Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost updates from Michael Tsirkin:
 "Fixes and tweaks:

   - virtio balloon page hinting support

   - vhost scsi control queue

   - misc fixes"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  MAINTAINERS: remove reference to bogus vsock file
  vhost/scsi: Use common handling code in request queue handler
  vhost/scsi: Extract common handling code from control queue handler
  vhost/scsi: Respond to control queue operations
  vhost/scsi: truncate T10 PI iov_iter to prot_bytes
  virtio-balloon: VIRTIO_BALLOON_F_PAGE_POISON
  mm/page_poison: expose page_poisoning_enabled to kernel modules
  virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
  kvm_config: add CONFIG_VIRTIO_MENU

MAINTAINERS

@@ -15858,7 +15858,6 @@ F:	net/vmw_vsock/virtio_transport_common.c
 F:	net/vmw_vsock/virtio_transport.c
 F:	drivers/net/vsockmon.c
 F:	drivers/vhost/vsock.c
-F:	drivers/vhost/vsock.h
 F:	tools/testing/vsock/
 
 VIRTIO CONSOLE DRIVER

drivers/vhost/scsi.c

@@ -203,6 +203,19 @@ struct vhost_scsi {
 	int vs_events_nr; /* num of pending events, protected by vq->mutex */
 };
 
+/*
+ * Context for processing request and control queue operations.
+ */
+struct vhost_scsi_ctx {
+	int head;
+	unsigned int out, in;
+	size_t req_size, rsp_size;
+	size_t out_size, in_size;
+	u8 *target, *lunp;
+	void *req;
+	struct iov_iter out_iter;
+};
+
 static struct workqueue_struct *vhost_scsi_workqueue;
 
 /* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */
@@ -800,24 +813,120 @@ vhost_scsi_send_bad_target(struct vhost_scsi *vs,
 		pr_err("Faulted on virtio_scsi_cmd_resp\n");
 }
 
+static int
+vhost_scsi_get_desc(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+		    struct vhost_scsi_ctx *vc)
+{
+	int ret = -ENXIO;
+
+	vc->head = vhost_get_vq_desc(vq, vq->iov,
+				     ARRAY_SIZE(vq->iov), &vc->out, &vc->in,
+				     NULL, NULL);
+
+	pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
+		 vc->head, vc->out, vc->in);
+
+	/* On error, stop handling until the next kick. */
+	if (unlikely(vc->head < 0))
+		goto done;
+
+	/* Nothing new?  Wait for eventfd to tell us they refilled. */
+	if (vc->head == vq->num) {
+		if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
+			vhost_disable_notify(&vs->dev, vq);
+			ret = -EAGAIN;
+		}
+		goto done;
+	}
+
+	/*
+	 * Get the size of request and response buffers.
+	 * FIXME: Not correct for BIDI operation
+	 */
+	vc->out_size = iov_length(vq->iov, vc->out);
+	vc->in_size = iov_length(&vq->iov[vc->out], vc->in);
+
+	/*
+	 * Copy over the virtio-scsi request header, which for a
+	 * ANY_LAYOUT enabled guest may span multiple iovecs, or a
+	 * single iovec may contain both the header + outgoing
+	 * WRITE payloads.
+	 *
+	 * copy_from_iter() will advance out_iter, so that it will
+	 * point at the start of the outgoing WRITE payload, if
+	 * DMA_TO_DEVICE is set.
+	 */
+	iov_iter_init(&vc->out_iter, WRITE, vq->iov, vc->out, vc->out_size);
+	ret = 0;
+
+done:
+	return ret;
+}
+
+static int
+vhost_scsi_chk_size(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc)
+{
+	if (unlikely(vc->in_size < vc->rsp_size)) {
+		vq_err(vq,
+		       "Response buf too small, need min %zu bytes got %zu",
+		       vc->rsp_size, vc->in_size);
+		return -EINVAL;
+	} else if (unlikely(vc->out_size < vc->req_size)) {
+		vq_err(vq,
+		       "Request buf too small, need min %zu bytes got %zu",
+		       vc->req_size, vc->out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int
+vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
+		   struct vhost_scsi_tpg **tpgp)
+{
+	int ret = -EIO;
+
+	if (unlikely(!copy_from_iter_full(vc->req, vc->req_size,
+					  &vc->out_iter))) {
+		vq_err(vq, "Faulted on copy_from_iter\n");
+	} else if (unlikely(*vc->lunp != 1)) {
+		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
+		vq_err(vq, "Illegal virtio-scsi lun: %u\n", *vc->lunp);
+	} else {
+		struct vhost_scsi_tpg **vs_tpg, *tpg;
+
+		vs_tpg = vq->private_data;	/* validated at handler entry */
+
+		tpg = READ_ONCE(vs_tpg[*vc->target]);
+		if (unlikely(!tpg)) {
+			vq_err(vq, "Target 0x%x does not exist\n", *vc->target);
+		} else {
+			if (tpgp)
+				*tpgp = tpg;
+			ret = 0;
+		}
+	}
+
+	return ret;
+}
+
 static void
 vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 {
 	struct vhost_scsi_tpg **vs_tpg, *tpg;
 	struct virtio_scsi_cmd_req v_req;
 	struct virtio_scsi_cmd_req_pi v_req_pi;
+	struct vhost_scsi_ctx vc;
 	struct vhost_scsi_cmd *cmd;
-	struct iov_iter out_iter, in_iter, prot_iter, data_iter;
+	struct iov_iter in_iter, prot_iter, data_iter;
 	u64 tag;
 	u32 exp_data_len, data_direction;
-	unsigned int out = 0, in = 0;
-	int head, ret, prot_bytes;
-	size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp);
-	size_t out_size, in_size;
+	int ret, prot_bytes;
 	u16 lun;
-	u8 *target, *lunp, task_attr;
+	u8 task_attr;
 	bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
-	void *req, *cdb;
+	void *cdb;
 
