When automatic NUMA balancing marks a PTE or PMD as protnone
(PAGE_NONE), hmm_pte_need_fault() requests a fault to restore access
permissions, including _PAGE_RW when write access is needed.

Calling handle_mm_fault() from hmm_do_fault() currently triggers NUMA
balancing in do_numa_page() and do_huge_pmd_numa_page(). When
hmm_range_fault() runs from a device driver or kworker context (such as
a GPU SVM or userptr rebind worker), folios get migrated toward the CPU
node executing the remote fault.

Also, each folio migration invokes try_to_migrate_one() ->
mmu_notifier_invalidate_range_start(), which invalidates the
caller's mmu_interval_notifier while holding mmap_lock. That causes
hmm_range_fault() to abort with -EBUSY after every 2 MiB PMD and exhaust
its retry timeout on large buffers, which has been observed with large
imported Xe userptr buffers.

Add FAULT_FLAG_NO_NUMA and set it in hmm_do_fault() so protnone entries
restore PTE/PMD permissions in-place without performing NUMA balancing,
matching GUP's default !FOLL_HONOR_NUMA_FAULT behaviour.

Signed-off-by: Matthew Auld <[email protected]>
Cc: Thomas Hellström <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Mika Penttilä <[email protected]>
Cc: Leon Romanovsky <[email protected]>
Cc: Jason Gunthorpe <[email protected]>
---
 include/linux/mm.h       | 3 ++-
 include/linux/mm_types.h | 3 +++
 mm/hmm.c                 | 2 +-
 mm/huge_memory.c         | 3 +++
 mm/memory.c              | 3 +++
 5 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 77b5d450fe45..4b6ad3c0b591 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -717,7 +717,8 @@ static inline bool fault_flag_allow_retry_first(enum 
fault_flag flags)
        { FAULT_FLAG_REMOTE,            "REMOTE" }, \
        { FAULT_FLAG_INSTRUCTION,       "INSTRUCTION" }, \
        { FAULT_FLAG_INTERRUPTIBLE,     "INTERRUPTIBLE" }, \
-       { FAULT_FLAG_VMA_LOCK,          "VMA_LOCK" }
+       { FAULT_FLAG_VMA_LOCK,          "VMA_LOCK" }, \
+       { FAULT_FLAG_NO_NUMA,           "NO_NUMA" }
 
 /*
  * vm_fault is filled by the pagefault handler and passed to the vma's
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1ed35d258d2e..2ea71c1bb170 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1819,6 +1819,8 @@ enum tlb_flush_reason {
  * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached.
  *                        We should only access orig_pte if this flag set.
  * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock.
+ * @FAULT_FLAG_NO_NUMA: Do not perform NUMA balancing migration or NUMA
+ *                      task access accounting on protnone faults.
  *
  * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
  * whether we would allow page faults to retry by specifying these two
@@ -1857,6 +1859,7 @@ enum fault_flag {
        FAULT_FLAG_UNSHARE =            1 << 10,
        FAULT_FLAG_ORIG_PTE_VALID =     1 << 11,
        FAULT_FLAG_VMA_LOCK =           1 << 12,
+       FAULT_FLAG_NO_NUMA =            1 << 13,
 };
 
 typedef unsigned int __bitwise zap_flags_t;
diff --git a/mm/hmm.c b/mm/hmm.c
index 2f1e98c6b644..62cdeb071781 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -648,7 +648,7 @@ static int hmm_do_fault(struct mm_struct *mm,
        unsigned long addr = hmm_vma_walk->last;
        unsigned long end = hmm_vma_walk->end;
        unsigned int required_fault = hmm_vma_walk->required_fault;
-       unsigned int fault_flags = FAULT_FLAG_REMOTE;
+       unsigned int fault_flags = FAULT_FLAG_REMOTE | FAULT_FLAG_NO_NUMA;
        struct vm_area_struct *vma;
 
        if (hmm_vma_walk->locked)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0d589be136d2..ea380bf45df0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2361,6 +2361,9 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
        if (!folio)
                goto out_map;
 
+       if (vmf->flags & FAULT_FLAG_NO_NUMA)
+               goto out_map;
+
        nid = folio_nid(folio);
 
        target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable,
diff --git a/mm/memory.c b/mm/memory.c
index fe72e66c9c2e..53c819a6e49a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6404,6 +6404,9 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
        if (!folio || folio_is_zone_device(folio))
                goto out_map;
 
+       if (vmf->flags & FAULT_FLAG_NO_NUMA)
+               goto out_map;
+
        nid = folio_nid(folio);
        nr_pages = folio_nr_pages(folio);
 

---
base-commit: 4318887a3efa4c53d6f083ccfd7105b809a3ac65
change-id: 20261112-numa-3649f4bf57c9

Reply via email to