Merge tag 'for-linus-7.2a-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:

 - rename function parameters and a comment related to
   xen_exchange_memory() (Jan Beulich)

 - replace __ASSEMBLY__ with __ASSEMBLER__ (Thomas Huth)

 - add some sanity checking to the Xen pvcalls frontend driver (Michael
   Bommarito)

 - fix error handling in the Xen gntdev driver (Wentao Liang)

 - fix several minor bugs in Xen related drivers (Yousef Alhouseen)

* tag 'for-linus-7.2a-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/Xen: correct commentary and parameter naming of xen_exchange_memory()
  xenbus: reject unterminated directory replies
  xen/gntalloc: validate grant count before allocation
  xen/gntalloc: make grant counters unsigned
  xen/front-pgdir-shbuf: free grant reference head on errors
  xen/gntdev: fix error handling in ioctl
  xen: Replace __ASSEMBLY__ with __ASSEMBLER__ in header files
  xen/pvcalls: bound backend response req_id before indexing rsp[]

arch/x86/xen/mmu_pv.c

@@ -2291,18 +2291,19 @@ static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
 }
 
 /*
- * Perform the hypercall to exchange a region of our pfns to point to
- * memory with the required contiguous alignment.  Takes the pfns as
- * input, and populates mfns as output.
+ * Perform the hypercall to exchange a region of our pages to point to memory
+ * with the required contiguous alignment.  Takes as input the mfns to trade
+ * in (mfns_in) and the pfns where the new pages are to appear (fns_inout),
+ * and populates mfns as output (fns_inout).
  *
  * Returns a success code indicating whether the hypervisor was able to
  * satisfy the request or not.
  */
 static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
-			       unsigned long *pfns_in,
+			       unsigned long *mfns_in,
 			       unsigned long extents_out,
 			       unsigned int order_out,
-			       unsigned long *mfns_out,
+			       unsigned long *fns_inout,
 			       unsigned int address_bits)
 {
 	long rc;
@@ -2312,13 +2313,13 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
 		.in = {
 			.nr_extents   = extents_in,
 			.extent_order = order_in,
-			.extent_start = pfns_in,
+			.extent_start = mfns_in,
 			.domid        = DOMID_SELF
 		},
 		.out = {
 			.nr_extents   = extents_out,
 			.extent_order = order_out,
-			.extent_start = mfns_out,
+			.extent_start = fns_inout,
 			.address_bits = address_bits,
 			.domid        = DOMID_SELF
 		}

drivers/xen/gntalloc.c

@@ -70,14 +70,14 @@
 #include <xen/gntalloc.h>
 #include <xen/events.h>
 
-static int limit = 1024;
-module_param(limit, int, 0644);
+static unsigned int limit = 1024;
+module_param(limit, uint, 0644);
 MODULE_PARM_DESC(limit, "Maximum number of grants that may be allocated by "
 		"the gntalloc device");
 
 static LIST_HEAD(gref_list);
 static DEFINE_MUTEX(gref_mutex);
-static int gref_size;
+static unsigned int gref_size;
 
 struct notify_info {
 	uint16_t pgoff:12;    /* Bits 0-11: Offset of the byte to clear */
@@ -272,6 +272,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 	int rc = 0;
 	struct ioctl_gntalloc_alloc_gref op;
 	uint32_t *gref_ids;
+	unsigned int limit_snapshot;
 
 	pr_debug("%s: priv %p\n", __func__, priv);
 
@@ -280,6 +281,12 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 		goto out;
 	}
 
+	limit_snapshot = READ_ONCE(limit);
+	if (op.count > limit_snapshot) {
+		rc = -ENOSPC;
+		goto out;
+	}
+
 	gref_ids = kcalloc(op.count, sizeof(gref_ids[0]), GFP_KERNEL);
 	if (!gref_ids) {
 		rc = -ENOMEM;
@@ -292,14 +299,16 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 	 * are about to enforce, removing them here is a good idea.
 	 */
 	do_cleanup();
-	if (gref_size + op.count > limit) {
+	limit_snapshot = READ_ONCE(limit);
+	if (gref_size > limit_snapshot ||
+	    op.count > limit_snapshot - gref_size) {
 		mutex_unlock(&gref_mutex);
 		rc = -ENOSPC;
 		goto out_free;
 	}
 	gref_size += op.count;
 	op.index = priv->index;
-	priv->index += op.count * PAGE_SIZE;
+	priv->index += (uint64_t)op.count * PAGE_SIZE;
 	mutex_unlock(&gref_mutex);
 
 	rc = add_grefs(&op, gref_ids, priv);

drivers/xen/gntdev.c

@@ -670,11 +670,15 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 	mutex_lock(&priv->lock);
 	gntdev_add_map(priv, map);
 	op.index = map->index << PAGE_SHIFT;
-	mutex_unlock(&priv->lock);
 