 	mutex_lock(&vq->mutex);
 	/*
@@ -828,85 +937,47 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 	if (!vs_tpg)
 		goto out;
 
+	memset(&vc, 0, sizeof(vc));
+	vc.rsp_size = sizeof(struct virtio_scsi_cmd_resp);
+
 	vhost_disable_notify(&vs->dev, vq);
 
 	for (;;) {
-		head = vhost_get_vq_desc(vq, vq->iov,
-					 ARRAY_SIZE(vq->iov), &out, &in,
-					 NULL, NULL);
-		pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
-			 head, out, in);
-		/* On error, stop handling until the next kick. */
-		if (unlikely(head < 0))
-			break;
-		/* Nothing new?  Wait for eventfd to tell us they refilled. */
-		if (head == vq->num) {
-			if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
-				vhost_disable_notify(&vs->dev, vq);
-				continue;
-			}
-			break;
-		}
-		/*
-		 * Check for a sane response buffer so we can report early
-		 * errors back to the guest.
-		 */
-		if (unlikely(vq->iov[out].iov_len < rsp_size)) {
-			vq_err(vq, "Expecting at least virtio_scsi_cmd_resp"
-				" size, got %zu bytes\n", vq->iov[out].iov_len);
-			break;
-		}
+		ret = vhost_scsi_get_desc(vs, vq, &vc);
+		if (ret)
+			goto err;
+
 		/*
 		 * Setup pointers and values based upon different virtio-scsi
 		 * request header if T10_PI is enabled in KVM guest.
 		 */
 		if (t10_pi) {
-			req = &v_req_pi;
-			req_size = sizeof(v_req_pi);
-			lunp = &v_req_pi.lun[0];
-			target = &v_req_pi.lun[1];
+			vc.req = &v_req_pi;
+			vc.req_size = sizeof(v_req_pi);
+			vc.lunp = &v_req_pi.lun[0];
+			vc.target = &v_req_pi.lun[1];
 		} else {
-			req = &v_req;
-			req_size = sizeof(v_req);
-			lunp = &v_req.lun[0];
-			target = &v_req.lun[1];
+			vc.req = &v_req;
+			vc.req_size = sizeof(v_req);
+			vc.lunp = &v_req.lun[0];
+			vc.target = &v_req.lun[1];
 		}
-		/*
-		 * FIXME: Not correct for BIDI operation
-		 */
-		out_size = iov_length(vq->iov, out);
-		in_size = iov_length(&vq->iov[out], in);
 
 		/*
-		 * Copy over the virtio-scsi request header, which for a
-		 * ANY_LAYOUT enabled guest may span multiple iovecs, or a
-		 * single iovec may contain both the header + outgoing
-		 * WRITE payloads.
-		 *
-		 * copy_from_iter() will advance out_iter, so that it will
-		 * point at the start of the outgoing WRITE payload, if
-		 * DMA_TO_DEVICE is set.
+		 * Validate the size of request and response buffers.
+		 * Check for a sane response buffer so we can report
+		 * early errors back to the guest.
 		 */
-		iov_iter_init(&out_iter, WRITE, vq->iov, out, out_size);
+		ret = vhost_scsi_chk_size(vq, &vc);
+		if (ret)
+			goto err;
 
-		if (unlikely(!copy_from_iter_full(req, req_size, &out_iter))) {
-			vq_err(vq, "Faulted on copy_from_iter\n");
-			vhost_scsi_send_bad_target(vs, vq, head, out);
-			continue;
-		}
-		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
-		if (unlikely(*lunp != 1)) {
-			vq_err(vq, "Illegal virtio-scsi lun: %u\n", *lunp);
-			vhost_scsi_send_bad_target(vs, vq, head, out);
-			continue;
-		}
+		ret = vhost_scsi_get_req(vq, &vc, &tpg);
+		if (ret)
+			goto err;
+
+		ret = -EIO;	/* bad target on any error from here on */
 
