock(folio);
- folio_put(folio);
- if (ret)
- return migrate_vma_collect_skip(start, end, walk);
- if (pmd_none(pmdp_get_lockless(pmdp)))
- return migrate_vma_collect_hole(start, end, -1, walk);
-
-done:
- return -ENOENT;
-}
-
-static int migrate_vma_collect_pmd(pmd_t *pmdp,
- unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
-{
- struct migrate_vma *migrate = walk->private;
- struct vm_area_struct *vma = walk->vma;
- struct mm_struct *mm = vma->vm_mm;
- unsigned long addr = start, unmapped = 0;
- spinlock_t *ptl;
- struct folio *fault_folio = migrate->fault_page ?
- page_folio(migrate->fault_page) : NULL;
- pte_t *ptep;
-
-again:
- if (pmd_trans_huge(*pmdp) || !pmd_present(*pmdp)) {
- int ret = migrate_vma_collect_huge_pmd(pmdp, start, end, walk, fault_folio);
-
- if (ret == -EAGAIN)
- goto again;
- if (ret == 0)
- return 0;
- }
-
- ptep = pte_offset_map_lock(mm, pmdp, start, &ptl);
- if (!ptep)
- goto again;
- arch_enter_lazy_mmu_mode();
- ptep += (addr - start) / PAGE_SIZE;
-
- for (; addr < end; addr += PAGE_SIZE, ptep++) {
- struct dev_pagemap *pgmap;
- unsigned long mpfn = 0, pfn;
- struct folio *folio;
- struct page *page;
- softleaf_t entry;
- pte_t pte;
-
- pte = ptep_get(ptep);
-
- if (pte_none(pte)) {
- if (vma_is_anonymous(vma)) {
- mpfn = MIGRATE_PFN_MIGRATE;
- migrate->cpages++;
- }
- goto next;
- }
-
- if (!pte_present(pte)) {
- /*
- * Only care about unaddressable device page special
- * page table entry. Other special swap entries are not
- * migratable, and we ignore regular swapped page.
- */
- entry = softleaf_from_pte(pte);
- if (!softleaf_is_device_private(entry))
- goto next;
-
- page = softleaf_to_page(entry);
- pgmap = page_pgmap(page);
- if (!(migrate->flags &
- MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
- pgmap->owner != migrate->pgmap_owner)
- goto next;
-
- folio = page_folio(page);
- if (folio_test_large(folio)) {
- int ret;
-
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(ptep, ptl);
- ret = migrate_vma_split_folio(folio,
- migrate->fault_page);
-
- if (ret) {
- if (unmapped)
- flush_tlb_range(walk->vma, start, end);
-
- return migrate_vma_collect_skip(addr, end, walk);
- }
-
- goto again;
- }
-
- mpfn = migrate_pfn(page_to_pfn(page)) |
- MIGRATE_PFN_MIGRATE;
- if (softleaf_is_device_private_write(entry))
- mpfn |= MIGRATE_PFN_WRITE;
- } else {
- pfn = pte_pfn(pte);
- if (is_zero_pfn(pfn) &&
- (migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) {
- mpfn = MIGRATE_PFN_MIGRATE;
- migrate->cpages++;
- goto next;
- }
- page = vm_normal_page(migrate->vma, addr, pte);
- if (page && !is_zone_device_page(page) &&
- !(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) {
- goto next;
- } else if (page && is_device_coherent_page(page)) {
- pgmap = page_pgmap(page);
-
- if (!(migrate->flags &
- MIGRATE_VMA_SELECT_DEVICE_COHERENT) ||
- pgmap->owner != migrate->pgmap_owner)
- goto next;
- }
- folio = page ? page_folio(page) : NULL;
- if (folio && folio_test_large(folio)) {
- int ret;
-
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(ptep, ptl);
- ret = migrate_vma_split_folio(folio,
- migrate->fault_page);
-
- if (ret) {
- if (unmapped)
- flush_tlb_range(walk->vma, start, end);
-
- return migrate_vma_collect_skip(addr, end, walk);
- }
-
- goto again;
- }
- mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
- mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
- }
-
- if (!page || !page->mapping) {
- mpfn = 0;
- goto next;
- }
-
- /*
- * By getting a reference on the folio we pin it and that blocks
- * any kind of migration. Side effect is that it "freezes" the
- * pte.
- *
- * We drop this reference after isolating the folio from the lru
- * for non device folio (device folio are not on the lru and thus
- * can't be dropped from it).