-	if (copy_to_user(u, &op, sizeof(op)) != 0)
+	if (copy_to_user(u, &op, sizeof(op)) != 0) {
+		list_del(&map->next);
+		mutex_unlock(&priv->lock);
+		gntdev_put_map(priv, map);
 		return -EFAULT;
+	}
 
+	mutex_unlock(&priv->lock);
 	return 0;
 }
 

drivers/xen/pvcalls-front.c

@@ -32,6 +32,7 @@ struct pvcalls_bedata {
 	struct xen_pvcalls_front_ring ring;
 	grant_ref_t ref;
 	int irq;
+	bool disabled;
 
 	struct list_head socket_mappings;
 	spinlock_t socket_lock;
@@ -131,6 +132,20 @@ static inline int get_request(struct pvcalls_bedata *bedata, int *req_id)
 	return 0;
 }
 
+/*
+ * Wait for the backend's response to req_id, or for the frontend to be
+ * disabled because the backend violated the wire protocol. Returns 0 once
+ * the response has arrived, or -EIO if the frontend was disabled.
+ */
+static int pvcalls_front_wait_rsp(struct pvcalls_bedata *bedata, u32 req_id)
+{
+	wait_event(bedata->inflight_req,
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id ||
+		   READ_ONCE(bedata->disabled));
+
+	return READ_ONCE(bedata->disabled) ? -EIO : 0;
+}
+
 static bool pvcalls_front_write_todo(struct sock_mapping *map)
 {
 	struct pvcalls_data_intf *intf = map->active.ring;
@@ -168,7 +183,8 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
 	struct pvcalls_bedata *bedata;
 	struct xen_pvcalls_response *rsp;
 	uint8_t *src, *dst;
-	int req_id = 0, more = 0, done = 0;
+	u32 req_id = 0;
+	int more = 0, done = 0;
 
 	if (dev == NULL)
 		return IRQ_HANDLED;
@@ -179,12 +195,31 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
 		pvcalls_exit();
 		return IRQ_HANDLED;
 	}
+	if (READ_ONCE(bedata->disabled)) {
+		pvcalls_exit();
+		return IRQ_HANDLED;
+	}
 
 again:
 	while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) {
 		rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons);
 
 		req_id = rsp->req_id;
+		if (req_id >= PVCALLS_NR_RSP_PER_RING) {
+			/*
+			 * The backend supplied a req_id that would index
+			 * bedata->rsp[] out of bounds: a protocol violation
+			 * from a malicious or buggy backend. Log once, stop
+			 * trusting this backend and disable the frontend rather
+			 * than silently dropping the response and continuing.
+			 */
+			pr_err_once("pvcalls: backend sent out-of-range req_id %u, disabling frontend\n",
+				    req_id);
+			WRITE_ONCE(bedata->disabled, true);
+			bedata->ring.rsp_cons++;
+			done = 1;
+			break;
+		}
 		if (rsp->cmd == PVCALLS_POLL) {
 			struct sock_mapping *map = (struct sock_mapping *)(uintptr_t)
 						   rsp->u.poll.id;
@@ -217,7 +252,7 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
 	}
 
 	RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more);
-	if (more)
+	if (more && !READ_ONCE(bedata->disabled))
 		goto again;
 	if (done)
 		wake_up(&bedata->inflight_req);
@@ -330,8 +365,11 @@ int pvcalls_front_socket(struct socket *sock)
 	if (notify)
 		notify_remote_via_irq(bedata->irq);
 
-	wait_event(bedata->inflight_req,
-		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+	ret = pvcalls_front_wait_rsp(bedata, req_id);
+	if (ret) {
+		pvcalls_exit();
+		return ret;
+	}
 
 	/* read req_id, then the content */
 	smp_rmb();
@@ -477,8 +515,11 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	if (notify)
 		notify_remote_via_irq(bedata->irq);
 
-	wait_event(bedata->inflight_req,
-		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+	ret = pvcalls_front_wait_rsp(bedata, req_id);
+	if (ret) {
+		pvcalls_exit_sock(sock);
+		return ret;
+	}
 
 	/* read req_id, then the content */
 	smp_rmb();
@@ -711,8 +752,11 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	if (notify)
 		notify_remote_via_irq(bedata->irq);
 