-		tpg = READ_ONCE(vs_tpg[*target]);
-		if (unlikely(!tpg)) {
-			/* Target does not exist, fail the request */
-			vhost_scsi_send_bad_target(vs, vq, head, out);
-			continue;
-		}
 		/*
 		 * Determine data_direction by calculating the total outgoing
 		 * iovec sizes + incoming iovec sizes vs. virtio-scsi request +
@@ -924,17 +995,17 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		 */
 		prot_bytes = 0;
 
-		if (out_size > req_size) {
+		if (vc.out_size > vc.req_size) {
 			data_direction = DMA_TO_DEVICE;
-			exp_data_len = out_size - req_size;
-			data_iter = out_iter;
-		} else if (in_size > rsp_size) {
+			exp_data_len = vc.out_size - vc.req_size;
+			data_iter = vc.out_iter;
+		} else if (vc.in_size > vc.rsp_size) {
 			data_direction = DMA_FROM_DEVICE;
-			exp_data_len = in_size - rsp_size;
+			exp_data_len = vc.in_size - vc.rsp_size;
 
-			iov_iter_init(&in_iter, READ, &vq->iov[out], in,
-				      rsp_size + exp_data_len);
-			iov_iter_advance(&in_iter, rsp_size);
+			iov_iter_init(&in_iter, READ, &vq->iov[vc.out], vc.in,
+				      vc.rsp_size + exp_data_len);
+			iov_iter_advance(&in_iter, vc.rsp_size);
 			data_iter = in_iter;
 		} else {
 			data_direction = DMA_NONE;
@@ -950,21 +1021,20 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 				if (data_direction != DMA_TO_DEVICE) {
 					vq_err(vq, "Received non zero pi_bytesout,"
 						" but wrong data_direction\n");
-					vhost_scsi_send_bad_target(vs, vq, head, out);
-					continue;
+					goto err;
 				}
 				prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesout);
 			} else if (v_req_pi.pi_bytesin) {
 				if (data_direction != DMA_FROM_DEVICE) {
 					vq_err(vq, "Received non zero pi_bytesin,"
 						" but wrong data_direction\n");
-					vhost_scsi_send_bad_target(vs, vq, head, out);
-					continue;
+					goto err;
 				}
 				prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin);
 			}
 			/*
-			 * Set prot_iter to data_iter, and advance past any
+			 * Set prot_iter to data_iter and truncate it to
+			 * prot_bytes, and advance data_iter past any
 			 * preceeding prot_bytes that may be present.
 			 *
 			 * Also fix up the exp_data_len to reflect only the
@@ -973,6 +1043,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			if (prot_bytes) {
 				exp_data_len -= prot_bytes;
 				prot_iter = data_iter;
+				iov_iter_truncate(&prot_iter, prot_bytes);
 				iov_iter_advance(&data_iter, prot_bytes);
 			}
 			tag = vhost64_to_cpu(vq, v_req_pi.tag);
@@ -996,8 +1067,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			vq_err(vq, "Received SCSI CDB with command_size: %d that"
 				" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
 				scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE);
-			vhost_scsi_send_bad_target(vs, vq, head, out);
-			continue;
+				goto err;
 		}
 		cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
 					 exp_data_len + prot_bytes,
@@ -1005,13 +1075,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		if (IS_ERR(cmd)) {
 			vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
 			       PTR_ERR(cmd));
-			vhost_scsi_send_bad_target(vs, vq, head, out);
-			continue;
+			goto err;
 		}
 		cmd->tvc_vhost = vs;
 		cmd->tvc_vq = vq;
-		cmd->tvc_resp_iov = vq->iov[out];
-		cmd->tvc_in_iovs = in;
+		cmd->tvc_resp_iov = vq->iov[vc.out];
+		cmd->tvc_in_iovs = vc.in;
 
 		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
 			 cmd->tvc_cdb[0], cmd->tvc_lun);
@@ -1019,14 +1088,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			 " %d\n", cmd, exp_data_len, prot_bytes, data_direction);
 
