mm/memory.c: fix race when faulting a device private page

mainline inclusion
from mainline-v6.1-rc1
commit 16ce101d
category: bugfix
bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5VZ0L
CVE: CVE-2022-3523

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=16ce101db85db694a91380aa4c89b25530871d33

--------------------------------

Patch series "Fix several device private page reference counting issues",
v2

This series aims to fix a number of page reference counting issues in
drivers dealing with device private ZONE_DEVICE pages.  These result in
use-after-free type bugs, either from accessing a struct page which no
longer exists because it has been removed or accessing fields within the
struct page which are no longer valid because the page has been freed.

During normal usage it is unlikely these will cause any problems.  However
without these fixes it is possible to crash the kernel from userspace.
These crashes can be triggered either by unloading the kernel module or
unbinding the device from the driver prior to a userspace task exiting.
In modules such as Nouveau it is also possible to trigger some of these
issues by explicitly closing the device file-descriptor prior to the task
exiting and then accessing device private memory.

This involves some minor changes to both PowerPC and AMD GPU code.
Unfortunately I lack hardware to test either of those so any help there
would be appreciated.  The changes mimic what is done in for both Nouveau
and hmm-tests though so I doubt they will cause problems.

This patch (of 8):

When the CPU tries to access a device private page the migrate_to_ram()
callback associated with the pgmap for the page is called.  However no
reference is taken on the faulting page.  Therefore a concurrent migration
of the device private page can free the page and possibly the underlying
pgmap.  This results in a race which can crash the kernel due to the
migrate_to_ram() function pointer becoming invalid.  It also means drivers
can't reliably read the zone_device_data field because the page may have
been freed with memunmap_pages().

Close the race by getting a reference on the page while holding the ptl to
ensure it has not been freed.  Unfortunately the elevated reference count
will cause the migration required to handle the fault to fail.  To avoid
this failure pass the faulting page into the migrate_vma functions so that
if an elevated reference count is found it can be checked to see if it's
expected or not.

[mpe@ellerman.id.au: fix build]
  Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au
Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com
Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.comSigned-off-by: NAlistair Popple <apopple@nvidia.com>
Acked-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Conflicts:
	arch/powerpc/kvm/book3s_hv_uvmem.c
	include/linux/migrate.h
	lib/test_hmm.c
	mm/migrate.c
Signed-off-by: NMa Wupeng <mawupeng1@huawei.com>
Reviewed-by: Ntong tiangen <tongtiangen@huawei.com>
Reviewed-by: NXiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

arch/powerpc/kvm/book3s_hv_uvmem.c

@@ -506,10 +506,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 		unsigned long start,
 		unsigned long end, unsigned long page_shift,
-		struct kvm *kvm, unsigned long gpa)
+		struct kvm *kvm, unsigned long gpa, struct page *fault_page)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
+	struct migrate_vma mig = { 0 };
 	struct page *dpage, *spage;
 	struct kvmppc_uvmem_page_pvt *pvt;
 	unsigned long pfn;
@@ -523,6 +523,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 	mig.dst = &dst_pfn;
 	mig.pgmap_owner = &kvmppc_uvmem_pgmap;
 	mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+	mig.fault_page = fault_page;
 
 	/* The requested page is already paged-out, nothing to do */
 	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
@@ -578,12 +579,14 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
 				      unsigned long start, unsigned long end,
 				      unsigned long page_shift,
-				      struct kvm *kvm, unsigned long gpa)
+				      struct kvm *kvm, unsigned long gpa,
+				      struct page *fault_page)
 {
 	int ret;
 
 	mutex_lock(&kvm->arch.uvmem_lock);
-	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa,
+				fault_page);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 
 	return ret;
@@ -632,7 +635,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			pvt->remove_gfn = true;
 
 			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
-						  PAGE_SHIFT, kvm, pvt->gpa))
+						  PAGE_SHIFT, kvm, pvt->gpa, NULL))
 				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
 				       pvt->gpa, addr);
 		} else {
@@ -735,7 +738,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma,
 		bool pagein)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
+	struct migrate_vma mig = { 0 };
 	struct page *spage;
 	unsigned long pfn;
 	struct page *dpage;
@@ -993,7 +996,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 
 	if (kvmppc_svm_page_out(vmf->vma, vmf->address,
 				vmf->address + PAGE_SIZE, PAGE_SHIFT,
-				pvt->kvm, pvt->gpa))
+				pvt->kvm, pvt->gpa, vmf->page))
 		return VM_FAULT_SIGBUS;
 	else
 		return 0;
@@ -1064,7 +1067,7 @@ kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa,
 	if (!vma || vma->vm_start > start || vma->vm_end < end)
 		goto out;
 
