+ rdma-umem-use-hmm_range_fault_unlocked_timeout-for-odp-faults.patch added to mm-unstable branch

The patch titled
     Subject: RDMA/umem: use hmm_range_fault_unlocked_timeout() for ODP faults
has been added to the -mm mm-unstable branch.  Its filename is
     rdma-umem-use-hmm_range_fault_unlocked_timeout-for-odp-faults.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/rdma-umem-use-hmm_range_fault_unlocked_timeout-for-odp-faults.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Stanislav Kinsburskii <[email protected]>
Subject: RDMA/umem: use hmm_range_fault_unlocked_timeout() for ODP faults
Date: Thu, 23 Jul 2026 10:36:38 -0700

ib_umem_odp_map_dma_and_lock() takes mmap_read_lock() only around
hmm_range_fault(), then retries -EBUSY until HMM_RANGE_DEFAULT_TIMEOUT
expires.

Use hmm_range_fault_unlocked_timeout() instead.  The HMM helper now owns
the mmap lock and refreshes range->notifier_seq for its internal retries. 
ODP keeps using HMM_RANGE_DEFAULT_TIMEOUT for each HMM fault attempt,
while interval invalidation retries continue to be handled by the existing
outer loop.

ODP still validates the interval notifier sequence while holding
umem_mutex before DMA mapping pages.

Link: https://lore.kernel.org/[email protected]
Signed-off-by: Stanislav Kinsburskii <[email protected]>
Reviewed-by: Jason Gunthorpe <[email protected]>
Cc: Danilo Krummrich <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Dexuan Cui <[email protected]>
Cc: Haiyang Zhang <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: K. Y. Srinivasan <[email protected]>
Cc: Leon Romanovsky <[email protected]>
Cc: Liam R. Howlett <[email protected]>
Cc: Lizhi Hou <[email protected]>
Cc: Long Li <[email protected]>
Cc: Lorenzo Stoakes <[email protected]>
Cc: Lyude <[email protected]>
Cc: Maarten Lankhorst <[email protected]>
Cc: Maxime Ripard <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Oded Gabbay <[email protected]>
Cc: Shuah Khan <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Thomas Zimemrmann <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Wei Liu <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
---

 drivers/infiniband/core/umem_odp.c |   18 +++++-------------
 1 file changed, 5 insertions(+), 13 deletions(-)

--- a/drivers/infiniband/core/umem_odp.c~rdma-umem-use-hmm_range_fault_unlocked_timeout-for-odp-faults
+++ a/drivers/infiniband/core/umem_odp.c
@@ -329,7 +329,7 @@ int ib_umem_odp_map_dma_and_lock(struct
 	struct mm_struct *owning_mm = umem_odp->umem.owning_mm;
 	int pfn_index, dma_index, ret = 0, start_idx;
 	unsigned int page_shift, hmm_order, pfn_start_idx;
-	unsigned long num_pfns, current_seq;
+	unsigned long num_pfns;
 	struct hmm_range range = {};
 	unsigned long timeout;
 
@@ -363,26 +363,18 @@ int ib_umem_odp_map_dma_and_lock(struct
 	}
 
 	range.hmm_pfns = &(umem_odp->map.pfn_list[pfn_start_idx]);
-	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+	timeout = msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 
 retry:
-	current_seq = range.notifier_seq =
-		mmu_interval_read_begin(&umem_odp->notifier);
-
-	mmap_read_lock(owning_mm);
-	ret = hmm_range_fault(&range);
-	mmap_read_unlock(owning_mm);
-	if (unlikely(ret)) {
-		if (ret == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
+	ret = hmm_range_fault_unlocked_timeout(&range, timeout);
+	if (unlikely(ret))
 		goto out_put_mm;
-	}
 
 	start_idx = (range.start - ib_umem_start(umem_odp)) >> page_shift;
 	dma_index = start_idx;
 
 	mutex_lock(&umem_odp->umem_mutex);
-	if (mmu_interval_read_retry(&umem_odp->notifier, current_seq)) {
+	if (mmu_interval_read_retry(&umem_odp->notifier, range.notifier_seq)) {
 		mutex_unlock(&umem_odp->umem_mutex);
 		goto retry;
 	}
_

Patches currently in -mm which might be from [email protected] are

mm-hmm-move-page-fault-handling-out-of-walk-callbacks.patch
mm-hmm-add-hmm_range_fault_unlocked_timeout-for-mmap-lock-drop-support.patch
selftests-mm-add-hmm-test-for-mmap-lock-dropping-faults.patch
mshv-use-hmm_range_fault_unlocked_timeout-for-region-faults.patch
drm-nouveau-use-hmm_range_fault_unlocked_timeout-for-svm-faults.patch
rdma-umem-use-hmm_range_fault_unlocked_timeout-for-odp-faults.patch
accel-amdxdna-use-hmm_range_fault_unlocked_timeout-for-range-population.patch
drm-gpusvm-use-hmm_range_fault_unlocked_timeout-for-range-faults.patch