 		if (data_direction != DMA_NONE) {
-			ret = vhost_scsi_mapal(cmd,
-					       prot_bytes, &prot_iter,
-					       exp_data_len, &data_iter);
-			if (unlikely(ret)) {
+			if (unlikely(vhost_scsi_mapal(cmd, prot_bytes,
+						      &prot_iter, exp_data_len,
+						      &data_iter))) {
 				vq_err(vq, "Failed to map iov to sgl\n");
 				vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
-				vhost_scsi_send_bad_target(vs, vq, head, out);
-				continue;
+				goto err;
 			}
 		}
 		/*
@@ -1034,7 +1101,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		 * complete the virtio-scsi request in TCM callback context via
 		 * vhost_scsi_queue_data_in() and vhost_scsi_queue_status()
 		 */
-		cmd->tvc_vq_desc = head;
+		cmd->tvc_vq_desc = vc.head;
 		/*
 		 * Dispatch cmd descriptor for cmwq execution in process
 		 * context provided by vhost_scsi_workqueue.  This also ensures
@@ -1043,6 +1110,166 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		 */
 		INIT_WORK(&cmd->work, vhost_scsi_submission_work);
 		queue_work(vhost_scsi_workqueue, &cmd->work);
+		ret = 0;
+err:
+		/*
+		 * ENXIO:  No more requests, or read error, wait for next kick
+		 * EINVAL: Invalid response buffer, drop the request
+		 * EIO:    Respond with bad target
+		 * EAGAIN: Pending request
+		 */
+		if (ret == -ENXIO)
+			break;
+		else if (ret == -EIO)
+			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+	}
+out:
+	mutex_unlock(&vq->mutex);
+}
+
+static void
+vhost_scsi_send_tmf_reject(struct vhost_scsi *vs,
+			   struct vhost_virtqueue *vq,
+			   struct vhost_scsi_ctx *vc)
+{
+	struct virtio_scsi_ctrl_tmf_resp __user *resp;
+	struct virtio_scsi_ctrl_tmf_resp rsp;
+	int ret;
+
+	pr_debug("%s\n", __func__);
+	memset(&rsp, 0, sizeof(rsp));
+	rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+	resp = vq->iov[vc->out].iov_base;
+	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
+	if (!ret)
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+	else
+		pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
+}
+
+static void
+vhost_scsi_send_an_resp(struct vhost_scsi *vs,
+			struct vhost_virtqueue *vq,
+			struct vhost_scsi_ctx *vc)
+{
+	struct virtio_scsi_ctrl_an_resp __user *resp;
+	struct virtio_scsi_ctrl_an_resp rsp;
+	int ret;
+
+	pr_debug("%s\n", __func__);
+	memset(&rsp, 0, sizeof(rsp));	/* event_actual = 0 */
+	rsp.response = VIRTIO_SCSI_S_OK;
+	resp = vq->iov[vc->out].iov_base;
+	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
+	if (!ret)
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+	else
+		pr_err("Faulted on virtio_scsi_ctrl_an_resp\n");
+}
+
+static void
+vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
+{
+	union {
+		__virtio32 type;
+		struct virtio_scsi_ctrl_an_req an;
+		struct virtio_scsi_ctrl_tmf_req tmf;
+	} v_req;
+	struct vhost_scsi_ctx vc;
+	size_t typ_size;
+	int ret;
+
+	mutex_lock(&vq->mutex);
+	/*
+	 * We can handle the vq only after the endpoint is setup by calling the
+	 * VHOST_SCSI_SET_ENDPOINT ioctl.
+	 */
+	if (!vq->private_data)
+		goto out;
+
+	memset(&vc, 0, sizeof(vc));
+
+	vhost_disable_notify(&vs->dev, vq);
+
+	for (;;) {
+		ret = vhost_scsi_get_desc(vs, vq, &vc);
+		if (ret)
+			goto err;
+
+		/*
+		 * Get the request type first in order to setup
+		 * other parameters dependent on the type.
+		 */
+		vc.req = &v_req.type;
+		typ_size = sizeof(v_req.type);
+
+		if (unlikely(!copy_from_iter_full(vc.req, typ_size,
+						  &vc.out_iter))) {
+			vq_err(vq, "Faulted on copy_from_iter tmf type\n");
+			/*
+			 * The size of the response buffer depends on the
+			 * request type and must be validated against it.
+			 * Since the request type is not known, don't send
+			 * a response.
+			 */
+			continue;
+		}
+
+		switch (v_req.type) {
+		case VIRTIO_SCSI_T_TMF:
+			vc.req = &v_req.tmf;
+			vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req);
+			vc.rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+			vc.lunp = &v_req.tmf.lun[0];
+			vc.target = &v_req.tmf.lun[1];
+			break;
+		case VIRTIO_SCSI_T_AN_QUERY:
+		case VIRTIO_SCSI_T_AN_SUBSCRIBE:
+			vc.req = &v_req.an;
+			vc.req_size = sizeof(struct virtio_scsi_ctrl_an_req);
+			vc.rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+			vc.lunp = &v_req.an.lun[0];
+			vc.target = NULL;
+			break;
+		default:
+			vq_err(vq, "Unknown control request %d", v_req.type);
+			continue;
+		}
+
+		/*
+		 * Validate the size of request and response buffers.
+		 * Check for a sane response buffer so we can report
+		 * early errors back to the guest.
+		 */
+		ret = vhost_scsi_chk_size(vq, &vc);
+		if (ret)
+			goto err;
+
+		/*
+		 * Get the rest of the request now that its size is known.
+		 */
+		vc.req += typ_size;
+		vc.req_size -= typ_size;
+
+		ret = vhost_scsi_get_req(vq, &vc, NULL);
+		if (ret)
+			goto err;
+
+		if (v_req.type == VIRTIO_SCSI_T_TMF)
+			vhost_scsi_send_tmf_reject(vs, vq, &vc);
+		else
+			vhost_scsi_send_an_resp(vs, vq, &vc);
+err:
+		/*
+		 * ENXIO:  No more requests, or read error, wait for next kick
+		 * EINVAL: Invalid response buffer, drop the request
+		 * EIO:    Respond with bad target
+		 * EAGAIN: Pending request
+		 */
+		if (ret == -ENXIO)
+			break;
+		else if (ret == -EIO)
+			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
 	}
 out:
 	mutex_unlock(&vq->mutex);
@@ -1050,7 +1277,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 
 static void vhost_scsi_ctl_handle_kick(struct vhost_work *work)
 {
+	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
+						poll.work);
+	struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);
+
 	pr_debug("%s: The handling func for control queue.\n", __func__);
+	vhost_scsi_ctl_handle_vq(vs, vq);
 }
 
