Char/Misc driver fixes for 4.14-rc5

Here are 4 patches to resolve some char/misc driver issues found these
 past weeks.
 
 One of them is a mei bugfix and another is a new mei device id.  There
 is also a hyper-v fix for a reported issue, and a binder issue fix for a
 problem reported by a few people.
 
 All of these have been in my tree for a while, I don't know if
 linux-next is really testing much this month.  But 0-day is happy with
 them :)
 
 Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 -----BEGIN PGP SIGNATURE-----
 
 iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCWeNCTw8cZ3JlZ0Brcm9h
 aC5jb20ACgkQMUfUDdst+ykNOQCgzskhoji+7Fsl+xc3SX/3ntJwoecAnAz5xQIA
 grpH4IOHq/0aPbQj8g3Y
 =F3xc
 -----END PGP SIGNATURE-----

Merge tag 'char-misc-4.14-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver fixes from Greg KH:
 "Here are 4 patches to resolve some char/misc driver issues found these
  past weeks.

  One of them is a mei bugfix and another is a new mei device id. There
  is also a hyper-v fix for a reported issue, and a binder issue fix for
  a problem reported by a few people.

  All of these have been in my tree for a while, I don't know if
  linux-next is really testing much this month. But 0-day is happy with
  them :)"

* tag 'char-misc-4.14-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  binder: fix use-after-free in binder_transaction()
  Drivers: hv: vmbus: Fix bugs in rescind handling
  mei: me: add gemini lake devices id
  mei: always use domain runtime pm callbacks.

drivers/android/binder.c

@@ -2582,6 +2582,48 @@ static bool binder_proc_transaction(struct binder_transaction *t,
 	return true;
 }
 