-	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa))
+	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, NULL))
 		ret = H_SUCCESS;
 out:
 	mmap_read_unlock(kvm->mm);

include/linux/migrate.h

@@ -36,6 +36,9 @@ extern const char *migrate_reason_names[MR_TYPES];
 #ifdef CONFIG_MIGRATION
 
 extern void putback_movable_pages(struct list_head *l);
+extern int migrate_page_extra(struct address_space *mapping,
+			      struct page *newpage, struct page *page,
+			      enum migrate_mode mode, int extra_count);
 extern int migrate_page(struct address_space *mapping,
 			struct page *newpage, struct page *page,
 			enum migrate_mode mode);
@@ -190,6 +193,12 @@ struct migrate_vma {
 	 */
 	void			*pgmap_owner;
 	unsigned long		flags;
+
+	/*
+	 * Set to vmf->page if this is being called to migrate a page as part of
+	 * a migrate_to_ram() callback.
+	 */
+	struct page		*fault_page;
 };
 
 int migrate_vma_setup(struct migrate_vma *args);

lib/test_hmm.c

@@ -671,7 +671,7 @@ static int dmirror_migrate(struct dmirror *dmirror,
 	unsigned long src_pfns[64];
 	unsigned long dst_pfns[64];
 	struct dmirror_bounce bounce;
-	struct migrate_vma args;
+	struct migrate_vma args = { 0 };
 	unsigned long next;
 	int ret;
 
@@ -1048,7 +1048,7 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
-	struct migrate_vma args;
+	struct migrate_vma args = { 0 };
 	unsigned long src_pfns;
 	unsigned long dst_pfns;
 	struct page *rpage;
@@ -1071,6 +1071,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	args.dst = &dst_pfns;
 	args.pgmap_owner = dmirror->mdevice;
 	args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+	args.fault_page = vmf->page;
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;

mm/memory.c

@@ -3383,7 +3383,21 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 					     vmf->address);
 		} else if (is_device_private_entry(entry)) {
 			vmf->page = device_private_entry_to_page(entry);
-			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
+			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+					vmf->address, &vmf->ptl);
+			if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
+				spin_unlock(vmf->ptl);
+				goto out;
+			}
+
+			/*
+			 * Get a page reference while we know the page can't be
+			 * freed.
+			 */
+			get_page(vmf->page);
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			vmf->page->pgmap->ops->migrate_to_ram(vmf);
+			put_page(vmf->page);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
 		} else {

mm/migrate.c

@@ -689,21 +689,15 @@ EXPORT_SYMBOL(migrate_page_copy);
  *                    Migration functions
  ***********************************************************/
 
-/*
- * Common logic to directly migrate a single LRU page suitable for
- * pages that do not use PagePrivate/PagePrivate2.
- *
- * Pages are locked upon entry and exit.
- */
-int migrate_page(struct address_space *mapping,
+int migrate_page_extra(struct address_space *mapping,
 		struct page *newpage, struct page *page,
-		enum migrate_mode mode)
+		enum migrate_mode mode, int extra_count)
 {
 	int rc;
 
 	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page, 0);
+	rc = migrate_page_move_mapping(mapping, newpage, page, extra_count);
 
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
@@ -714,6 +708,19 @@ int migrate_page(struct address_space *mapping,
 		migrate_page_states(newpage, page);
 	return MIGRATEPAGE_SUCCESS;
 }
+
+/*
+ * Common logic to directly migrate a single LRU page suitable for
+ * pages that do not use PagePrivate/PagePrivate2.
+ *
+ * Pages are locked upon entry and exit.
+ */
+int migrate_page(struct address_space *mapping,
+		struct page *newpage, struct page *page,
+		enum migrate_mode mode)
+{
+	return migrate_page_extra(mapping, newpage, page, mode, 0);
+}
 EXPORT_SYMBOL(migrate_page);
 
 #ifdef CONFIG_BLOCK
@@ -2524,14 +2531,14 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
  * migrate_page_move_mapping(), except that here we allow migration of a
  * ZONE_DEVICE page.
  */
-static bool migrate_vma_check_page(struct page *page)
+static bool migrate_vma_check_page(struct page *page, struct page *fault_page)
 {
 	/*
 	 * One extra ref because caller holds an extra reference, either from
 	 * isolate_lru_page() for a regular page, or migrate_vma_collect() for
 	 * a device page.
 	 */
-	int extra = 1;
+	int extra = 1 + (page == fault_page);
 
 	/*
 	 * FIXME support THP (transparent huge page), it is bit more complex to
@@ -2639,7 +2646,7 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
 			put_page(page);
 		}
 
-		if (!migrate_vma_check_page(page)) {
+		if (!migrate_vma_check_page(page, migrate->fault_page)) {
 			if (remap) {
 				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 				migrate->cpages--;
@@ -2707,7 +2714,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
 				goto restore;
 		}
 
-		if (migrate_vma_check_page(page))
+		if (migrate_vma_check_page(page, migrate->fault_page))
 			continue;
 
 restore:
@@ -2817,6 +2824,8 @@ int migrate_vma_setup(struct migrate_vma *args)
 		return -EINVAL;
 	if (!args->src || !args->dst)
 		return -EINVAL;
+	if (args->fault_page && !is_device_private_page(args->fault_page))
+		return -EINVAL;
 
 	memset(args->src, 0, sizeof(*args->src) * nr_pages);
 	args->cpages = 0;
@@ -3047,7 +3056,12 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 			}
 		}
 
-		r = migrate_page(mapping, newpage, page, MIGRATE_SYNC_NO_COPY);
+		if (migrate->fault_page == page)
+			r = migrate_page_extra(mapping, newpage, page,
+					       MIGRATE_SYNC_NO_COPY, 1);
+		else
+			r = migrate_page(mapping, newpage, page,
+					 MIGRATE_SYNC_NO_COPY);
 		if (r != MIGRATEPAGE_SUCCESS)
 			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 	}