 static void

drivers/virtio/virtio_balloon.c

@@ -41,13 +41,34 @@
 #define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
 #define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
 
+#define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
+					     __GFP_NOMEMALLOC)
+/* The order of free page blocks to report to host */
+#define VIRTIO_BALLOON_FREE_PAGE_ORDER (MAX_ORDER - 1)
+/* The size of a free page block in bytes */
+#define VIRTIO_BALLOON_FREE_PAGE_SIZE \
+	(1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT))
+
 #ifdef CONFIG_BALLOON_COMPACTION
 static struct vfsmount *balloon_mnt;
 #endif
 
+enum virtio_balloon_vq {
+	VIRTIO_BALLOON_VQ_INFLATE,
+	VIRTIO_BALLOON_VQ_DEFLATE,
+	VIRTIO_BALLOON_VQ_STATS,
+	VIRTIO_BALLOON_VQ_FREE_PAGE,
+	VIRTIO_BALLOON_VQ_MAX
+};
+
 struct virtio_balloon {
 	struct virtio_device *vdev;
-	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
+
+	/* Balloon's own wq for cpu-intensive work items */
+	struct workqueue_struct *balloon_wq;
+	/* The free page reporting work item submitted to the balloon wq */
+	struct work_struct report_free_page_work;
 
 	/* The balloon servicing is delegated to a freezable workqueue. */
 	struct work_struct update_balloon_stats_work;
@@ -57,6 +78,18 @@ struct virtio_balloon {
 	spinlock_t stop_update_lock;
 	bool stop_update;
 
+	/* The list of allocated free pages, waiting to be given back to mm */
+	struct list_head free_page_list;
+	spinlock_t free_page_list_lock;
+	/* The number of free page blocks on the above list */
+	unsigned long num_free_page_blocks;
+	/* The cmd id received from host */
+	u32 cmd_id_received;
+	/* The cmd id that is actively in use */
+	__virtio32 cmd_id_active;
+	/* Buffer to store the stop sign */
+	__virtio32 cmd_id_stop;
+
 	/* Waiting for host to ack the pages we released. */
 	wait_queue_head_t acked;
 
@@ -320,17 +353,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
 	virtqueue_kick(vq);
 }
 
-static void virtballoon_changed(struct virtio_device *vdev)
-{
-	struct virtio_balloon *vb = vdev->priv;
-	unsigned long flags;
-
-	spin_lock_irqsave(&vb->stop_update_lock, flags);
-	if (!vb->stop_update)
-		queue_work(system_freezable_wq, &vb->update_balloon_size_work);
-	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-}
-
 static inline s64 towards_target(struct virtio_balloon *vb)
 {
 	s64 target;
@@ -347,6 +369,60 @@ static inline s64 towards_target(struct virtio_balloon *vb)
 	return target - vb->num_pages;
 }
 