+/**
+ * binder_get_node_refs_for_txn() - Get required refs on node for txn
+ * @node:         struct binder_node for which to get refs
+ * @proc:         returns @node->proc if valid
+ * @error:        if no @proc then returns BR_DEAD_REPLY
+ *
+ * User-space normally keeps the node alive when creating a transaction
+ * since it has a reference to the target. The local strong ref keeps it
+ * alive if the sending process dies before the target process processes
+ * the transaction. If the source process is malicious or has a reference
+ * counting bug, relying on the local strong ref can fail.
+ *
+ * Since user-space can cause the local strong ref to go away, we also take
+ * a tmpref on the node to ensure it survives while we are constructing
+ * the transaction. We also need a tmpref on the proc while we are
+ * constructing the transaction, so we take that here as well.
+ *
+ * Return: The target_node with refs taken or NULL if no @node->proc is NULL.
+ * Also sets @proc if valid. If the @node->proc is NULL indicating that the
+ * target proc has died, @error is set to BR_DEAD_REPLY
+ */
+static struct binder_node *binder_get_node_refs_for_txn(
+		struct binder_node *node,
+		struct binder_proc **procp,
+		uint32_t *error)
+{
+	struct binder_node *target_node = NULL;
+
+	binder_node_inner_lock(node);
+	if (node->proc) {
+		target_node = node;
+		binder_inc_node_nilocked(node, 1, 0, NULL);
+		binder_inc_node_tmpref_ilocked(node);
+		node->proc->tmp_ref++;
+		*procp = node->proc;
+	} else
+		*error = BR_DEAD_REPLY;
+	binder_node_inner_unlock(node);
+
+	return target_node;
+}
+
 static void binder_transaction(struct binder_proc *proc,
 			       struct binder_thread *thread,
 			       struct binder_transaction_data *tr, int reply,
@@ -2685,43 +2727,35 @@ static void binder_transaction(struct binder_proc *proc,
 			ref = binder_get_ref_olocked(proc, tr->target.handle,
 						     true);
 			if (ref) {
-				binder_inc_node(ref->node, 1, 0, NULL);
+				target_node = binder_get_node_refs_for_txn(
-				target_node = ref->node;
+						ref->node, &target_proc,
+						&return_error);
+			} else {
+				binder_user_error("%d:%d got transaction to invalid handle\n",
+						  proc->pid, thread->pid);
+				return_error = BR_FAILED_REPLY;
 			}
 			binder_proc_unlock(proc);
-			if (target_node == NULL) {
-				binder_user_error("%d:%d got transaction to invalid handle\n",
-					proc->pid, thread->pid);
-				return_error = BR_FAILED_REPLY;
-				return_error_param = -EINVAL;
-				return_error_line = __LINE__;
-				goto err_invalid_target_handle;
-			}
 		} else {
 			mutex_lock(&context->context_mgr_node_lock);
 			target_node = context->binder_context_mgr_node;
-			if (target_node == NULL) {
+			if (target_node)
+				target_node = binder_get_node_refs_for_txn(
+						target_node, &target_proc,
+						&return_error);
+			else
 				return_error = BR_DEAD_REPLY;
-				mutex_unlock(&context->context_mgr_node_lock);
-				return_error_line = __LINE__;
-				goto err_no_context_mgr_node;
-			}
-			binder_inc_node(target_node, 1, 0, NULL);
 			mutex_unlock(&context->context_mgr_node_lock);
 		}
-		e->to_node = target_node->debug_id;
+		if (!target_node) {
-		binder_node_lock(target_node);
+			/*
-		target_proc = target_node->proc;
+			 * return_error is set above
-		if (target_proc == NULL) {
+			 */
-			binder_node_unlock(target_node);
+			return_error_param = -EINVAL;
-			return_error = BR_DEAD_REPLY;
 			return_error_line = __LINE__;
 			goto err_dead_binder;
 		}
-		binder_inner_proc_lock(target_proc);
+		e->to_node = target_node->debug_id;
-		target_proc->tmp_ref++;
-		binder_inner_proc_unlock(target_proc);
-		binder_node_unlock(target_node);
 		if (security_binder_transaction(proc->tsk,
 						target_proc->tsk) < 0) {
 			return_error = BR_FAILED_REPLY;
@@ -3071,6 +3105,8 @@ static void binder_transaction(struct binder_proc *proc,
 	if (target_thread)
 		binder_thread_dec_tmpref(target_thread);
 	binder_proc_dec_tmpref(target_proc);
+	if (target_node)
+		binder_dec_node_tmpref(target_node);
 	/*
 	 * write barrier to synchronize with initialization
 	 * of log entry
@@ -3090,6 +3126,8 @@ err_bad_parent:
 err_copy_data_failed:
 	trace_binder_transaction_failed_buffer_release(t->buffer);
 	binder_transaction_buffer_release(target_proc, t->buffer, offp);
+	if (target_node)
+		binder_dec_node_tmpref(target_node);
 	target_node = NULL;
 	t->buffer->transaction = NULL;
 	binder_alloc_free_buf(&target_proc->alloc, t->buffer);
@@ -3104,13 +3142,14 @@ err_bad_call_stack:
 err_empty_call_stack:
 err_dead_binder:
 err_invalid_target_handle:
-err_no_context_mgr_node:
 	if (target_thread)
 		binder_thread_dec_tmpref(target_thread);
 	if (target_proc)
 		binder_proc_dec_tmpref(target_proc);
-	if (target_node)
+	if (target_node) {
 		binder_dec_node(target_node, 1, 0);
+		binder_dec_node_tmpref(target_node);
+	}
 
 	binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
 		     "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n",

drivers/hv/channel.c

@@ -640,6 +640,7 @@ void vmbus_close(struct vmbus_channel *channel)
 		 */
 		return;
 	}
+	mutex_lock(&vmbus_connection.channel_mutex);
 	/*
 	 * Close all the sub-channels first and then close the
 	 * primary channel.
@@ -648,16 +649,15 @@ void vmbus_close(struct vmbus_channel *channel)
 		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
 		vmbus_close_internal(cur_channel);
 		if (cur_channel->rescind) {
-			mutex_lock(&vmbus_connection.channel_mutex);
+			hv_process_channel_removal(
-			hv_process_channel_removal(cur_channel,
 					   cur_channel->offermsg.child_relid);
-			mutex_unlock(&vmbus_connection.channel_mutex);
 		}
 	}
 	/*
 	 * Now close the primary.
 	 */
 	vmbus_close_internal(channel);
+	mutex_unlock(&vmbus_connection.channel_mutex);
 }
 EXPORT_SYMBOL_GPL(vmbus_close);
 

drivers/hv/channel_mgmt.c

@@ -159,7 +159,7 @@ static void vmbus_rescind_cleanup(struct vmbus_channel *channel)
 
