Merge tag 'xsa396-5.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:
 "Several Linux PV device frontends are using the grant table interfaces
  for removing access rights of the backends in ways being subject to
  race conditions, resulting in potential data leaks, data corruption by
  malicious backends, and denial of service triggered by malicious
  backends:

   - blkfront, netfront, scsifront and the gntalloc driver are testing
     whether a grant reference is still in use. If this is not the case,
     they assume that a following removal of the granted access will
     always succeed, which is not true in case the backend has mapped
     the granted page between those two operations.

     As a result the backend can keep access to the memory page of the
     guest no matter how the page will be used after the frontend I/O
     has finished. The xenbus driver has a similar problem, as it
     doesn't check the success of removing the granted access of a
     shared ring buffer.

   - blkfront, netfront, scsifront, usbfront, dmabuf, xenbus, 9p,
     kbdfront, and pvcalls are using a functionality to delay freeing a
     grant reference until it is no longer in use, but the freeing of
     the related data page is not synchronized with dropping the granted
     access.

     As a result the backend can keep access to the memory page even
     after it has been freed and then re-used for a different purpose.

   - netfront will fail a BUG_ON() assertion if it fails to revoke
     access in the rx path.

     This will result in a Denial of Service (DoS) situation of the
     guest which can be triggered by the backend"

* tag 'xsa396-5.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/netfront: react properly to failing gnttab_end_foreign_access_ref()
  xen/gnttab: fix gnttab_end_foreign_access() without page specified
  xen/pvcalls: use alloc/free_pages_exact()
  xen/9p: use alloc/free_pages_exact()
  xen/usb: don't use gnttab_end_foreign_access() in xenhcd_gnttab_done()
  xen: remove gnttab_query_foreign_access()
  xen/gntalloc: don't use gnttab_query_foreign_access()
  xen/scsifront: don't use gnttab_query_foreign_access() for mapped status
  xen/netfront: don't use gnttab_query_foreign_access() for mapped status
  xen/blkfront: don't use gnttab_query_foreign_access() for mapped status
  xen/grant-table: add gnttab_try_end_foreign_access()
  xen/xenbus: don't let xenbus_grant_ring() remove grants in error case

1 files changed, 37 insertions, 26 deletions

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ca71a0585333..03b5fb341e58 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1288,7 +1288,8 @@ free_shadow:
 			rinfo->ring_ref[i] = GRANT_INVALID_REF;
 		}
 	}
-	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
+	free_pages_exact(rinfo->ring.sring,
+			 info->nr_ring_pages * XEN_PAGE_SIZE);
 	rinfo->ring.sring = NULL;
 
 	if (rinfo->irq)
@@ -1372,9 +1373,15 @@ static int blkif_get_final_status(enum blk_req_status s1,
 	return BLKIF_RSP_OKAY;
 }
 
-static bool blkif_completion(unsigned long *id,
-			     struct blkfront_ring_info *rinfo,
-			     struct blkif_response *bret)
+/*
+ * Return values:
+ *  1 response processed.
+ *  0 missing further responses.
+ * -1 error while processing.
+ */
+static int blkif_completion(unsigned long *id,
+			    struct blkfront_ring_info *rinfo,
+			    struct blkif_response *bret)
 {
 	int i = 0;
 	struct scatterlist *sg;
@@ -1397,7 +1404,7 @@ static bool blkif_completion(unsigned long *id,
 