+/* Gives back @num_to_return blocks of free pages to mm. */
+static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb,
+					     unsigned long num_to_return)
+{
+	struct page *page;
+	unsigned long num_returned;
+
+	spin_lock_irq(&vb->free_page_list_lock);
+	for (num_returned = 0; num_returned < num_to_return; num_returned++) {
+		page = balloon_page_pop(&vb->free_page_list);
+		if (!page)
+			break;
+		free_pages((unsigned long)page_address(page),
+			   VIRTIO_BALLOON_FREE_PAGE_ORDER);
+	}
+	vb->num_free_page_blocks -= num_returned;
+	spin_unlock_irq(&vb->free_page_list_lock);
+
+	return num_returned;
+}
+
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+	unsigned long flags;
+	s64 diff = towards_target(vb);
+
+	if (diff) {
+		spin_lock_irqsave(&vb->stop_update_lock, flags);
+		if (!vb->stop_update)
+			queue_work(system_freezable_wq,
+				   &vb->update_balloon_size_work);
+		spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		virtio_cread(vdev, struct virtio_balloon_config,
+			     free_page_report_cmd_id, &vb->cmd_id_received);
+		if (vb->cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) {
+			/* Pass ULONG_MAX to give back all the free pages */
+			return_free_pages_to_mm(vb, ULONG_MAX);
+		} else if (vb->cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP &&
+			   vb->cmd_id_received !=
+			   virtio32_to_cpu(vdev, vb->cmd_id_active)) {
+			spin_lock_irqsave(&vb->stop_update_lock, flags);
+			if (!vb->stop_update) {
+				queue_work(vb->balloon_wq,
+					   &vb->report_free_page_work);
+			}
+			spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+		}
+	}
+}
+
 static void update_balloon_size(struct virtio_balloon *vb)
 {
 	u32 actual = vb->num_pages;
@@ -389,26 +465,44 @@ static void update_balloon_size_func(struct work_struct *work)
 
 static int init_vqs(struct virtio_balloon *vb)
 {
-	struct virtqueue *vqs[3];
-	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
-	static const char * const names[] = { "inflate", "deflate", "stats" };
-	int err, nvqs;
+	struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
+	vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
+	const char *names[VIRTIO_BALLOON_VQ_MAX];
+	int err;
 
 	/*
-	 * We expect two virtqueues: inflate and deflate, and
-	 * optionally stat.
+	 * Inflateq and deflateq are used unconditionally. The names[]
+	 * will be NULL if the related feature is not enabled, which will
+	 * cause no allocation for the corresponding virtqueue in find_vqs.
 	 */
-	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
+	callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
+	names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
+	callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
+	names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
+	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
+	names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
+		names[VIRTIO_BALLOON_VQ_STATS] = "stats";
+		callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
+	}
+
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
+		callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+	}
+
+	err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
+					 vqs, callbacks, names, NULL, NULL);
 	if (err)
 		return err;
 
-	vb->inflate_vq = vqs[0];
-	vb->deflate_vq = vqs[1];
+	vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE];
+	vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE];
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
 		struct scatterlist sg;
 		unsigned int num_stats;
-		vb->stats_vq = vqs[2];
+		vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
 
 		/*
 		 * Prime this virtqueue with one buffer so the hypervisor can
@@ -426,9 +520,145 @@ static int init_vqs(struct virtio_balloon *vb)
 		}
 		virtqueue_kick(vb->stats_vq);
 	}
+
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
+
+	return 0;
+}
+
+static int send_cmd_id_start(struct virtio_balloon *vb)
+{
+	struct scatterlist sg;
+	struct virtqueue *vq = vb->free_page_vq;
+	int err, unused;
+
+	/* Detach all the used buffers from the vq */
+	while (virtqueue_get_buf(vq, &unused))
+		;
+
+	vb->cmd_id_active = cpu_to_virtio32(vb->vdev, vb->cmd_id_received);
+	sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
+	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
+	if (!err)
+		virtqueue_kick(vq);
+	return err;
+}
+
+static int send_cmd_id_stop(struct virtio_balloon *vb)
+{
+	struct scatterlist sg;
+	struct virtqueue *vq = vb->free_page_vq;
+	int err, unused;
+
+	/* Detach all the used buffers from the vq */
+	while (virtqueue_get_buf(vq, &unused))
+		;
+
+	sg_init_one(&sg, &vb->cmd_id_stop, sizeof(vb->cmd_id_stop));
+	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_stop, GFP_KERNEL);
+	if (!err)
+		virtqueue_kick(vq);
+	return err;
+}
+
+static int get_free_page_and_send(struct virtio_balloon *vb)
+{
+	struct virtqueue *vq = vb->free_page_vq;
+	struct page *page;
+	struct scatterlist sg;
+	int err, unused;
+	void *p;
+
+	/* Detach all the used buffers from the vq */
+	while (virtqueue_get_buf(vq, &unused))
+		;
+
+	page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG,
+			   VIRTIO_BALLOON_FREE_PAGE_ORDER);
+	/*
+	 * When the allocation returns NULL, it indicates that we have got all
+	 * the possible free pages, so return -EINTR to stop.
+	 */
+	if (!page)
+		return -EINTR;
+
+	p = page_address(page);
+	sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE);
+	/* There is always 1 entry reserved for the cmd id to use. */
+	if (vq->num_free > 1) {
+		err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL);
+		if (unlikely(err)) {
+			free_pages((unsigned long)p,
+				   VIRTIO_BALLOON_FREE_PAGE_ORDER);
+			return err;
+		}
+		virtqueue_kick(vq);
+		spin_lock_irq(&vb->free_page_list_lock);
+		balloon_page_push(&vb->free_page_list, page);
+		vb->num_free_page_blocks++;
+		spin_unlock_irq(&vb->free_page_list_lock);
+	} else {
+		/*
+		 * The vq has no available entry to add this page block, so
+		 * just free it.
+		 */
+		free_pages((unsigned long)p, VIRTIO_BALLOON_FREE_PAGE_ORDER);
+	}
+
+	return 0;
+}
+
+static int send_free_pages(struct virtio_balloon *vb)
+{
+	int err;
+	u32 cmd_id_active;
+
+	while (1) {
+		/*
+		 * If a stop id or a new cmd id was just received from host,
+		 * stop the reporting.
+		 */
+		cmd_id_active = virtio32_to_cpu(vb->vdev, vb->cmd_id_active);
+		if (cmd_id_active != vb->cmd_id_received)
+			break;
+
+		/*
+		 * The free page blocks are allocated and sent to host one by
+		 * one.
+		 */
+		err = get_free_page_and_send(vb);
+		if (err == -EINTR)
+			break;
+		else if (unlikely(err))
+			return err;
+	}
+
 	return 0;
 }
 