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
-
+	channel->rescind = true;
 	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
 				msglistentry) {
 
@@ -381,14 +381,21 @@ static void vmbus_release_relid(u32 relid)
 		       true);
 }
 
-void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
+void hv_process_channel_removal(u32 relid)
 {
 	unsigned long flags;
-	struct vmbus_channel *primary_channel;
+	struct vmbus_channel *primary_channel, *channel;
 
-	BUG_ON(!channel->rescind);
 	BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
 
+	/*
+	 * Make sure channel is valid as we may have raced.
+	 */
+	channel = relid2channel(relid);
+	if (!channel)
+		return;
+
+	BUG_ON(!channel->rescind);
 	if (channel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(channel->target_cpu,
@@ -515,6 +522,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 	if (!fnew) {
 		if (channel->sc_creation_callback != NULL)
 			channel->sc_creation_callback(newchannel);
+		newchannel->probe_done = true;
 		return;
 	}
 
@@ -834,7 +842,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 {
 	struct vmbus_channel_rescind_offer *rescind;
 	struct vmbus_channel *channel;
-	unsigned long flags;
 	struct device *dev;
 
 	rescind = (struct vmbus_channel_rescind_offer *)hdr;
@@ -873,16 +880,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		return;
 	}
 
-	spin_lock_irqsave(&channel->lock, flags);
-	channel->rescind = true;
-	spin_unlock_irqrestore(&channel->lock, flags);
-
-	/*
-	 * Now that we have posted the rescind state, perform
-	 * rescind related cleanup.
-	 */
-	vmbus_rescind_cleanup(channel);
-
 	/*
 	 * Now wait for offer handling to complete.
 	 */
@@ -901,6 +898,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	if (channel->device_obj) {
 		if (channel->chn_rescind_callback) {
 			channel->chn_rescind_callback(channel);
+			vmbus_rescind_cleanup(channel);
 			return;
 		}
 		/*
@@ -909,6 +907,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		 */
 		dev = get_device(&channel->device_obj->device);
 		if (dev) {
+			vmbus_rescind_cleanup(channel);
 			vmbus_device_unregister(channel->device_obj);
 			put_device(dev);
 		}
@@ -921,16 +920,16 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		 * 1. Close all sub-channels first
 		 * 2. Then close the primary channel.
 		 */
+		mutex_lock(&vmbus_connection.channel_mutex);
+		vmbus_rescind_cleanup(channel);
 		if (channel->state == CHANNEL_OPEN_STATE) {
 			/*
 			 * The channel is currently not open;
 			 * it is safe for us to cleanup the channel.
 			 */
-			mutex_lock(&vmbus_connection.channel_mutex);
+			hv_process_channel_removal(rescind->child_relid);
-			hv_process_channel_removal(channel,
-						channel->offermsg.child_relid);
-			mutex_unlock(&vmbus_connection.channel_mutex);
 		}
+		mutex_unlock(&vmbus_connection.channel_mutex);
 	}
 }
 

drivers/hv/vmbus_drv.c

@@ -768,8 +768,7 @@ static void vmbus_device_release(struct device *device)
 	struct vmbus_channel *channel = hv_dev->channel;
 
 	mutex_lock(&vmbus_connection.channel_mutex);
-	hv_process_channel_removal(channel,
+	hv_process_channel_removal(channel->offermsg.child_relid);
-				   channel->offermsg.child_relid);
 	mutex_unlock(&vmbus_connection.channel_mutex);
 	kfree(hv_dev);
 

drivers/misc/mei/hw-me-regs.h

@@ -127,6 +127,8 @@
 #define MEI_DEV_ID_BXT_M      0x1A9A  /* Broxton M */
 #define MEI_DEV_ID_APL_I      0x5A9A  /* Apollo Lake I */
 
