Commit 744dd977 authored by Alistair Popple's avatar Alistair Popple Committed by Andrew Morton
Browse files

lib: test_hmm: evict device pages on file close to avoid use-after-free 

Patch series "Minor hmm_test fixes and cleanups".

Two bugfixes a cleanup for the HMM kernel selftests.  These were mostly
reported by Zenghui Yu with special thanks to Lorenzo for analysing and
pointing out the problems.


This patch (of 3):

When dmirror_fops_release() is called it frees the dmirror struct but
doesn't migrate device private pages back to system memory first.  This
leaves those pages with a dangling zone_device_data pointer to the freed
dmirror.

If a subsequent fault occurs on those pages (eg.  during coredump) the
dmirror_devmem_fault() callback dereferences the stale pointer causing a
kernel panic.  This was reported [1] when running mm/ksft_hmm.sh on arm64,
where a test failure triggered SIGABRT and the resulting coredump walked
the VMAs faulting in the stale device private pages.

Fix this by calling dmirror_device_evict_chunk() for each devmem chunk in
dmirror_fops_release() to migrate all device private pages back to system
memory before freeing the dmirror struct.  The function is moved earlier
in the file to avoid a forward declaration.

Link: https://lore.kernel.org/20260331063445.3551404-1-apopple@nvidia.com
Link: https://lore.kernel.org/20260331063445.3551404-2-apopple@nvidia.com


Fixes: b2ef9f5a ("mm/hmm/test: add selftest driver for HMM")
Signed-off-by: default avatarAlistair Popple <apopple@nvidia.com>
Reported-by: default avatarZenghui Yu <zenghui.yu@linux.dev>
Closes: https://lore.kernel.org/linux-mm/8bd0396a-8997-4d2e-a13f-5aac033083d7@linux.dev/


Reviewed-by: default avatarBalbir Singh <balbirs@nvidia.com>
Tested-by: default avatarZenghui Yu <zenghui.yu@linux.dev>
Cc: David Hildenbrand <david@kernel.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zenghui Yu <zenghui.yu@linux.dev>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 047a6d49

lib/test_hmm.c

+62 −50
Original line number Diff line number Diff line
@@ -185,11 +185,73 @@ static int dmirror_fops_open(struct inode *inode, struct file *filp) 
	return 0;

}



static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk)

{

	unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT;

	unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT;

	unsigned long npages = end_pfn - start_pfn + 1;

	unsigned long i;

	unsigned long *src_pfns;

	unsigned long *dst_pfns;

	unsigned int order = 0;



	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);

	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);



	migrate_device_range(src_pfns, start_pfn, npages);

	for (i = 0; i < npages; i++) {

		struct page *dpage, *spage;



		spage = migrate_pfn_to_page(src_pfns[i]);

		if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE))

			continue;



		if (WARN_ON(!is_device_private_page(spage) &&

			    !is_device_coherent_page(spage)))

			continue;



		order = folio_order(page_folio(spage));

		spage = BACKING_PAGE(spage);

		if (src_pfns[i] & MIGRATE_PFN_COMPOUND) {

			dpage = folio_page(folio_alloc(GFP_HIGHUSER_MOVABLE,

					      order), 0);

		} else {

			dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL);

			order = 0;

		}



		/* TODO Support splitting here */

		lock_page(dpage);

		dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));

		if (src_pfns[i] & MIGRATE_PFN_WRITE)

			dst_pfns[i] |= MIGRATE_PFN_WRITE;

		if (order)

			dst_pfns[i] |= MIGRATE_PFN_COMPOUND;

		folio_copy(page_folio(dpage), page_folio(spage));

	}

	migrate_device_pages(src_pfns, dst_pfns, npages);

	migrate_device_finalize(src_pfns, dst_pfns, npages);

	kvfree(src_pfns);

	kvfree(dst_pfns);

}



static int dmirror_fops_release(struct inode *inode, struct file *filp)

{

	struct dmirror *dmirror = filp->private_data;

	struct dmirror_device *mdevice = dmirror->mdevice;

	int i;



	mmu_interval_notifier_remove(&dmirror->notifier);



	if (mdevice->devmem_chunks) {

		for (i = 0; i < mdevice->devmem_count; i++) {

			struct dmirror_chunk *devmem =

				mdevice->devmem_chunks[i];



			dmirror_device_evict_chunk(devmem);

		}

	}



	xa_destroy(&dmirror->pt);

	kfree(dmirror);

	return 0;
@@ -1377,56 +1439,6 @@ static int dmirror_snapshot(struct dmirror *dmirror, 
	return ret;

}



static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk)

{

	unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT;

	unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT;

	unsigned long npages = end_pfn - start_pfn + 1;

	unsigned long i;

	unsigned long *src_pfns;

	unsigned long *dst_pfns;

	unsigned int order = 0;



	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);

	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);



	migrate_device_range(src_pfns, start_pfn, npages);

	for (i = 0; i < npages; i++) {

		struct page *dpage, *spage;



		spage = migrate_pfn_to_page(src_pfns[i]);

		if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE))

			continue;



		if (WARN_ON(!is_device_private_page(spage) &&

			    !is_device_coherent_page(spage)))

			continue;



		order = folio_order(page_folio(spage));

		spage = BACKING_PAGE(spage);

		if (src_pfns[i] & MIGRATE_PFN_COMPOUND) {

			dpage = folio_page(folio_alloc(GFP_HIGHUSER_MOVABLE,

					      order), 0);

		} else {

			dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL);

			order = 0;

		}



		/* TODO Support splitting here */

		lock_page(dpage);

		dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));

		if (src_pfns[i] & MIGRATE_PFN_WRITE)

			dst_pfns[i] |= MIGRATE_PFN_WRITE;

		if (order)

			dst_pfns[i] |= MIGRATE_PFN_COMPOUND;

		folio_copy(page_folio(dpage), page_folio(spage));

	}

	migrate_device_pages(src_pfns, dst_pfns, npages);

	migrate_device_finalize(src_pfns, dst_pfns, npages);

	kvfree(src_pfns);

	kvfree(dst_pfns);

}



/* Removes free pages from the free list so they can't be re-allocated */

static void dmirror_remove_free_pages(struct dmirror_chunk *devmem)

{