+static void report_free_page_func(struct work_struct *work)
+{
+	int err;
+	struct virtio_balloon *vb = container_of(work, struct virtio_balloon,
+						 report_free_page_work);
+	struct device *dev = &vb->vdev->dev;
+
+	/* Start by sending the received cmd id to host with an outbuf. */
+	err = send_cmd_id_start(vb);
+	if (unlikely(err))
+		dev_err(dev, "Failed to send a start id, err = %d\n", err);
+
+	err = send_free_pages(vb);
+	if (unlikely(err))
+		dev_err(dev, "Failed to send a free page, err = %d\n", err);
+
+	/* End by sending a stop id to host with an outbuf. */
+	err = send_cmd_id_stop(vb);
+	if (unlikely(err))
+		dev_err(dev, "Failed to send a stop id, err = %d\n", err);
+}
+
 #ifdef CONFIG_BALLOON_COMPACTION
 /*
  * virtballoon_migratepage - perform the balloon page migration on behalf of
@@ -512,14 +742,23 @@ static struct file_system_type balloon_fs = {
 
 #endif /* CONFIG_BALLOON_COMPACTION */
 
-static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
-						  struct shrink_control *sc)
+static unsigned long shrink_free_pages(struct virtio_balloon *vb,
+				       unsigned long pages_to_free)
 {
-	unsigned long pages_to_free, pages_freed = 0;
-	struct virtio_balloon *vb = container_of(shrinker,
-					struct virtio_balloon, shrinker);
+	unsigned long blocks_to_free, blocks_freed;
 
-	pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;
+	pages_to_free = round_up(pages_to_free,
+				 1 << VIRTIO_BALLOON_FREE_PAGE_ORDER);
+	blocks_to_free = pages_to_free >> VIRTIO_BALLOON_FREE_PAGE_ORDER;
+	blocks_freed = return_free_pages_to_mm(vb, blocks_to_free);
+
+	return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER;
+}
+
+static unsigned long shrink_balloon_pages(struct virtio_balloon *vb,
+					  unsigned long pages_to_free)
+{
+	unsigned long pages_freed = 0;
 
 	/*
 	 * One invocation of leak_balloon can deflate at most
@@ -527,12 +766,33 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
 	 * multiple times to deflate pages till reaching pages_to_free.
 	 */
 	while (vb->num_pages && pages_to_free) {
+		pages_freed += leak_balloon(vb, pages_to_free) /
+					VIRTIO_BALLOON_PAGES_PER_PAGE;
 		pages_to_free -= pages_freed;
-		pages_freed += leak_balloon(vb, pages_to_free);
 	}
 	update_balloon_size(vb);
 
-	return pages_freed / VIRTIO_BALLOON_PAGES_PER_PAGE;
+	return pages_freed;
+}
+
+static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
+						  struct shrink_control *sc)
+{
+	unsigned long pages_to_free, pages_freed = 0;
+	struct virtio_balloon *vb = container_of(shrinker,
+					struct virtio_balloon, shrinker);
+
+	pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;
+
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		pages_freed = shrink_free_pages(vb, pages_to_free);
+
+	if (pages_freed >= pages_to_free)
+		return pages_freed;
+
+	pages_freed += shrink_balloon_pages(vb, pages_to_free - pages_freed);
+
+	return pages_freed;
 }
 
 static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
@@ -540,8 +800,12 @@ static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
 {
 	struct virtio_balloon *vb = container_of(shrinker,
 					struct virtio_balloon, shrinker);
+	unsigned long count;
 