+#define MEI_DEV_ID_GLK        0x319A  /* Gemini Lake */
+
 #define MEI_DEV_ID_KBP        0xA2BA  /* Kaby Point */
 #define MEI_DEV_ID_KBP_2      0xA2BB  /* Kaby Point 2 */
 

drivers/misc/mei/pci-me.c

@@ -93,6 +93,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_GLK, MEI_ME_PCH8_CFG)},
+
 	{MEI_PCI_DEVICE(MEI_DEV_ID_KBP, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, MEI_ME_PCH8_CFG)},
 
@@ -226,12 +228,15 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	/*
-	* For not wake-able HW runtime pm framework
+	 * ME maps runtime suspend/resume to D0i states,
-	* can't be used on pci device level.
+	 * hence we need to go around native PCI runtime service which
-	* Use domain runtime pm callbacks instead.
+	 * eventually brings the device into D3cold/hot state,
-	*/
+	 * but the mei device cannot wake up from D3 unlike from D0i3.
-	if (!pci_dev_run_wake(pdev))
+	 * To get around the PCI device native runtime pm,
-		mei_me_set_pm_domain(dev);
+	 * ME uses runtime pm domain handlers which take precedence
+	 * over the driver's pm handlers.
+	 */
+	mei_me_set_pm_domain(dev);
 
 	if (mei_pg_is_enabled(dev))
 		pm_runtime_put_noidle(&pdev->dev);
@@ -271,8 +276,7 @@ static void mei_me_shutdown(struct pci_dev *pdev)
 	dev_dbg(&pdev->dev, "shutdown\n");
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
+	mei_me_unset_pm_domain(dev);
-		mei_me_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
@@ -300,8 +304,7 @@ static void mei_me_remove(struct pci_dev *pdev)
 	dev_dbg(&pdev->dev, "stop\n");
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
+	mei_me_unset_pm_domain(dev);
-		mei_me_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 

drivers/misc/mei/pci-txe.c

@@ -144,12 +144,14 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	/*
-	* For not wake-able HW runtime pm framework
+	 * TXE maps runtime suspend/resume to own power gating states,
-	* can't be used on pci device level.
+	 * hence we need to go around native PCI runtime service which
-	* Use domain runtime pm callbacks instead.
+	 * eventually brings the device into D3cold/hot state.
-	*/
+	 * But the TXE device cannot wake up from D3 unlike from own
-	if (!pci_dev_run_wake(pdev))
+	 * power gating. To get around PCI device native runtime pm,
-		mei_txe_set_pm_domain(dev);
+	 * TXE uses runtime pm domain handlers which take precedence.
+	 */
+	mei_txe_set_pm_domain(dev);
 
 	pm_runtime_put_noidle(&pdev->dev);
 
@@ -186,8 +188,7 @@ static void mei_txe_shutdown(struct pci_dev *pdev)
 	dev_dbg(&pdev->dev, "shutdown\n");
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
+	mei_txe_unset_pm_domain(dev);
-		mei_txe_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
@@ -215,8 +216,7 @@ static void mei_txe_remove(struct pci_dev *pdev)
 
 	mei_stop(dev);
 
-	if (!pci_dev_run_wake(pdev))
+	mei_txe_unset_pm_domain(dev);
-		mei_txe_unset_pm_domain(dev);
 
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
@@ -318,15 +318,7 @@ static int mei_txe_pm_runtime_suspend(struct device *device)
 	else
 		ret = -EAGAIN;
 
-	/*
+	/* keep irq on we are staying in D0 */
-	 * If everything is okay we're about to enter PCI low
-	 * power state (D3) therefor we need to disable the
-	 * interrupts towards host.
-	 * However if device is not wakeable we do not enter
-	 * D-low state and we need to keep the interrupt kicking
-	 */
-	if (!ret && pci_dev_run_wake(pdev))
-		mei_disable_interrupts(dev);
 
 	dev_dbg(&pdev->dev, "rpm: txe: runtime suspend ret=%d\n", ret);
 

include/linux/hyperv.h

@@ -1403,7 +1403,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
 				const int *srv_version, int srv_vercnt,
 				int *nego_fw_version, int *nego_srv_version);
 
-void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
+void hv_process_channel_removal(u32 relid);
 
 void vmbus_setevent(struct vmbus_channel *channel);
 /*