[PATCH 1/3] lib: test_hmm: evict device pages on file close to avoid use-after-free

[Alistair Popple <apopple@nvidia.com>]

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.

Fixes: b2ef9f5a5cb3 ("mm/hmm/test: add selftest driver for HMM")
Reported-by: Zenghui Yu <zenghui.yu@linux.dev>
Closes: https://lore.kernel.org/linux-mm/8bd0396a-8997-4d2e-a13f-5aac033083d7@linux.dev/
Signed-off-by: Alistair Popple <apopple@nvidia.com>

---

Note that I wasn't able to replicate the exact crash in [1] although I
replicated something similar. So I haven't been able to verify this
fixes the crash conclusively, but it should.

[1] https://lore.kernel.org/linux-mm/8bd0396a-8997-4d2e-a13f-5aac033083d7@linux.dev/
---
 lib/test_hmm.c | 112 +++++++++++++++++++++++++++----------------------
 1 file changed, 62 insertions(+), 50 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 0964d53365e6..79fe7d233df1 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -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)
 {
-- 
2.53.0