-	return vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
+	count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
+	count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER;
+
+	return count;
 }
 
 static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
@@ -561,6 +825,7 @@ static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
+	__u32 poison_val;
 	int err;
 
 	if (!vdev->config->get) {
@@ -604,6 +869,36 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	}
 	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
 #endif
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		/*
+		 * There is always one entry reserved for cmd id, so the ring
+		 * size needs to be at least two to report free page hints.
+		 */
+		if (virtqueue_get_vring_size(vb->free_page_vq) < 2) {
+			err = -ENOSPC;
+			goto out_del_vqs;
+		}
+		vb->balloon_wq = alloc_workqueue("balloon-wq",
+					WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
+		if (!vb->balloon_wq) {
+			err = -ENOMEM;
+			goto out_del_vqs;
+		}
+		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
+		vb->cmd_id_received = VIRTIO_BALLOON_CMD_ID_STOP;
+		vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
+						  VIRTIO_BALLOON_CMD_ID_STOP);
+		vb->cmd_id_stop = cpu_to_virtio32(vb->vdev,
+						  VIRTIO_BALLOON_CMD_ID_STOP);
+		vb->num_free_page_blocks = 0;
+		spin_lock_init(&vb->free_page_list_lock);
+		INIT_LIST_HEAD(&vb->free_page_list);
+		if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+			memset(&poison_val, PAGE_POISON, sizeof(poison_val));
+			virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+				      poison_val, &poison_val);
+		}
+	}
 	/*
 	 * We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a
 	 * shrinker needs to be registered to relieve memory pressure.
@@ -611,7 +906,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
 		err = virtio_balloon_register_shrinker(vb);
 		if (err)
-			goto out_del_vqs;
+			goto out_del_balloon_wq;
 	}
 	virtio_device_ready(vdev);
 
@@ -619,6 +914,9 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		virtballoon_changed(vdev);
 	return 0;
 
+out_del_balloon_wq:
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		destroy_workqueue(vb->balloon_wq);
 out_del_vqs:
 	vdev->config->del_vqs(vdev);
 out_free_vb:
@@ -652,6 +950,11 @@ static void virtballoon_remove(struct virtio_device *vdev)
 	cancel_work_sync(&vb->update_balloon_size_work);
 	cancel_work_sync(&vb->update_balloon_stats_work);
 
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		cancel_work_sync(&vb->report_free_page_work);
+		destroy_workqueue(vb->balloon_wq);
+	}
+
 	remove_common(vb);
 #ifdef CONFIG_BALLOON_COMPACTION
 	if (vb->vb_dev_info.inode)
@@ -695,6 +998,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
 
 static int virtballoon_validate(struct virtio_device *vdev)
 {
+	if (!page_poisoning_enabled())
+		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+
 	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
 	return 0;
 }
@@ -703,6 +1009,8 @@ static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
 	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
+	VIRTIO_BALLOON_F_FREE_PAGE_HINT,
+	VIRTIO_BALLOON_F_PAGE_POISON,
 };
 
 static struct virtio_driver virtio_balloon_driver = {

include/uapi/linux/virtio_balloon.h

@@ -34,15 +34,23 @@
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
 #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
+#define VIRTIO_BALLOON_F_FREE_PAGE_HINT	3 /* VQ to report free pages */
+#define VIRTIO_BALLOON_F_PAGE_POISON	4 /* Guest is using page poisoning */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
 
+#define VIRTIO_BALLOON_CMD_ID_STOP	0
+#define VIRTIO_BALLOON_CMD_ID_DONE	1
 struct virtio_balloon_config {
 	/* Number of pages host wants Guest to give up. */
 	__u32 num_pages;
 	/* Number of pages we've actually got in balloon. */
 	__u32 actual;
+	/* Free page report command id, readonly by guest */
+	__u32 free_page_report_cmd_id;
+	/* Stores PAGE_POISON if page poisoning is in use */
+	__u32 poison_val;
 };
 
 #define VIRTIO_BALLOON_S_SWAP_IN  0   /* Amount of memory swapped in */

kernel/configs/kvm_guest.config

@@ -20,6 +20,7 @@ CONFIG_PARAVIRT=y
 CONFIG_KVM_GUEST=y
 CONFIG_S390_GUEST=y
 CONFIG_VIRTIO=y
+CONFIG_VIRTIO_MENU=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_BLK=y
 CONFIG_VIRTIO_CONSOLE=y

mm/page_poison.c

@@ -17,6 +17,11 @@ static int __init early_page_poison_param(char *buf)
 }
 early_param("page_poison", early_page_poison_param);
 
+/**
+ * page_poisoning_enabled - check if page poisoning is enabled
+ *
+ * Return true if page poisoning is enabled, or false if not.
+ */
 bool page_poisoning_enabled(void)
 {
 	/*
@@ -29,6 +34,7 @@ bool page_poisoning_enabled(void)
 		(!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
 		debug_pagealloc_enabled()));
 }
+EXPORT_SYMBOL_GPL(page_poisoning_enabled);
 
 static void poison_page(struct page *page)
 {