 		/* Wait the second response if not yet here. */
 		if (s2->status < REQ_DONE)
-			return false;
+			return 0;
 
 		bret->status = blkif_get_final_status(s->status,
 						      s2->status);
@@ -1448,42 +1455,43 @@ static bool blkif_completion(unsigned long *id,
 	}
 	/* Add the persistent grant into the list of free grants */
 	for (i = 0; i < num_grant; i++) {
-		if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
+		if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) {
 			/*
 			 * If the grant is still mapped by the backend (the
 			 * backend has chosen to make this grant persistent)
 			 * we add it at the head of the list, so it will be
 			 * reused first.
 			 */
-			if (!info->feature_persistent)
-				pr_alert_ratelimited("backed has not unmapped grant: %u\n",
-						     s->grants_used[i]->gref);
+			if (!info->feature_persistent) {
+				pr_alert("backed has not unmapped grant: %u\n",
+					 s->grants_used[i]->gref);
+				return -1;
+			}
 			list_add(&s->grants_used[i]->node, &rinfo->grants);
 			rinfo->persistent_gnts_c++;
 		} else {
 			/*
-			 * If the grant is not mapped by the backend we end the
-			 * foreign access and add it to the tail of the list,
-			 * so it will not be picked again unless we run out of
-			 * persistent grants.
+			 * If the grant is not mapped by the backend we add it
+			 * to the tail of the list, so it will not be picked
+			 * again unless we run out of persistent grants.
 			 */
-			gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
 			s->grants_used[i]->gref = GRANT_INVALID_REF;
 			list_add_tail(&s->grants_used[i]->node, &rinfo->grants);
 		}
 	}
 	if (s->req.operation == BLKIF_OP_INDIRECT) {
 		for (i = 0; i < INDIRECT_GREFS(num_grant); i++) {
-			if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) {
-				if (!info->feature_persistent)
-					pr_alert_ratelimited("backed has not unmapped grant: %u\n",
-							     s->indirect_grants[i]->gref);
+			if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) {
+				if (!info->feature_persistent) {
+					pr_alert("backed has not unmapped grant: %u\n",
+						 s->indirect_grants[i]->gref);
+					return -1;
+				}
 				list_add(&s->indirect_grants[i]->node, &rinfo->grants);
 				rinfo->persistent_gnts_c++;
 			} else {
 				struct page *indirect_page;
 
-				gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL);
 				/*
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
@@ -1498,7 +1506,7 @@ static bool blkif_completion(unsigned long *id,
 		}
 	}
 
-	return true;
+	return 1;
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -1564,12 +1572,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 		}
 
 		if (bret.operation != BLKIF_OP_DISCARD) {
+			int ret;
+
 			/*
 			 * We may need to wait for an extra response if the
 			 * I/O request is split in 2
 			 */
-			if (!blkif_completion(&id, rinfo, &bret))
+			ret = blkif_completion(&id, rinfo, &bret);
+			if (!ret)
 				continue;
+			if (unlikely(ret < 0))
+				goto err;
 		}
 
 		if (add_id_to_freelist(rinfo, id)) {
@@ -1676,8 +1689,7 @@ static int setup_blkring(struct xenbus_device *dev,
 	for (i = 0; i < info->nr_ring_pages; i++)
 		rinfo->ring_ref[i] = GRANT_INVALID_REF;
 
-	sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH,
-						       get_order(ring_size));
+	sring = alloc_pages_exact(ring_size, GFP_NOIO);
 	if (!sring) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
 		return -ENOMEM;
@@ -1687,7 +1699,7 @@ static int setup_blkring(struct xenbus_device *dev,
 
 	err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref);
 	if (err < 0) {
-		free_pages((unsigned long)sring, get_order(ring_size));
+		free_pages_exact(sring, ring_size);
 		rinfo->ring.sring = NULL;
 		goto fail;
 	}
@@ -2532,11 +2544,10 @@ static void purge_persistent_grants(struct blkfront_info *info)
 		list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants,
 					 node) {
 			if (gnt_list_entry->gref == GRANT_INVALID_REF ||
-			    gnttab_query_foreign_access(gnt_list_entry->gref))
+			    !gnttab_try_end_foreign_access(gnt_list_entry->gref))
 				continue;
 
 			list_del(&gnt_list_entry->node);
-			gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL);
 			rinfo->persistent_gnts_c--;
 			gnt_list_entry->gref = GRANT_INVALID_REF;
 			list_add_tail(&gnt_list_entry->node, &rinfo->grants);