- */
- folio = page_folio(page);
- folio_get(folio);
-
- /*
- * We rely on folio_trylock() to avoid deadlock between
- * concurrent migrations where each is waiting on the others
- * folio lock. If we can't immediately lock the folio we fail this
- * migration as it is only best effort anyway.
- *
- * If we can lock the folio it's safe to set up a migration entry
- * now. In the common case where the folio is mapped once in a
- * single process setting up the migration entry now is an
- * optimisation to avoid walking the rmap later with
- * try_to_migrate().
- */
- if (fault_folio == folio || folio_trylock(folio)) {
- bool anon_exclusive;
- pte_t swp_pte;
-
- flush_cache_page(vma, addr, pte_pfn(pte));
- anon_exclusive = folio_test_anon(folio) &&
- PageAnonExclusive(page);
- if (anon_exclusive) {
- pte = ptep_clear_flush(vma, addr, ptep);
-
- if (folio_try_share_anon_rmap_pte(folio, page)) {
- set_pte_at(mm, addr, ptep, pte);
- if (fault_folio != folio)
- folio_unlock(folio);
- folio_put(folio);
- mpfn = 0;
- goto next;
- }
- } else {
- pte = ptep_get_and_clear(mm, addr, ptep);
- }
-
- migrate->cpages++;
-
- /* Set the dirty flag on the folio now the pte is gone. */
- if (pte_dirty(pte))
- folio_mark_dirty(folio);
-
- /* Setup special migration page table entry */
- if (mpfn & MIGRATE_PFN_WRITE)
- entry = make_writable_migration_entry(
- page_to_pfn(page));
- else if (anon_exclusive)
- entry = make_readable_exclusive_migration_entry(
- page_to_pfn(page));
- else
- entry = make_readable_migration_entry(
- page_to_pfn(page));
- if (pte_present(pte)) {
- if (pte_young(pte))
- entry = make_migration_entry_young(entry);
- if (pte_dirty(pte))
- entry = make_migration_entry_dirty(entry);
- }
- swp_pte = swp_entry_to_pte(entry);
- if (pte_present(pte)) {
- if (pte_soft_dirty(pte))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_uffd_wp(pte))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- } else {
- if (pte_swp_soft_dirty(pte))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_swp_uffd_wp(pte))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- }
- set_pte_at(mm, addr, ptep, swp_pte);
-
- /*
- * This is like regular unmap: we remove the rmap and
- * drop the folio refcount. The folio won't be freed, as
- * we took a reference just above.
- */
- folio_remove_rmap_pte(folio, page, vma);
- folio_put(folio);
-
- if (pte_present(pte))
- unmapped++;
- } else {
- folio_put(folio);
- mpfn = 0;
- }
-
-next:
- migrate->dst[migrate->npages] = 0;
- migrate->src[migrate->npages++] = mpfn;
- }
-
- /* Only flush the TLB if we actually modified any entries */
- if (unmapped)
- flush_tlb_range(walk->vma, start, end);
-
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(ptep - 1, ptl);
-
- return 0;
-}
-
-static const struct mm_walk_ops migrate_vma_walk_ops = {
- .pmd_entry = migrate_vma_collect_pmd,
- .pte_hole = migrate_vma_collect_hole,
- .walk_lock = PGWALK_RDLOCK,
-};
-
-/*
- * migrate_vma_collect() - collect pages over a range of virtual addresses
- * @migrate: migrate struct containing all migration information
- *
- * This will walk the CPU page table. For each virtual address backed by a
- * valid page, it updates the src array and takes a reference on the page, in
- * order to pin the page until we lock it and unmap it.
- */
-static void migrate_vma_collect(struct migrate_vma *migrate)
-{
- struct mmu_notifier_range range;
-
- /*
- * Note that the pgmap_owner is passed to the mmu notifier callback so
- * that the registered device driver can skip invalidating device
- * private page mappings that won't be migrated.
- */
- mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0,
- migrate->vma->vm_mm, migrate->start, migrate->end,
- migrate->pgmap_owner);
- mmu_notifier_invalidate_range_start(&range);
-
- walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end,
- &migrate_vma_walk_ops, migrate);
-
- mmu_notifier_invalidate_range_end(&range);
- migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT);
-}
-
/*
* migrate_vma_check_page() - check if page is pinned or not
* @page: struct page to check
--
2.50.0
^ permalink raw reply [flat|nested] 4+ messages in thread