-	wait_event(bedata->inflight_req,
-		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+	ret = pvcalls_front_wait_rsp(bedata, req_id);
+	if (ret) {
+		pvcalls_exit_sock(sock);
+		return ret;
+	}
 
 	/* read req_id, then the content */
 	smp_rmb();
@@ -761,8 +805,11 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	if (notify)
 		notify_remote_via_irq(bedata->irq);
 
-	wait_event(bedata->inflight_req,
-		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+	ret = pvcalls_front_wait_rsp(bedata, req_id);
+	if (ret) {
+		pvcalls_exit_sock(sock);
+		return ret;
+	}
 
 	/* read req_id, then the content */
 	smp_rmb();
@@ -820,6 +867,14 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock,
 		}
 	}
 
+	if (READ_ONCE(bedata->disabled)) {
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		wake_up(&map->passive.inflight_accept_req);
+		pvcalls_exit_sock(sock);
+		return -EIO;
+	}
+
 	map2 = kzalloc_obj(*map2);
 	if (map2 == NULL) {
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
@@ -880,10 +935,18 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock,
 	}
 
 	if (wait_event_interruptible(bedata->inflight_req,
-		READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) {
+		READ_ONCE(bedata->rsp[req_id].req_id) == req_id ||
+		READ_ONCE(bedata->disabled))) {
 		pvcalls_exit_sock(sock);
 		return -EINTR;
 	}
+	if (READ_ONCE(bedata->disabled)) {
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		wake_up(&map->passive.inflight_accept_req);
+		pvcalls_exit_sock(sock);
+		return -EIO;
+	}
 	/* read req_id, then the content */
 	smp_rmb();
 
@@ -1054,7 +1117,8 @@ int pvcalls_front_release(struct socket *sock)
 		notify_remote_via_irq(bedata->irq);
 
 	wait_event(bedata->inflight_req,
-		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id ||
+		   READ_ONCE(bedata->disabled));
 
 	if (map->active_socket) {
 		/*

drivers/xen/xen-front-pgdir-shbuf.c

@@ -445,8 +445,10 @@ static int grant_references(struct xen_front_pgdir_shbuf *buf)
 		unsigned long frame;
 
 		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
-		if (cur_ref < 0)
-			return cur_ref;
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			goto out_free_refs;
+		}
 
 		frame = xen_page_to_gfn(virt_to_page(buf->directory +
 						     PAGE_SIZE * i));
@@ -457,11 +459,13 @@ static int grant_references(struct xen_front_pgdir_shbuf *buf)
 	if (buf->ops->grant_refs_for_buffer) {
 		ret = buf->ops->grant_refs_for_buffer(buf, &priv_gref_head, j);
 		if (ret)
-			return ret;
+			goto out_free_refs;
 	}
 
+	ret = 0;
+out_free_refs:
 	gnttab_free_grant_references(priv_gref_head);
-	return 0;
+	return ret;
 }
 
 /*

drivers/xen/xenbus/xenbus_xs.c

@@ -417,6 +417,12 @@ static char **split_strings(char *strings, unsigned int len, unsigned int *num)
 {
 	char *p, **ret;
 
+	if (len && strings[len - 1]) {
+		pr_err_once("malformed XS_DIRECTORY reply\n");
+		kfree(strings);
+		return ERR_PTR(-EIO);
+	}
+
 	/* Count the strings. */
 	*num = count_strings(strings, len);
 

include/xen/interface/xen-mca.h

@@ -50,7 +50,7 @@
 /* OUT: There was no machine check data to fetch. */
 #define XEN_MC_NODATA		0x2
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* vIRQ injected to Dom0 */
 #define VIRQ_MCA VIRQ_ARCH_0
 
@@ -388,5 +388,5 @@ struct xen_mce_log {
 #define MCE_GET_LOG_LEN      _IOR('M', 2, int)
 #define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __XEN_PUBLIC_ARCH_X86_MCA_H__ */

include/xen/interface/xen.h

@@ -337,7 +337,7 @@
 #define MMUEXT_MARK_SUPER       19
 #define MMUEXT_UNMARK_SUPER     20
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct mmuext_op {
 	unsigned int cmd;
 	union {
@@ -415,7 +415,7 @@ DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
 
 #define MAX_VMASST_TYPE 5
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 typedef uint16_t domid_t;
 
@@ -760,11 +760,11 @@ struct tmem_op {
 
 DEFINE_GUEST_HANDLE(u64);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 /* In assembly code we cannot use C numeric constant suffixes. */
 #define mk_unsigned_long(x) x
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __XEN_PUBLIC_XEN_H__ */